https://github.com/yeaight7/awesome-ai-devtools
The open-source map of the AI developer tooling ecosystem
https://github.com/yeaight7/awesome-ai-devtools
List: awesome-ai-devtools
ai ai-agents anthropic api awesome awesome-list awesome-lists claude claude-code devtools gemini mcp open-source openai
Last synced: 22 days ago
JSON representation
The open-source map of the AI developer tooling ecosystem
- Host: GitHub
- URL: https://github.com/yeaight7/awesome-ai-devtools
- Owner: yeaight7
- License: mit
- Created: 2026-05-07T19:13:47.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2026-05-29T11:04:12.000Z (24 days ago)
- Last Synced: 2026-05-29T12:28:51.973Z (24 days ago)
- Topics: ai, ai-agents, anthropic, api, awesome, awesome-list, awesome-lists, claude, claude-code, devtools, gemini, mcp, open-source, openai
- Language: TypeScript
- Homepage:
- Size: 8.94 MB
- Stars: 4
- Watchers: 2
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-readme - yeaight7/awesome-ai-devtools - Auto-Generated README built from structured metadata, with a custom SVG header, comparison matrix, category index, tool tables, and review-backed summaries. (Examples)
- ultimate-awesome - awesome-ai-devtools - The open-source map of the AI developer tooling ecosystem. (Other Lists / Vue Lists)
README
# Awesome AI Devtools
The open-source map of the AI developer tooling ecosystem.
Window-shop coding agents, IDE assistants, MCP tooling, evals, observability, security, and self-hosted AI dev stacks.
360 tools 273 reviewed 87 draft 17 active reviewed shelves
## Why this exists
AI developer tooling changes quickly. This directory keeps entries in structured metadata so the public view can stay polished while the data remains sortable, reviewable, and validation-backed.
No rankings. No launch hype. Just a clean storefront for discovering tools worth a closer look.
## Start here
### Agent skills and plugins
- [Agent Powerups](https://github.com/yeaight7/agent-powerups) - Curated skill packs, commands, MCP configs, hooks, templates, and workflows for coding agents.
- [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) - Agent harness performance system with skills, hooks, MCP configs, memory optimization, and cross-harness workflows.
- [Claude Skills](https://github.com/alirezarezvani/claude-skills) - Repository of 232+ Claude Code skills and agent plugins convertible to 12 AI coding tools including Codex, Cursor, and Windsurf.
- [Anthropic Skills](https://github.com/anthropics/skills) - Official public repository of Agent Skills for Claude demonstrating creative, technical, and enterprise workflow patterns.
- [Superpowers](https://github.com/obra/superpowers) - Core skills library for Claude Code with TDD, debugging, collaboration patterns, and systematic problem-solving techniques.
### Open-source coding agents
- [Aider](https://aider.chat/) - Open-source terminal pair programmer that edits tracked files in a local Git repository.
- [Cline](https://docs.cline.bot/introduction/overview) - Open-source coding agent for editor workflows with file edits, terminal commands, browser use, and MCP-based tool extension.
- [OpenCode](https://opencode.ai/) - Open-source AI coding agent for terminal, desktop, IDE, and GitHub repository workflows.
- [OpenHands](https://openhands.dev/) - Open-source software agent platform with GUI, CLI, SDK, and self-hosted or cloud deployment options.
- [Continue](https://docs.continue.dev/) - Open-source AI code assistant and CLI for IDE agents, source-controlled checks, and customizable development workflows.
### Self-hosted AI dev stacks
- [AnythingLLM](https://useanything.com) - Self-hosted RAG and agent platform with no-code agent builder and Docker Compose deployment options.
- [Dify](https://dify.ai) - Open-source LLMOps platform with visual studio for chatbots, workflows, agents, and RAG that supports self-hosted deployment.
- [Onyx](https://onyx.dotenv.dev) - Open-source self-hostable AI platform offering chat UI with agents, RAG, MCP tools, and multi-provider model support.
- [Open WebUI Platform](https://openwebui.com) - Self-hosted AI platform and UI that supports Ollama and OpenAI-compatible APIs and can run entirely offline.
- [Tabby](https://www.tabbyml.com/) - Self-hosted AI coding assistant for teams that want private code assistance and repository-aware development.
### MCP tools
- [Chrome DevTools MCP](https://developer.chrome.com/blog/chrome-devtools-mcp) - MCP server that gives AI agents Chrome DevTools debugging capabilities for web applications.
- [GitHub MCP Server](https://github.com/github/github-mcp-server) - Official GitHub MCP server for repository access, issues, pull requests, code analysis, and workflow automation.
- [Context7 MCP Server](https://context7.com) - MCP server for retrieving up-to-date library documentation and code examples for AI coding assistants.
- [Browserbase MCP Server](https://browserbase.com) - MCP server that lets AI agents control cloud browsers through Browserbase and Stagehand.
- [Agent Powerups](https://github.com/yeaight7/agent-powerups) - Curated skill packs, commands, MCP configs, hooks, templates, and workflows for coding agents.
### Observability and evals
- [Arize Phoenix](https://arize.com/phoenix) - Open-source AI observability platform with tracing, evals, datasets, and experiments for LLM, agent, and RAG systems.
- [Comet Opik](https://www.comet.com) - Open-source LLM observability framework for tracing, evaluating, and monitoring LLM, RAG, and agent workflows.
- [Helicone](https://www.helicone.ai) - Open-source LLM observability platform and gateway for logging, tracing, and evaluating LLM and agent requests.
- [Langfuse](https://langfuse.com/docs) - Open-source LLM engineering platform for observability, tracing, prompt management, datasets, and evaluations.
- [OpenLIT](https://openlit.io) - Open-source OpenTelemetry-native observability and evaluations platform for GenAI and LLM applications.
### Local-first picks
- [Ollama](https://ollama.com) - Local LLM runtime and model manager that runs open models on your machine with an OpenAI-compatible Chat Completions API.
- [LM Studio](https://lmstudio.ai) - Cross-platform desktop app and SDKs to discover, run, and serve local LLMs with an OpenAI-compatible server mode.
- [Llamafile](https://github.com/Mozilla-Ocho/llamafile/blob/main/README.md) - Single-file local LLM runtime bundling llama.cpp and web UI, with an OpenAI-compatible /v1 chat completions endpoint.
- [LocalAI](https://localai.io) - Self-hosted REST server that emulates the OpenAI API to run local ggml/llama.cpp and related models on your own hardware.
- [vLLM](https://vllm.ai) - High-throughput LLM inference engine with an OpenAI-compatible HTTP server for serving models locally or on servers.
## Explore by intent
### Build with agents
[Coding agents](#coding-agents) (27) · [Terminal agents](#terminal-agents) (13) · [IDE assistants](#ide-assistants) (17) · [Browser agents](#browser-agents) (24)
### Extend agents
[MCP servers](#mcp-servers) (15) · [MCP clients](#mcp-clients) (6) · [MCP tooling](#mcp-tooling) (17) · [Agent skill packs](#agent-skill-packs) (30)
### Operate agents
[Agent observability](#agent-observability) (41) · [Agent evals](#agent-evals) (22)
### Run locally/self-host
[Self-hosted AI dev stacks](#self-hosted-ai-dev-stacks) (25) · [Local LLM developer tools](#local-llm-developer-tools) (31)
### Automate repo work
[Repo automation tools](#repo-automation-tools) (27) · [AI code review tools](#ai-code-review-tools) (10) · [Documentation agents](#documentation-agents) (24) · [Test generation agents](#test-generation-agents) (6)
## Comparison Matrix
| Tool | Main shelf | OSS | Local | Self-hosted | CLI | IDE | MCP | Links |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Agent Powerups](https://github.com/yeaight7/agent-powerups) | Agent skill packs | Yes | Yes | No | Yes | No | Yes | [Repo](https://github.com/yeaight7/agent-powerups) |
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | Agent skill packs | Yes | Yes | No | Yes | No | Yes | [Docs](https://github.com/affaan-m/everything-claude-code#readme) / [Repo](https://github.com/affaan-m/everything-claude-code) |
| [Claude Skills](https://github.com/alirezarezvani/claude-skills) | Agent skill packs | Yes | Yes | No | Yes | No | No | [Repo](https://github.com/alirezarezvani/claude-skills) |
| [Anthropic Skills](https://github.com/anthropics/skills) | Agent skill packs | Yes | Yes | No | No | No | No | [Repo](https://github.com/anthropics/skills) |
| [Superpowers](https://github.com/obra/superpowers) | Agent skill packs | Yes | Yes | No | No | No | No | [Repo](https://github.com/obra/superpowers) |
| [Aider](https://aider.chat/) | Coding agents | Yes | Yes | No | Yes | No | No | [Website](https://aider.chat/) / [Docs](https://aider.chat/docs/) / [Repo](https://github.com/Aider-AI/aider) |
| [Cline](https://docs.cline.bot/introduction/overview) | Coding agents | Yes | No | No | Yes | Yes | Yes | [Docs](https://docs.cline.bot/introduction/overview) / [Repo](https://github.com/cline/cline) |
| [OpenCode](https://opencode.ai/) | Coding agents | Yes | Yes | No | Yes | Yes | Yes | [Website](https://opencode.ai/) / [Docs](https://opencode.ai/docs/) / [Repo](https://github.com/anomalyco/opencode) |
| [OpenHands](https://openhands.dev/) | Coding agents | Yes | No | Yes | Yes | No | No | [Website](https://openhands.dev/) / [Docs](https://docs.openhands.dev/overview/quickstart) / [Repo](https://github.com/OpenHands/OpenHands) |
| [Continue](https://docs.continue.dev/) | IDE assistants | Yes | No | No | Yes | Yes | No | [Docs](https://docs.continue.dev/) / [Repo](https://github.com/continuedev/continue) |
| [AnythingLLM](https://useanything.com) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Website](https://useanything.com) / [Docs](https://docs.useanything.com) / [Repo](https://github.com/Mintplex-Labs/anything-llm) |
| [Dify](https://dify.ai) | Self-hosted AI dev stacks | Yes | No | Yes | No | No | No | [Website](https://dify.ai) / [Docs](https://docs.dify.ai) / [Repo](https://github.com/langgenius/dify) |
| [Onyx](https://onyx.dotenv.dev) | Self-hosted AI dev stacks | Yes | Yes | Yes | No | No | Yes | [Website](https://onyx.dotenv.dev) / [Docs](https://github.com/onyx-dot-app/onyx#readme) / [Repo](https://github.com/onyx-dot-app/onyx) |
| [Open WebUI Platform](https://openwebui.com) | Self-hosted AI dev stacks | Yes | Yes | Yes | No | No | No | [Website](https://openwebui.com) / [Docs](https://docs.openwebui.com) / [Repo](https://github.com/open-webui/open-webui) |
| [Tabby](https://www.tabbyml.com/) | Self-hosted AI dev stacks | Yes | No | Yes | No | Yes | No | [Website](https://www.tabbyml.com/) / [Docs](https://tabby.tabbyml.com/docs/) / [Repo](https://github.com/TabbyML/tabby) |
| [Chrome DevTools MCP](https://developer.chrome.com/blog/chrome-devtools-mcp) | MCP servers | Yes | Yes | No | No | No | Yes | [Docs](https://developer.chrome.com/blog/chrome-devtools-mcp) / [Repo](https://github.com/ChromeDevTools/chrome-devtools-mcp) |
| [GitHub MCP Server](https://github.com/github/github-mcp-server) | MCP servers | Yes | No | No | No | No | Yes | [Repo](https://github.com/github/github-mcp-server) |
| [Context7 MCP Server](https://context7.com) | MCP servers | Yes | No | No | No | No | Yes | [Website](https://context7.com) / [Repo](https://github.com/upstash/context7) |
| [Browserbase MCP Server](https://browserbase.com) | MCP servers | Yes | No | No | No | No | Yes | [Website](https://browserbase.com) / [Repo](https://github.com/browserbase/mcp-server-browserbase) |
| [Arize Phoenix](https://arize.com/phoenix) | Agent observability | Yes | No | Yes | No | No | No | [Website](https://arize.com/phoenix) / [Docs](https://arize.com/docs/phoenix) / [Repo](https://github.com/arize-ai/phoenix) |
| [Comet Opik](https://www.comet.com) | Agent observability | Yes | No | No | No | No | No | [Website](https://www.comet.com) / [Docs](https://docs.comet.com/docs/opik-overview) / [Repo](https://github.com/comet-ml/opik) |
| [Helicone](https://www.helicone.ai) | Agent observability | Yes | No | Yes | No | No | No | [Website](https://www.helicone.ai) / [Docs](https://docs.helicone.ai) / [Repo](https://github.com/Helicone/helicone) |
| [Langfuse](https://langfuse.com/docs) | Agent observability | Yes | No | Yes | No | No | No | [Docs](https://langfuse.com/docs) / [Repo](https://github.com/langfuse/langfuse) |
| [OpenLIT](https://openlit.io) | Agent observability | Yes | No | Yes | Yes | No | No | [Website](https://openlit.io) / [Docs](https://docs.openlit.io) / [Repo](https://github.com/openlit/openlit) |
| [Ollama](https://ollama.com) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Website](https://ollama.com) / [Docs](https://docs.ollama.com) / [Repo](https://github.com/ollama/ollama) |
| [LM Studio](https://lmstudio.ai) | Local LLM developer tools | Yes | Yes | No | Yes | No | No | [Website](https://lmstudio.ai) / [Docs](https://lmstudio.ai/docs) / [Repo](https://github.com/lmstudio-ai) |
| [Llamafile](https://github.com/Mozilla-Ocho/llamafile/blob/main/README.md) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Docs](https://github.com/Mozilla-Ocho/llamafile/blob/main/README.md) / [Repo](https://github.com/Mozilla-Ocho/llamafile) |
| [LocalAI](https://localai.io) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Website](https://localai.io) / [Docs](https://localai.io/docs) / [Repo](https://github.com/go-skynet/LocalAI) |
| [vLLM](https://vllm.ai) | Local LLM developer tools | Yes | No | Yes | Yes | No | No | [Website](https://vllm.ai) / [Docs](https://docs.vllm.ai/en/stable/serving/openai_compatible_server.html) / [Repo](https://github.com/vllm-project/vllm) |
| [Athenaeum](https://github.com/herakles-dev/athenaeum#readme) | Self-hosted AI dev stacks | Yes | Yes | Yes | No | No | Yes | [Docs](https://github.com/herakles-dev/athenaeum#readme) / [Repo](https://github.com/herakles-dev/athenaeum) |
| [Gemini CLI](https://developers.google.com/gemini-code-assist/docs/gemini-cli) | Coding agents | Yes | Yes | No | Yes | No | Yes | [Docs](https://developers.google.com/gemini-code-assist/docs/gemini-cli) / [Repo](https://github.com/google-gemini/gemini-cli) |
| [Goose](https://goose-docs.ai/) | Coding agents | Yes | Yes | No | Yes | No | Yes | [Website](https://goose-docs.ai/) / [Docs](https://goose-docs.ai/docs/quickstart/) / [Repo](https://github.com/aaif-goose/goose) |
| [Harbor CLI Stack](https://github.com/harbor-ai/harbor#readme) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Docs](https://github.com/harbor-ai/harbor#readme) / [Repo](https://github.com/harbor-ai/harbor) |
| [IBM MCP CLI](https://github.com/IBM/mcp-cli) | MCP tooling | Yes | Yes | No | Yes | No | Yes | [Repo](https://github.com/IBM/mcp-cli) |
| [Jan Server](https://jan.ai) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Website](https://jan.ai) / [Docs](https://github.com/janhq/server#readme) / [Repo](https://github.com/janhq/server) |
| [KoboldCpp](https://koboldcpp.com) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Website](https://koboldcpp.com) / [Docs](https://github.com/LostRuins/koboldcpp/wiki) / [Repo](https://github.com/LostRuins/koboldcpp) |
| [llama-cpp-python](https://llama-cpp-python.readthedocs.io) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Docs](https://llama-cpp-python.readthedocs.io) / [Repo](https://github.com/abetlen/llama-cpp-python) |
| [llama.cpp](https://github.com/ggml-org/llama.cpp/tree/master/examples) | Local LLM developer tools | Yes | Yes | Yes | Yes | No | No | [Docs](https://github.com/ggml-org/llama.cpp/tree/master/examples) / [Repo](https://github.com/ggml-org/llama.cpp) |
| [MCP Bundles (MCPB)](https://modelcontextprotocol.io/docs/develop/build-with-agent-skills) | MCP servers | Yes | Yes | No | Yes | No | Yes | [Docs](https://modelcontextprotocol.io/docs/develop/build-with-agent-skills) / [Repo](https://github.com/modelcontextprotocol/mcpb) |
| [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) | MCP tooling | Yes | Yes | No | Yes | No | Yes | [Docs](https://modelcontextprotocol.io/docs/tools/inspector) / [Repo](https://github.com/modelcontextprotocol/inspector) |
| [mcp-cli (wong2)](https://www.npmjs.com/package/@wong2/mcp-cli) | MCP tooling | Yes | Yes | No | Yes | No | Yes | [Website](https://www.npmjs.com/package/@wong2/mcp-cli) / [Repo](https://github.com/wong2/mcp-cli) |
| [Redis + Ollama RAG Stack](https://github.com/TtheBC01/redis-ollama-RAG#readme) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Docs](https://github.com/TtheBC01/redis-ollama-RAG#readme) / [Repo](https://github.com/TtheBC01/redis-ollama-RAG) |
| [Ruflo](https://github.com/ruvnet/ruflo) | Coding agents | Yes | No | Yes | Yes | No | Yes | [Docs](https://github.com/ruvnet/ruflo#readme) / [Repo](https://github.com/ruvnet/ruflo) |
| [Self-hosted AI Starter Kit (n8n)](https://docs.n8n.io/hosting/starter-kits/ai-starter-kit/) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Docs](https://docs.n8n.io/hosting/starter-kits/ai-starter-kit/) / [Repo](https://github.com/n8n-io/self-hosted-ai-starter-kit) |
| [Smithery CLI](https://smithery.ai) | MCP tooling | Yes | Yes | No | Yes | No | Yes | [Website](https://smithery.ai) / [Docs](https://smithery.ai/docs/concepts/cli) / [Repo](https://github.com/smithery-ai/cli) |
| [Zed](https://zed.dev/) | IDE assistants | Yes | Yes | No | No | Yes | Yes | [Website](https://zed.dev/) / [Docs](https://zed.dev/releases/stable/0.233.5) / [Repo](https://github.com/zed-industries/zed) |
| [Nosia](https://nosia.ai) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Website](https://nosia.ai) / [Docs](https://nosia.ai/readme/) |
| [Nosia Installer Stack](https://get.nosia.ai) | Self-hosted AI dev stacks | Yes | Yes | Yes | Yes | No | No | [Website](https://get.nosia.ai) / [Docs](https://nosia.ai/readme/) |
| [Roo Code](https://roocode.com/) | Coding agents | Yes | No | No | Yes | Yes | Yes | [Website](https://roocode.com/) / [Docs](https://docs.roocode.com/) / [Repo](https://github.com/RooCodeInc/Roo-Code) |
| [Agent Skills](https://github.com/datalayer/agent-skills) | Agent skill packs | Yes | Yes | No | No | No | Yes | [Repo](https://github.com/datalayer/agent-skills) |
## Browse The Shelves
### Coding agents
Agentic tools that can inspect, modify, and reason about source code.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Aider](https://aider.chat/) | Open-source terminal pair programmer that edits tracked files in a local Git repository. | CLI · Local | [Website](https://aider.chat/) / [Docs](https://aider.chat/docs/) / [Repo](https://github.com/Aider-AI/aider) |
| [Amazon Q Developer](https://aws.amazon.com/q/developer/) | AWS coding assistant with IDE, CLI, and GitHub agents for coding, testing, review, and transformations. | CLI · GitHub app · IDE · Hybrid | [Website](https://aws.amazon.com/q/developer/) / [Docs](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) |
| [Amp](https://ampcode.com/) | Terminal-centric coding agent with deep codebase context, editor links, and automation-oriented SDK features. | API · CLI · Hybrid | [Website](https://ampcode.com/) / [Docs](https://ampcode.com/manual) |
| [Augment Code](https://www.augmentcode.com/) | Repo-aware coding agent for editors and terminal that edits files, uses tools, and understands large codebases. | CLI · IDE · Hybrid | [Website](https://www.augmentcode.com/) / [Docs](https://docs.augmentcode.com/introduction) |
| [Claude Code](https://code.claude.com/docs/en/setup) | Anthropic coding agent for terminal workflows that can read code, edit files, run commands, and use project context. | CLI · Hybrid | [Docs](https://code.claude.com/docs/en/setup) |
| [Cline](https://docs.cline.bot/introduction/overview) | Open-source coding agent for editor workflows with file edits, terminal commands, browser use, and MCP-based tool extension. | Browser · CLI · IDE · Hybrid | [Docs](https://docs.cline.bot/introduction/overview) / [Repo](https://github.com/cline/cline) |
| [Cursor](https://cursor.com/) | AI code editor built around chat, codebase context, agents, rules, MCP, and terminal-assisted development workflows. | CLI · Desktop · IDE · Hybrid | [Website](https://cursor.com/) / [Docs](https://cursor.com/docs) |
| [Devin](https://devin.ai/) | Cloud software engineering agent for teams that works on repositories and can run tasks in parallel. | Web · Hosted | [Website](https://devin.ai/) / [Docs](https://docs.devin.ai/es/get-started/devin-intro) |
| [Ellipsis](https://www.ellipsis.dev/) | GitHub agent that reviews pull requests, answers repo questions, and can generate changes or release notes. | GitHub app · Web · Hosted | [Website](https://www.ellipsis.dev/) / [Docs](https://docs.ellipsis.dev/introduction) |
| [Factory Droid](https://factory.ai/) | Coding agent platform with CLI, desktop, and headless automation for code changes, review, and CI workflows. | API · CLI · Desktop · Hybrid | [Website](https://factory.ai/) / [Docs](https://docs.factory.ai/welcome) |
| [Gemini CLI](https://developers.google.com/gemini-code-assist/docs/gemini-cli) | Open-source terminal coding agent that uses tool calls and MCP servers to work on repository tasks. | CLI · MCP · Local | [Docs](https://developers.google.com/gemini-code-assist/docs/gemini-cli) / [Repo](https://github.com/google-gemini/gemini-cli) |
| [Gemini Code Assist](https://developers.google.com/gemini-code-assist) | Google's coding assistant for IDEs and GitHub with agent mode, PR summaries, and code review. | GitHub app · IDE · Hosted | [Website](https://developers.google.com/gemini-code-assist) / [Docs](https://developers.google.com/gemini-code-assist/docs/overview) |
| [Goose](https://goose-docs.ai/) | Open-source local agent with desktop, CLI, and API surfaces for editing, running, and testing code. | API · CLI · Desktop · Local | [Website](https://goose-docs.ai/) / [Docs](https://goose-docs.ai/docs/quickstart/) / [Repo](https://github.com/aaif-goose/goose) |
| [Ivy Tendril](https://tendril.ivy.app) | Open-source AI coding orchestrator that manages Claude Code, Codex, Antigravity, Copilot and more through a plan-based lifecycle with verification gates and self-improving memory. | Desktop · Local | [Website](https://tendril.ivy.app) / [Docs](https://tendril.ivy.app/getting-started/installation) |
| [Jules](https://jules.google/) | Google asynchronous coding agent for GitHub that fixes bugs, adds features, and updates documentation. | API · Web · Hosted | [Website](https://jules.google/) / [Docs](https://jules.google/docs/) |
| [Junie](https://www.jetbrains.com/junie/) | JetBrains coding agent for IDEs and terminal that plans, edits, tests, and reviews project changes. | CLI · IDE · Hybrid | [Website](https://www.jetbrains.com/junie/) / [Docs](https://www.jetbrains.com/help/ai-assistant/junie-agent.html) / [Repo](https://github.com/JetBrains/junie) |
| [OpenAI Codex CLI](https://github.com/openai/codex) | Local terminal coding agent from OpenAI that can inspect code, edit files, and run commands in a developer workspace. | CLI · Hybrid | [Docs](https://developers.openai.com/codex/cli/) / [Repo](https://github.com/openai/codex) |
| [OpenCode](https://opencode.ai/) | Open-source AI coding agent for terminal, desktop, IDE, and GitHub repository workflows. | CLI · Desktop · GitHub app · IDE · MCP · Local | [Website](https://opencode.ai/) / [Docs](https://opencode.ai/docs/) / [Repo](https://github.com/anomalyco/opencode) |
| [OpenHands](https://openhands.dev/) | Open-source software agent platform with GUI, CLI, SDK, and self-hosted or cloud deployment options. | API · CLI · Web · Hybrid | [Website](https://openhands.dev/) / [Docs](https://docs.openhands.dev/overview/quickstart) / [Repo](https://github.com/OpenHands/OpenHands) |
| [Plandex](https://plandex.ai/) | Open-source terminal agent for long-running tasks across large projects and real repositories. | CLI · Local | [Website](https://plandex.ai/) / [Docs](https://docs.plandex.ai/quick-start) / [Repo](https://github.com/plandex-ai/plandex) |
| [Qwen Code](https://qwen.ai/) | Open-source terminal coding agent optimized for Qwen models and large repository tasks. | CLI · Local | [Website](https://qwen.ai/) / [Repo](https://github.com/QwenLM/qwen-code) |
| [Refact.ai](https://refact.ai/) | Coding agent for IDEs and enterprises that can automate coding, debugging, testing, and documentation tasks. | IDE · Web · Hybrid | [Website](https://refact.ai/) / [Docs](https://docs.refact.ai/) / [Repo](https://github.com/smallcloudai/refact-vscode) |
| [Roo Code](https://roocode.com/) | Open-source coding agent for VS Code and cloud agents that can code, review, and automate repository tasks. | CLI · IDE · Web · Hybrid | [Website](https://roocode.com/) / [Docs](https://docs.roocode.com/) / [Repo](https://github.com/RooCodeInc/Roo-Code) |
| [Ruflo](https://github.com/ruvnet/ruflo) | Enterprise-grade multi-agent orchestration framework for Claude that deploys 60+ specialized AI agents with shared memory, RAG, and swarm coordination across machines and teams. | API · CLI · Web · Self-hosted | [Docs](https://github.com/ruvnet/ruflo#readme) / [Repo](https://github.com/ruvnet/ruflo) |
| [SWE-agent](https://swe-agent.com/) | Open-source agent for resolving real repository issues and automating software engineering tasks. | CLI · Local | [Website](https://swe-agent.com/) / [Docs](https://swe-agent.com/latest/) / [Repo](https://github.com/swe-agent/swe-agent) |
| [Sweep](https://sweep.dev/) | JetBrains-focused coding assistant with agent mode, repo edits, AI code review, and MCP integration. | IDE · Hybrid | [Website](https://sweep.dev/) / [Docs](https://docs.sweep.dev/) / [Repo](https://github.com/sweepai/sweep) |
| [Windsurf Editor](https://windsurf.com/) | AI code editor with repo-aware agent workflows for multi-file edits and developer automation. | Desktop · Hybrid | [Website](https://windsurf.com/) / [Docs](https://docs.windsurf.com/) |
### Terminal agents
AI developer tools primarily operated from a command-line interface.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [agenttrace](https://luoyuctl.github.io/agenttrace/) | Local CLI/TUI that turns AI coding agent session logs into cost, token, latency, failure, and health reports. | CLI · Local | [Website](https://luoyuctl.github.io/agenttrace/) / [Docs](https://github.com/luoyuctl/agenttrace#readme) / [Repo](https://github.com/luoyuctl/agenttrace) |
| [Aider](https://aider.chat/) | Open-source terminal pair programmer that edits tracked files in a local Git repository. | CLI · Local | [Website](https://aider.chat/) / [Docs](https://aider.chat/docs/) / [Repo](https://github.com/Aider-AI/aider) |
| [Amazon Q Developer](https://aws.amazon.com/q/developer/) | AWS coding assistant with IDE, CLI, and GitHub agents for coding, testing, review, and transformations. | CLI · GitHub app · IDE · Hybrid | [Website](https://aws.amazon.com/q/developer/) / [Docs](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) |
| [Amp](https://ampcode.com/) | Terminal-centric coding agent with deep codebase context, editor links, and automation-oriented SDK features. | API · CLI · Hybrid | [Website](https://ampcode.com/) / [Docs](https://ampcode.com/manual) |
| [Augment Code](https://www.augmentcode.com/) | Repo-aware coding agent for editors and terminal that edits files, uses tools, and understands large codebases. | CLI · IDE · Hybrid | [Website](https://www.augmentcode.com/) / [Docs](https://docs.augmentcode.com/introduction) |
| [Claude Code](https://code.claude.com/docs/en/setup) | Anthropic coding agent for terminal workflows that can read code, edit files, run commands, and use project context. | CLI · Hybrid | [Docs](https://code.claude.com/docs/en/setup) |
| [CodeRabbit](https://coderabbit.ai/) | AI code review agent for pull requests, local IDE review, and terminal-based review workflows. | CLI · GitHub app · IDE · Hybrid | [Website](https://coderabbit.ai/) / [Docs](https://docs.coderabbit.ai/) |
| [Factory Droid](https://factory.ai/) | Coding agent platform with CLI, desktop, and headless automation for code changes, review, and CI workflows. | API · CLI · Desktop · Hybrid | [Website](https://factory.ai/) / [Docs](https://docs.factory.ai/welcome) |
| [Gemini CLI](https://developers.google.com/gemini-code-assist/docs/gemini-cli) | Open-source terminal coding agent that uses tool calls and MCP servers to work on repository tasks. | CLI · MCP · Local | [Docs](https://developers.google.com/gemini-code-assist/docs/gemini-cli) / [Repo](https://github.com/google-gemini/gemini-cli) |
| [Junie](https://www.jetbrains.com/junie/) | JetBrains coding agent for IDEs and terminal that plans, edits, tests, and reviews project changes. | CLI · IDE · Hybrid | [Website](https://www.jetbrains.com/junie/) / [Docs](https://www.jetbrains.com/help/ai-assistant/junie-agent.html) / [Repo](https://github.com/JetBrains/junie) |
| [OpenAI Codex CLI](https://github.com/openai/codex) | Local terminal coding agent from OpenAI that can inspect code, edit files, and run commands in a developer workspace. | CLI · Hybrid | [Docs](https://developers.openai.com/codex/cli/) / [Repo](https://github.com/openai/codex) |
| [OpenCode](https://opencode.ai/) | Open-source AI coding agent for terminal, desktop, IDE, and GitHub repository workflows. | CLI · Desktop · GitHub app · IDE · MCP · Local | [Website](https://opencode.ai/) / [Docs](https://opencode.ai/docs/) / [Repo](https://github.com/anomalyco/opencode) |
| [Qwen Code](https://qwen.ai/) | Open-source terminal coding agent optimized for Qwen models and large repository tasks. | CLI · Local | [Website](https://qwen.ai/) / [Repo](https://github.com/QwenLM/qwen-code) |
### IDE assistants
AI assistants embedded in editors or IDEs for coding workflows.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Amazon Q Developer](https://aws.amazon.com/q/developer/) | AWS coding assistant with IDE, CLI, and GitHub agents for coding, testing, review, and transformations. | CLI · GitHub app · IDE · Hybrid | [Website](https://aws.amazon.com/q/developer/) / [Docs](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) |
| [Augment Code](https://www.augmentcode.com/) | Repo-aware coding agent for editors and terminal that edits files, uses tools, and understands large codebases. | CLI · IDE · Hybrid | [Website](https://www.augmentcode.com/) / [Docs](https://docs.augmentcode.com/introduction) |
| [Cline](https://docs.cline.bot/introduction/overview) | Open-source coding agent for editor workflows with file edits, terminal commands, browser use, and MCP-based tool extension. | Browser · CLI · IDE · Hybrid | [Docs](https://docs.cline.bot/introduction/overview) / [Repo](https://github.com/cline/cline) |
| [CodeRabbit](https://coderabbit.ai/) | AI code review agent for pull requests, local IDE review, and terminal-based review workflows. | CLI · GitHub app · IDE · Hybrid | [Website](https://coderabbit.ai/) / [Docs](https://docs.coderabbit.ai/) |
| [Continue](https://docs.continue.dev/) | Open-source AI code assistant and CLI for IDE agents, source-controlled checks, and customizable development workflows. | CLI · IDE · Hybrid | [Docs](https://docs.continue.dev/) / [Repo](https://github.com/continuedev/continue) |
| [Cursor](https://cursor.com/) | AI code editor built around chat, codebase context, agents, rules, MCP, and terminal-assisted development workflows. | CLI · Desktop · IDE · Hybrid | [Website](https://cursor.com/) / [Docs](https://cursor.com/docs) |
| [Gemini Code Assist](https://developers.google.com/gemini-code-assist) | Google's coding assistant for IDEs and GitHub with agent mode, PR summaries, and code review. | GitHub app · IDE · Hosted | [Website](https://developers.google.com/gemini-code-assist) / [Docs](https://developers.google.com/gemini-code-assist/docs/overview) |
| [GitHub Copilot](https://github.com/features/copilot) | GitHub AI coding assistant for IDEs and GitHub workflows, including code suggestions, chat, and pull request support. | GitHub app · IDE · Web · Hosted | [Website](https://github.com/features/copilot) / [Docs](https://docs.github.com/en/copilot/overview-of-github-copilot/about-github-copilot) |
| [Junie](https://www.jetbrains.com/junie/) | JetBrains coding agent for IDEs and terminal that plans, edits, tests, and reviews project changes. | CLI · IDE · Hybrid | [Website](https://www.jetbrains.com/junie/) / [Docs](https://www.jetbrains.com/help/ai-assistant/junie-agent.html) / [Repo](https://github.com/JetBrains/junie) |
| [OpenCode](https://opencode.ai/) | Open-source AI coding agent for terminal, desktop, IDE, and GitHub repository workflows. | CLI · Desktop · GitHub app · IDE · MCP · Local | [Website](https://opencode.ai/) / [Docs](https://opencode.ai/docs/) / [Repo](https://github.com/anomalyco/opencode) |
| [Qodo](https://www.qodo.ai/) | Code review and IDE assistant product focused on reviewing diffs, tests, and repository context. | GitHub app · IDE · Hosted | [Website](https://www.qodo.ai/) / [Docs](https://docs.qodo.ai/) |
| [Refact.ai](https://refact.ai/) | Coding agent for IDEs and enterprises that can automate coding, debugging, testing, and documentation tasks. | IDE · Web · Hybrid | [Website](https://refact.ai/) / [Docs](https://docs.refact.ai/) / [Repo](https://github.com/smallcloudai/refact-vscode) |
| [Roo Code](https://roocode.com/) | Open-source coding agent for VS Code and cloud agents that can code, review, and automate repository tasks. | CLI · IDE · Web · Hybrid | [Website](https://roocode.com/) / [Docs](https://docs.roocode.com/) / [Repo](https://github.com/RooCodeInc/Roo-Code) |
| [Sweep](https://sweep.dev/) | JetBrains-focused coding assistant with agent mode, repo edits, AI code review, and MCP integration. | IDE · Hybrid | [Website](https://sweep.dev/) / [Docs](https://docs.sweep.dev/) / [Repo](https://github.com/sweepai/sweep) |
| [Tabby](https://www.tabbyml.com/) | Self-hosted AI coding assistant for teams that want private code assistance and repository-aware development. | API · IDE · Self-hosted | [Website](https://www.tabbyml.com/) / [Docs](https://tabby.tabbyml.com/docs/) / [Repo](https://github.com/TabbyML/tabby) |
| [Windsurf Editor](https://windsurf.com/) | AI code editor with repo-aware agent workflows for multi-file edits and developer automation. | Desktop · Hybrid | [Website](https://windsurf.com/) / [Docs](https://docs.windsurf.com/) |
| [Zed](https://zed.dev/) | Code editor with built-in agent workflows, external agent support, and MCP-connected coding assistance. | Desktop · MCP · Local | [Website](https://zed.dev/) / [Docs](https://zed.dev/releases/stable/0.233.5) / [Repo](https://github.com/zed-industries/zed) |
### Browser agents
Tools that can inspect, drive, or test browser-based developer workflows.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Agent Browser](https://github.com/vercel-labs/agent-browser) | Rust-based headless browser automation CLI designed for AI agents, wrapping Chromium control behind a simple command-line tool. | CLI | [Repo](https://github.com/vercel-labs/agent-browser) |
| [Agent-E](https://github.com/EmergenceAI/Agent-E) | Open-source agent system focused on browser automation, offering a natural-language web automation API and local agent runtime. | Framework · Library | [Repo](https://github.com/EmergenceAI/Agent-E) |
| [Agent-WebVoyager](https://github.com/mrmoxon/Agent-WebVoyager) | Implementation showcasing an autonomous WebVoyager-style agent that navigates and extracts data from sites via visual interactions. | Framework · Library | [Repo](https://github.com/mrmoxon/Agent-WebVoyager) |
| [Anchor Browser](https://anchorbrowser.io) | Cloud-hosted browser fleet built for AI agents, providing human-like Chromium instances and deterministic browser task execution APIs. | API · Hosted | [Docs](https://anchorbrowser.io) |
| [Browser MCP](https://browsermcp.io) | Local MCP server and browser extension that connect AI apps to your real browser profile for automating web tasks using AI tools. | Browser · MCP · Local | [Docs](https://browsermcp.io) |
| [Browser Use](https://browser-use.com) | Open-source Python library that lets AI agents control browsers via Playwright using natural language to navigate, extract, and automate web tasks. | API · Framework · Library · Hybrid | [Website](https://browser-use.com) / [Repo](https://github.com/browser-use/browser-use) |
| [Browserbase](https://www.browserbase.com) | Cloud headless browser infrastructure built for AI agents and web automation, providing scalable browser sessions with anti-detection features. | API · Hosted | [Docs](https://www.browserbase.com) / [Repo](https://github.com/browserbase/integrations) |
| [Browserless](https://www.browserless.io) | Hosted headless Chrome service that exposes browser automation via APIs and MCP so AI agents can scrape, capture, and audit real web pages. | API · MCP · Hosted | [Website](https://www.browserless.io) / [Docs](https://www.browserless.io/blog/announcing-browserless-mcp-with-ai) |
| [BrowserPilot](https://github.com/handrew/browserpilot) | Python library that offers an intelligent web browsing agent controlled by natural language commands over a ChromeDriver-driven browser. | Library | [Repo](https://github.com/handrew/browserpilot) |
| [Charlotte MCP Server](https://vibehackers.io/mcp/charlotte) | Open-source MCP server that renders web pages into structured, token-efficient representations using headless Chromium for agents. | MCP · Self-hosted | [Docs](https://vibehackers.io/mcp/charlotte) / [Repo](https://github.com/TickTockBent/charlotte) |
| [Cline](https://docs.cline.bot/introduction/overview) | Open-source coding agent for editor workflows with file edits, terminal commands, browser use, and MCP-based tool extension. | Browser · CLI · IDE · Hybrid | [Docs](https://docs.cline.bot/introduction/overview) / [Repo](https://github.com/cline/cline) |
| [Firecrawl](https://www.firecrawl.dev) | Open-source web data API for AI that lets agents search, scrape, and interact with the web at scale via HTTP, SDKs, CLI, and MCP. | API · CLI · Library · MCP · Hybrid | [Docs](https://www.firecrawl.dev) / [Repo](https://github.com/firecrawl/firecrawl) |
| [Firecrawl Web Agent](https://github.com/firecrawl/web-agent) | Autonomous web data agent built on Firecrawl and browser-use to execute web tasks over an HTTP API for downstream applications. | API · Framework | [Repo](https://github.com/firecrawl/web-agent) |
| [HyperAgent](https://github.com/hyperbrowserai/HyperAgent) | TypeScript SDK and CLI that layers AI commands like page.ai and executeTask on top of Playwright for intelligent browser automation. | CLI · Library | [Repo](https://github.com/hyperbrowserai/HyperAgent) |
| [Komos](https://www.komos.ai/browser-automation-tools) | Hosted browser automation platform for reusable AI tasks that drive websites, call APIs, process files, and run operations workflows. | API · Browser · Web · Hybrid | [Website](https://www.komos.ai/browser-automation-tools) / [Docs](https://docs.komos.ai/) |
| [LaVague](https://github.com/lavague-ai/LaVague) | Large Action Model framework that turns natural language instructions into Selenium-based browser interactions for AI web agents. | Framework · Library | [Repo](https://github.com/lavague-ai/LaVague) |
| [OpenAgents Web Agent](https://openagents.org) | Web Agent inside the OpenAgents platform that performs autonomous web browsing with open-source code and UI for real-world tasks. | Framework · Web | [Website](https://openagents.org) / [Repo](https://github.com/xlang-ai/openagents) |
| [OpenAI Computer Use](https://developers.openai.com) | OpenAI API capability that lets models operate software through the UI, including navigating and interacting with browser windows. | API · Hosted | [Website](https://developers.openai.com) / [Docs](https://developers.openai.com/api/docs/guides/tools-computer-use) |
| [Skyvern](https://pypi.org/project/skyvern/0.1.70/) | AI browser automation framework that uses LLMs and computer vision to automate multi-step workflows across websites via an API and SDK. | API · Library · Hybrid | [Docs](https://pypi.org/project/skyvern/0.1.70/) / [Repo](https://github.com/Skyvern-AI/skyvern) |
| [Stagehand](https://stagehand.dev) | AI browser automation framework that mixes natural language actions with Playwright code for reliable production browser agents. | Framework · Library | [Website](https://stagehand.dev) / [Repo](https://github.com/browserbase/stagehand) |
| [Steel Browser](https://steel.dev) | Open-source browser API that lets AI apps and agents perform programmatic browsing tasks without managing browser processes directly. | API · Library | [Website](https://steel.dev) / [Repo](https://github.com/steel-dev/steel-browser) |
| [Tarsier](https://github.com/reworkd/tarsier) | Vision utility library that gives web interaction agents structured, OCR-backed views of pages by tagging interactable elements. | Library | [Repo](https://github.com/reworkd/tarsier) |
| [Webagent (webagent-cloud)](https://github.com/webagent-cloud/webagent) | Simple web agent server built on Browser Use that exposes browser automation to other apps via HTTP APIs. | API · Framework | [Repo](https://github.com/webagent-cloud/webagent) |
| [WebVoyager](https://github.com/MinorJerry/WebVoyager) | LMM-powered web agent that completes end-to-end tasks on real websites using visual and textual signals in a Selenium environment. | Framework · Library | [Repo](https://github.com/MinorJerry/WebVoyager) |
### MCP servers
Model Context Protocol servers that expose tools, resources, or prompts.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Anki MCP Server](https://ankimcp.ai) | MCP server that lets AI assistants interact with Anki flashcards and spaced-repetition workflows. | MCP · Local | [Website](https://ankimcp.ai) / [Repo](https://github.com/ankimcp/anki-mcp-server) |
| [ArXiv MCP Server](https://github.com/blazickjp/arxiv-mcp-server) | MCP server for searching arXiv papers and exposing academic paper content to AI assistants. | MCP · Local | [Repo](https://github.com/blazickjp/arxiv-mcp-server) |
| [Browserbase MCP Server](https://browserbase.com) | MCP server that lets AI agents control cloud browsers through Browserbase and Stagehand. | MCP · Hybrid | [Website](https://browserbase.com) / [Repo](https://github.com/browserbase/mcp-server-browserbase) |
| [Chrome DevTools MCP](https://developer.chrome.com/blog/chrome-devtools-mcp) | MCP server that gives AI agents Chrome DevTools debugging capabilities for web applications. | MCP · Local | [Docs](https://developer.chrome.com/blog/chrome-devtools-mcp) / [Repo](https://github.com/ChromeDevTools/chrome-devtools-mcp) |
| [Context7 MCP Server](https://context7.com) | MCP server for retrieving up-to-date library documentation and code examples for AI coding assistants. | MCP · Hybrid | [Website](https://context7.com) / [Repo](https://github.com/upstash/context7) |
| [e2b-mcp](https://e2b.dev) | CLI and API for running MCP servers inside isolated E2B cloud sandboxes. | CLI · Hosted | [Website](https://e2b.dev) / [Repo](https://github.com/cased/e2b-mcp) |
| [Exa MCP Server](https://github.com/exa-labs/exa-mcp-server) | MCP server for connecting AI assistants to Exa web search, crawling, and research tools. | MCP · Hosted | [Repo](https://github.com/exa-labs/exa-mcp-server) |
| [GitHub MCP Server](https://github.com/github/github-mcp-server) | Official GitHub MCP server for repository access, issues, pull requests, code analysis, and workflow automation. | MCP · Hybrid | [Repo](https://github.com/github/github-mcp-server) |
| [Google MCP Servers](https://github.com/google/mcp) | Collection of Google MCP servers for Google Cloud services such as BigQuery, Maps, Cloud SQL, and Cloud Storage. | MCP · Hosted | [Repo](https://github.com/google/mcp) |
| [MCP Bundles (MCPB)](https://modelcontextprotocol.io/docs/develop/build-with-agent-skills) | CLI tool for packaging local MCP servers into installable .mcpb files. | CLI · Local | [Docs](https://modelcontextprotocol.io/docs/develop/build-with-agent-skills) / [Repo](https://github.com/modelcontextprotocol/mcpb) |
| [Next.js DevTools MCP](https://github.com/vercel/next-devtools-mcp) | MCP server for exposing Next.js development tools and diagnostics to coding agents. | MCP · Local | [Repo](https://github.com/vercel/next-devtools-mcp) |
| [Playwright Code Runner](https://playwright.dev) | MCP-related tool for running Playwright code as part of browser automation workflows. | MCP · Local | [Website](https://playwright.dev) / [Repo](https://github.com/exe-language/playwright-mcp) |
| [Playwright MCP Server](https://playwright.dev/docs/getting-started-mcp) | MCP server that uses Playwright to let AI agents interact with web pages through accessibility snapshots. | MCP · Local | [Docs](https://playwright.dev/docs/getting-started-mcp) / [Repo](https://github.com/microsoft/playwright-mcp) |
| [ServiceGraph MCP](https://github.com/servicegraph/mcp-server) | MCP server for exposing observability data such as service metrics and logs to AI agents. | MCP · Hosted | [Repo](https://github.com/servicegraph/mcp-server) |
| [Supabase MCP Server](https://github.com/supabase-community/supabase-mcp) | Official Supabase MCP server for connecting AI assistants to Supabase projects and database operations. | MCP · Hosted | [Repo](https://github.com/supabase-community/supabase-mcp) |
### MCP clients
Applications and agents that connect to Model Context Protocol servers.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Augment Code](https://www.augmentcode.com/) | Repo-aware coding agent for editors and terminal that edits files, uses tools, and understands large codebases. | CLI · IDE · Hybrid | [Website](https://www.augmentcode.com/) / [Docs](https://docs.augmentcode.com/introduction) |
| [Gemini CLI](https://developers.google.com/gemini-code-assist/docs/gemini-cli) | Open-source terminal coding agent that uses tool calls and MCP servers to work on repository tasks. | CLI · MCP · Local | [Docs](https://developers.google.com/gemini-code-assist/docs/gemini-cli) / [Repo](https://github.com/google-gemini/gemini-cli) |
| [OpenCode](https://opencode.ai/) | Open-source AI coding agent for terminal, desktop, IDE, and GitHub repository workflows. | CLI · Desktop · GitHub app · IDE · MCP · Local | [Website](https://opencode.ai/) / [Docs](https://opencode.ai/docs/) / [Repo](https://github.com/anomalyco/opencode) |
| [Roo Code](https://roocode.com/) | Open-source coding agent for VS Code and cloud agents that can code, review, and automate repository tasks. | CLI · IDE · Web · Hybrid | [Website](https://roocode.com/) / [Docs](https://docs.roocode.com/) / [Repo](https://github.com/RooCodeInc/Roo-Code) |
| [Sweep](https://sweep.dev/) | JetBrains-focused coding assistant with agent mode, repo edits, AI code review, and MCP integration. | IDE · Hybrid | [Website](https://sweep.dev/) / [Docs](https://docs.sweep.dev/) / [Repo](https://github.com/sweepai/sweep) |
| [Zed](https://zed.dev/) | Code editor with built-in agent workflows, external agent support, and MCP-connected coding assistance. | Desktop · MCP · Local | [Website](https://zed.dev/) / [Docs](https://zed.dev/releases/stable/0.233.5) / [Repo](https://github.com/zed-industries/zed) |
### MCP tooling
Developer tools for building, testing, debugging, or managing MCP systems.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [cheqd MCP Toolkit](https://github.com/cheqd/mcp-toolkit) | Modular MCP toolkit and server framework for decentralized identity workflows on the Cheqd network. | Framework | [Docs](https://github.com/cheqd/mcp-toolkit#readme) / [Repo](https://github.com/cheqd/mcp-toolkit) |
| [IBM MCP CLI](https://github.com/IBM/mcp-cli) | IBM command-line interface for interacting with MCP servers from scripts and terminals. | CLI · Local | [Repo](https://github.com/IBM/mcp-cli) |
| [MCP C# SDK](https://csharp.sdk.modelcontextprotocol.io) | Official C# SDK for MCP servers and clients, maintained with Microsoft and published to NuGet. | Library | [Docs](https://csharp.sdk.modelcontextprotocol.io) / [Repo](https://github.com/modelcontextprotocol/csharp-sdk) |
| [MCP Clients Registry](https://github.com/TianqiZhang/mcp-client-registry) | Community-maintained registry mapping MCP client identifiers to official client names and metadata. | Library | [Repo](https://github.com/TianqiZhang/mcp-client-registry) |
| [MCP Framework (QuantGeekDev)](https://mcp-framework.com/) | TypeScript-first framework and CLI for building MCP servers with automatic discovery and multi-transport support. | CLI · Framework | [Docs](https://mcp-framework.com/) / [Repo](https://github.com/QuantGeekDev/mcp-framework) |
| [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) | Official visual and command-line testing tool for developing, inspecting, and debugging Model Context Protocol servers. | CLI · MCP · Web · Local | [Docs](https://modelcontextprotocol.io/docs/tools/inspector) / [Repo](https://github.com/modelcontextprotocol/inspector) |
| [MCP Registry](https://registry.modelcontextprotocol.io) | Community-driven registry service and REST API for publishing and discovering Model Context Protocol servers. | API · Hybrid | [Website](https://registry.modelcontextprotocol.io) / [Docs](https://modelcontextprotocol.io/registry/about) / [Repo](https://github.com/modelcontextprotocol/registry) |
| [MCP Registry Server (KBB99)](https://mcpservers.org/servers/KBB99/mcp-registry-server) | MCP server that exposes semantic search and retrieval over an MCP registry for discovering other servers. | MCP · Self-hosted | [Website](https://mcpservers.org/servers/KBB99/mcp-registry-server) / [Repo](https://github.com/KBB99/mcp-registry-server) |
| [MCP Rust SDK (rmcp)](https://crates.io/crates/rmcp) | Rust SDK for implementing MCP clients and servers, published as the rmcp crate. | Library | [Docs](https://crates.io/crates/rmcp) / [Repo](https://github.com/modelcontextprotocol/rust-sdk) |
| [mcp-cli (wong2)](https://www.npmjs.com/package/@wong2/mcp-cli) | Interactive and non-interactive CLI inspector for running, listing, and calling MCP server tools, resources, and prompts. | CLI · Local | [Website](https://www.npmjs.com/package/@wong2/mcp-cli) / [Repo](https://github.com/wong2/mcp-cli) |
| [mcpscan.ai](https://mcpscan.ai) | Web-based security scanner for discovering vulnerabilities in MCP server implementations and configurations. | Web | [Docs](https://mcpscan.ai) |
| [Model Context Protocol Specification Repo](https://modelcontextprotocol.io) | Official repository containing the MCP specification, schemas, and documentation website sources. | Library | [Website](https://modelcontextprotocol.io) / [Repo](https://github.com/modelcontextprotocol/modelcontextprotocol) |
| [Model Context Protocol TypeScript SDK](https://modelcontextprotocol.io/docs/sdk) | Official TypeScript SDK for building MCP servers and clients with stdio and HTTP transports. | Library | [Website](https://modelcontextprotocol.io/docs/sdk) / [Docs](https://www.npmjs.com/package/@modelcontextprotocol/sdk) / [Repo](https://github.com/modelcontextprotocol/typescript-sdk) |
| [PulseMCP Registry](https://www.pulsemcp.com) | MCP-focused registry and API that aggregates, enriches, and exposes metadata about public MCP servers. | API · Web · Hosted | [Website](https://www.pulsemcp.com) / [Docs](https://www.pulsemcp.com/api) |
| [Smithery CLI](https://smithery.ai) | CLI to search, install, run, publish, and inspect MCP servers and skills across clients. | CLI · Local | [Website](https://smithery.ai) / [Docs](https://smithery.ai/docs/concepts/cli) / [Repo](https://github.com/smithery-ai/cli) |
| [Smithery MCP Installer Server](https://github.com/smithery-ai/smithery-cli-mcp) | Official MCP server for Smithery CLI that finds, configures, and installs MCP servers for local clients. | MCP · Self-hosted | [Repo](https://github.com/smithery-ai/smithery-cli-mcp) |
| [WebMCP JavaScript Library](https://webmcp.dev) | JavaScript library and runtime for exposing website functionality as WebMCP tools to MCP-aware agents. | Library | [Website](https://webmcp.dev) / [Docs](https://docs.mcp-b.ai/explanation/webmcp-vs-mcp) / [Repo](https://github.com/webmachinelearning/webmcp) |
### Agent skill packs
Reusable instruction, workflow, or capability packs for coding agents.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Agent Powerups](https://github.com/yeaight7/agent-powerups) | Curated skill packs, commands, MCP configs, hooks, templates, and workflows for coding agents. | CLI · Desktop · MCP · Skill Pack · Template · Local | [Repo](https://github.com/yeaight7/agent-powerups) |
| [Agent Skills](https://github.com/datalayer/agent-skills) | Python package to create, manage, and execute reusable code-based tool compositions for AI agents with MCP integration. | MCP · Local | [Repo](https://github.com/datalayer/agent-skills) |
| [Agent Skills Specification](https://github.com/agentskills/agentskills) | Open specification and documentation for Agent Skills format maintained by Anthropic with reference SDK and examples. | Framework · Skill Pack | [Repo](https://github.com/agentskills/agentskills) |
| [AgentSkills MCP](https://github.com/zouyingcao/agentskills-mcp) | MCP server that brings Anthropic Agent Skills to any MCP-compatible agent with progressive disclosure architecture. | MCP · Local | [Repo](https://github.com/zouyingcao/agentskills-mcp) |
| [Anthropic Knowledge Work Plugins](https://github.com/anthropics/knowledge-work-plugins) | Official open-source plugins for Claude Cowork and Claude Code with skills, commands, and MCP connectors for knowledge workers. | MCP · Local | [Repo](https://github.com/anthropics/knowledge-work-plugins) |
| [Anthropic Skills](https://github.com/anthropics/skills) | Official public repository of Agent Skills for Claude demonstrating creative, technical, and enterprise workflow patterns. | Skill Pack · Local | [Repo](https://github.com/anthropics/skills) |
| [Astronomer Agents](https://github.com/astronomer/agents) | AI agent tooling for data engineering workflows with Airflow MCP server and skills for DAG development, lineage, and dbt integration. | MCP · Local | [Repo](https://github.com/astronomer/agents) |
| [Awesome Agent Skills](https://github.com/heilcheng/awesome-agent-skills) | Community-curated directory of agent skills, tutorials, and guides for Claude, Copilot, Codex, and other AI assistants. | Skill Pack | [Repo](https://github.com/heilcheng/awesome-agent-skills) |
| [Awesome Cursorrules](https://github.com/PatrickJS/awesome-cursorrules) | Community collection of configuration files that enhance Cursor AI editor with custom rules and behaviors. | Template · Local | [Repo](https://github.com/PatrickJS/awesome-cursorrules) |
| [Awesome GitHub Copilot](https://github.com/github/awesome-copilot) | Community collection of custom agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot. | Skill Pack · Template | [Repo](https://github.com/github/awesome-copilot) |
| [Awesome Rules](https://github.com/continuedev/awesome-rules) | Collection of useful markdown rules with YAML frontmatter for coding assistants including testing, DevOps, and documentation categories. | Skill Pack · Template · Local | [Repo](https://github.com/continuedev/awesome-rules) |
| [Azure DevOps Skills](https://github.com/microsoft/azure-devops-skills) | Example skills for GitHub Copilot integrating with Azure DevOps via MCP server for work items, iterations, and builds. | MCP · Local | [Repo](https://github.com/microsoft/azure-devops-skills) |
| [CC DevOps Skills](https://github.com/akin-ozer/cc-devops-skills) | Practical agent skill pack with 31 skills for DevOps work in Claude Code and Codex including generators, validators, and debuggers. | CLI · Local | [Repo](https://github.com/akin-ozer/cc-devops-skills) |
| [Claude Skills](https://github.com/alirezarezvani/claude-skills) | Repository of 232+ Claude Code skills and agent plugins convertible to 12 AI coding tools including Codex, Cursor, and Windsurf. | CLI · Local | [Repo](https://github.com/alirezarezvani/claude-skills) |
| [Cursor Rules](https://github.com/survivorforge/cursor-rules) | Curated collection of .cursorrules files for Cursor IDE covering React, Next.js, Python, Node.js, and more frameworks. | Template · Local | [Repo](https://github.com/survivorforge/cursor-rules) |
| [Cursorrules Collection](https://github.com/nedcodes-ok/cursorrules-collection) | 110+ tested .cursorrules and .mdc rule files for Cursor, Claude Code, Copilot, Windsurf, Gemini CLI, and Codex. | Template · Local | [Repo](https://github.com/nedcodes-ok/cursorrules-collection) |
| [Custom Modes for Roo Code](https://github.com/jtgsystems/Custom-Modes-Roo-Code) | Collection of 171 specialized AI agent configurations for Roo Code across 9 categories with security-first principles. | Skill Pack · Template · Local | [Repo](https://github.com/jtgsystems/Custom-Modes-Roo-Code) |
| [dbt Agent Skills](https://github.com/dbt-labs/dbt-agent-skills) | Curated Agent Skills for working with dbt to help AI agents understand and execute analytics engineering workflows. | Skill Pack · Local | [Repo](https://github.com/dbt-labs/dbt-agent-skills) |
| [dotskills](https://github.com/vincentkoc/dotskills) | Personal .skills repository for Codex, Cursor, and OpenClaw with reusable skill units bundling prompts, scripts, and validation workflows. | Skill Pack · Template · Local | [Repo](https://github.com/vincentkoc/dotskills) |
| [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) | Agent harness performance system with skills, hooks, MCP configs, memory optimization, and cross-harness workflows. | CLI · MCP · Local | [Docs](https://github.com/affaan-m/everything-claude-code#readme) / [Repo](https://github.com/affaan-m/everything-claude-code) |
| [helderberto/skills](https://github.com/helderberto/skills) | Reusable AI agent skills for development workflows including code review, refactoring, TDD, security audit, and git automation. | Skill Pack · Local | [Repo](https://github.com/helderberto/skills) |
| [Invariant Testing](https://github.com/invariantlabs-ai/testing) | Lightweight library for writing debuggable unit tests for AI agent applications with localized assertions. | Library · Skill Pack · Local | [Repo](https://github.com/invariantlabs-ai/testing) |
| [Microsoft Skills](https://github.com/microsoft/skills) | Skills, custom agents, AGENTS.md templates, and MCP configurations for AI coding agents working with Azure SDKs and Microsoft AI Foundry. | MCP · Local | [Repo](https://github.com/microsoft/skills) |
| [Pulumi Agent Skills](https://github.com/pulumi/agent-skills) | Agent Skills for infrastructure-as-code workflows teaching AI assistants Pulumi migrations, components, and secrets management. | Skill Pack · Template · Local | [Repo](https://github.com/pulumi/agent-skills) |
| [roomode](https://github.com/upamune/roomode) | CLI tool to create, list, export, and import custom modes for RooCode defined in markdown files. | CLI · Local | [Repo](https://github.com/upamune/roomode) |
| [rules](https://github.com/continuedev/rules) | CLI tool to create, manage, and convert rule sets for code guidance across Cursor, Continue.dev, Claude, Copilot, and Codex. | CLI · Local | [Repo](https://github.com/continuedev/rules) |
| [Superpowers](https://github.com/obra/superpowers) | Core skills library for Claude Code with TDD, debugging, collaboration patterns, and systematic problem-solving techniques. | Skill Pack · Local | [Repo](https://github.com/obra/superpowers) |
| [Superpowers Lab](https://github.com/obra/superpowers-lab) | Experimental skills for Claude Code including semantic duplicate detection, tmux automation, and on-demand MCP server usage. | Skill Pack · Local | [Repo](https://github.com/obra/superpowers-lab) |
| [Swarms](https://github.com/am-will/swarms) | Multi-agent orchestration skills for Claude Code and Codex with dependency-aware planning and wave-based parallel execution. | Framework · Skill Pack · Local | [Repo](https://github.com/am-will/swarms) |
| [wshobson/agents](https://github.com/wshobson/agents) | Unified repository with 185 specialized agents, 16 orchestrators, 153 skills, and 100 commands for Claude Code automation. | CLI · Local | [Repo](https://github.com/wshobson/agents) |
### Agent observability
Tools for tracing, monitoring, and debugging agent or LLM application behavior.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [agenttrace](https://luoyuctl.github.io/agenttrace/) | Local CLI/TUI that turns AI coding agent session logs into cost, token, latency, failure, and health reports. | CLI · Local | [Website](https://luoyuctl.github.io/agenttrace/) / [Docs](https://github.com/luoyuctl/agenttrace#readme) / [Repo](https://github.com/luoyuctl/agenttrace) |
| [Amazon CloudWatch GenAI Observability](https://aws.amazon.com/cloudwatch/) | CloudWatch capabilities for monitoring and tracing generative AI agents, workloads, and quality metrics on AWS. | API · Web · Hosted | [Website](https://aws.amazon.com/cloudwatch/) / [Docs](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/GenAI-observability.html) / [Repo](https://github.com/aws-samples/sample-amazon-cloudwatch-generative-ai-observability) |
| [Arize AX](https://arize.com/ai-agents/agent-observability/) | Commercial agent and LLM observability platform built on Phoenix for tracing, evaluation, and monitoring production AI systems. | API · Web · Hosted | [Website](https://arize.com/ai-agents/agent-observability/) / [Docs](https://arize.com/docs/ax/observe/quickstart-llm) |
| [Arize Phoenix](https://arize.com/phoenix) | Open-source AI observability platform with tracing, evals, datasets, and experiments for LLM, agent, and RAG systems. | API · Web · Self-hosted | [Website](https://arize.com/phoenix) / [Docs](https://arize.com/docs/phoenix) / [Repo](https://github.com/arize-ai/phoenix) |
| [Braintrust](https://www.braintrust.dev) | AI observability and evaluation platform that logs LLM and agent traces and turns production logs into test datasets. | API · Web · Hosted | [Website](https://www.braintrust.dev) / [Docs](https://docs.braintrust.dev) |
| [Comet Opik](https://www.comet.com) | Open-source LLM observability framework for tracing, evaluating, and monitoring LLM, RAG, and agent workflows. | API · Web · Hybrid | [Website](https://www.comet.com) / [Docs](https://docs.comet.com/docs/opik-overview) / [Repo](https://github.com/comet-ml/opik) |
| [Confident AI](https://www.confident-ai.com) | Evaluation and observability platform that traces LLM apps and runs DeepEval metrics on components and end-to-end workflows. | API · Web · Hosted | [Website](https://www.confident-ai.com) / [Docs](https://www.confident-ai.com/docs) |
| [Datadog LLM Observability](https://www.datadoghq.com/product/ai/llm-observability/) | Datadog product for tracing, monitoring, and evaluating LLM and agent applications with integrated APM views. | API · Library · Web · Hosted | [Website](https://www.datadoghq.com/product/ai/llm-observability/) / [Docs](https://docs.datadoghq.com/tracing/llm_observability/) / [Repo](https://github.com/DataDog/llm-observability) |
| [Dunetrace](https://dunetrace.dev) | Open-source anomaly detection layer that monitors agent traces for structural failures and alerts in real time. | API · Self-hosted | [Website](https://dunetrace.dev) / [Docs](https://github.com/dunetrace/dunetrace#readme) / [Repo](https://github.com/dunetrace/dunetrace) |
| [Evidently AI](https://www.evidentlyai.com) | Open-source library and cloud service for evaluating, testing, and monitoring ML and LLM systems, including RAG and agents. | API · Web · Hybrid | [Website](https://www.evidentlyai.com) / [Docs](https://docs.evidentlyai.com) / [Repo](https://github.com/evidentlyai/evidently) |
| [Fiddler AI Observability](https://www.fiddler.ai) | AI observability and security platform for monitoring, alerting, and troubleshooting LLM and ML applications. | API · Web · Hosted | [Website](https://www.fiddler.ai) / [Docs](https://docs.fiddler.ai) |
| [Flexible GraphRAG Observability Stack](https://github.com/stevereiner/flexible-graphrag) | Observability setup in Flexible GraphRAG that instruments LlamaIndex RAG apps with OTEL traces, metrics, and Grafana dashboards. | CLI · Self-hosted | [Docs](https://github.com/stevereiner/flexible-graphrag/blob/main/docs/DEVELOPER/OBSERVABILITY/OBSERVABILITY.md) / [Repo](https://github.com/stevereiner/flexible-graphrag) |
| [Galileo AI](https://galileo.ai) | Agent-centric observability and evaluation platform with tracing, guardrails, and Luna models for RAG and agents. | API · Web · Hosted | [Website](https://galileo.ai) / [Docs](https://docs.galileo.ai) |
| [Grafana GenAI Observability](https://grafana.com) | Grafana Cloud dashboards and metrics for monitoring LLM application performance, token usage, and cost. | API · Web · Hosted | [Website](https://grafana.com) / [Docs](https://grafana.com/docs/grafana-cloud/monitor-applications/ai-observability/genai/observability/) |
| [Helicone](https://www.helicone.ai) | Open-source LLM observability platform and gateway for logging, tracing, and evaluating LLM and agent requests. | API · Web · Self-hosted | [Website](https://www.helicone.ai) / [Docs](https://docs.helicone.ai) / [Repo](https://github.com/Helicone/helicone) |
| [IBM Instana GenAI Observability](https://www.ibm.com/instana) | Instana module that provides GenAI observability for LLM and agentic workloads with unified tracing and metrics. | API · Web · Hosted | [Website](https://www.ibm.com/instana) / [Docs](https://www.ibm.com/docs/en/instana-observability) |
| [Keywords AI](https://keywordsai.co) | LLM observability platform offering real-time traces, logs, metrics, and quality scores across many models. | API · Web · Hosted | [Website](https://keywordsai.co) / [Docs](https://docs.keywordsai.co) |
| [Langfuse](https://langfuse.com/docs) | Open-source LLM engineering platform for observability, tracing, prompt management, datasets, and evaluations. | API · Web · Hybrid | [Docs](https://langfuse.com/docs) / [Repo](https://github.com/langfuse/langfuse) |
| [LangSmith](https://www.langchain.com/langsmith-platform) | Hosted observability and evaluation platform for tracing, debugging, and monitoring LangChain and other LLM or agent applications. | API · Web · Hosted | [Website](https://www.langchain.com/langsmith-platform) / [Docs](https://www.langchain.com/langsmith/observability) |
| [Langtrace](https://langtrace.ai) | Open-source OpenTelemetry-based observability tool and dashboard for tracing, evaluating, and debugging LLM applications. | API · Web · Self-hosted | [Website](https://langtrace.ai) / [Docs](https://docs.langtrace.ai) / [Repo](https://github.com/Scale3-Labs/langtrace) |
| [LangWatch](https://langwatch.ai) | LLM observability and evaluation platform focused on tracing, debugging, and optimizing AI agents and applications. | API · Web · Hybrid | [Website](https://langwatch.ai) / [Docs](https://docs.langwatch.ai) / [Repo](https://github.com/langwatch/langwatch) |
| [Lunary](https://lunary.ai) | Open-source observability and prompt platform for LLM chatbots with analytics, logs, traces, and evaluations. | API · Library · Web · Hybrid | [Website](https://lunary.ai) / [Docs](https://docs.lunary.ai) / [Repo](https://github.com/lunary-ai/lunary) |
| [Mastra Observability](https://mastra.ai) | Observability module in Mastra for tracing, monitoring, and evaluating LLM agents and workflows via OpenTelemetry. | API · Web · Hybrid | [Website](https://mastra.ai) / [Docs](https://mastra.ai/docs/observability) / [Repo](https://github.com/mastra-ai/mastra) |
| [Maxim AI](https://getmaxim.ai) | End-to-end AI evaluation and observability platform for testing and monitoring agents and LLM applications. | API · Web · Hosted | [Website](https://getmaxim.ai) / [Docs](https://docs.getbifrost.ai/features/observability/maxim) / [Repo](https://github.com/maximhq) |
| [MLflow AI Observability](https://mlflow.org) | MLflow extensions for LLM and agent observability with tracing, evaluation, and integration with TruLens scorers. | API · CLI · Web · Hybrid | [Website](https://mlflow.org) / [Docs](https://mlflow.org/docs/latest/llm/index.html) / [Repo](https://github.com/mlflow/mlflow) |
| [Monocle](https://monocle2ai.org) | Linux Foundation project providing a framework to trace GenAI app code and agent workflows with minimal code changes. | API · Local | [Website](https://monocle2ai.org) / [Docs](https://docs.monocle.sh) / [Repo](https://github.com/monocle2ai/monocle) |
| [Noveum AI Agent Monitoring](https://noveum.ai/en/solutions/ai-agent-monitoring) | Enterprise AI agent monitoring platform with real-time tracing of LLM calls, RAG steps, and tool interactions. | API · Web · Hosted | [Website](https://noveum.ai/en/solutions/ai-agent-monitoring) |
| [Okahu](https://www.okahu.ai) | AI observability platform and tools for debugging, testing, and monitoring agentic and LLM-based applications. | API · Web · Hosted | [Website](https://www.okahu.ai) / [Docs](https://docs.okahu.ai) / [Repo](https://github.com/okahu-demos) |
| [OpenAI Traces and Evals](https://platform.openai.com) | Built-in OpenAI platform capabilities for tracing agent workflows and running evaluations on traces and datasets. | API · Web · Hosted | [Website](https://platform.openai.com) / [Docs](https://developers.openai.com/api/docs/guides/agent-evals) / [Repo](https://github.com/openai/evals) |
| [OpenClaw Monitor](https://github.com/flik2002/openclaw-monitor) | Real-time monitoring dashboard for OpenClaw agents — track task execution, token usage, and agent activity with an intuitive UI. | Web · Self-hosted | [Repo](https://github.com/flik2002/openclaw-monitor) |
| [OpenInference](https://arize-ai.github.io/openinference/) | Open-source OpenTelemetry-based specification and instrumentations for tracing AI and LLM applications. | Library · Local | [Docs](https://arize-ai.github.io/openinference/) / [Repo](https://github.com/Arize-ai/openinference) |
| [OpenLIT](https://openlit.io) | Open-source OpenTelemetry-native observability and evaluations platform for GenAI and LLM applications. | API · CLI · Web · Self-hosted | [Website](https://openlit.io) / [Docs](https://docs.openlit.io) / [Repo](https://github.com/openlit/openlit) |
| [OpenObserve LLM Observability](https://openobserve.ai) | Open-source observability platform that unifies infrastructure and LLM observability with logs, metrics, and traces. | API · Web · Hybrid | [Website](https://openobserve.ai) / [Docs](https://openobserve.ai/docs) / [Repo](https://github.com/openobserve/openobserve) |
| [OpenSearch GenAI Observability SDK](https://opensearch.org) | OpenTelemetry-native Python SDK for one-line LLM observability using OpenSearch and Data Prepper as backend. | Library · Local | [Website](https://opensearch.org) / [Docs](https://github.com/opensearch-project/genai-observability-sdk-py#readme) / [Repo](https://github.com/opensearch-project/genai-observability-sdk-py) |
| [PostHog LLM Analytics](https://posthog.com) | LLM observability product in PostHog that captures traces, spans, and sessions for AI-powered applications. | API · Web · Hosted | [Website](https://posthog.com) / [Docs](https://posthog.com/docs/ai-engineering/llm-analytics) / [Repo](https://github.com/PostHog/posthog) |
| [Respan](https://respan.ai) | LLM engineering platform that unifies observability, evals, prompt optimization, and gateway for AI applications. | API · Web · Hosted | [Website](https://respan.ai) |
| [Traceloop OpenLLMetry](https://traceloop.com) | Open-source OpenTelemetry extensions and SDKs for providing LLM and RAG observability across backends. | API · Local | [Website](https://traceloop.com) / [Docs](https://docs.traceloop.com) / [Repo](https://github.com/traceloop/openllmetry) |
| [TruLens](https://www.trulens.org) | Open-source library for tracing and evaluating AI agents, RAG systems, and LLM applications with feedback functions. | Web · Local | [Website](https://www.trulens.org) / [Docs](https://www.trulens.org/docs) / [Repo](https://github.com/truera/trulens) |
| [Weights & Biases Weave](https://wandb.ai) | Framework and UI for debugging, tracing, and monitoring LLM applications with W&B observability. | API · Web · Hybrid | [Website](https://wandb.ai) / [Docs](https://docs.wandb.ai/guides/weave) / [Repo](https://github.com/wandb/weave) |
| [WhyLabs OpenLLMTelemetry](https://whylabs.ai) | Python library that instruments LLM calls and sends OpenTelemetry traces and safeguards data to WhyLabs. | API · Local | [Website](https://whylabs.ai) / [Docs](https://docs.whylabs.ai/docs/openllmtelemetry) / [Repo](https://github.com/whylabs/openllmtelemetry) |
| [Zenity AI Observability Platform](https://zenity.io/platform/ai-observability) | Security-focused AI observability platform for discovering and monitoring agents across SaaS, endpoints, and environments. | API · Web · Hosted | [Website](https://zenity.io/platform/ai-observability) |
### Agent evals
Evaluation frameworks and systems for agents, LLM apps, and developer workflows.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Agent Eval Framework](https://github.com/goker/agent-eval-framework) | Python package for production-grade evaluation and continuous improvement of AI agents across multiple quality dimensions. | Framework · Library | [Repo](https://github.com/goker/agent-eval-framework) |
| [Agentic Security](https://github.com/msoedov/agentic_security) | Open-source vulnerability scanner and red-teaming kit for LLM agents and workflows focused on security evaluation. | CLI · Framework · Library | [Repo](https://github.com/msoedov/agentic_security) |
| [Async Labs LLM Eval (PHP)](https://github.com/Aysnc-Labs/llm-eval) | PHP package for evaluating LLM outputs to test prompts and validate responses in PHP applications. | Framework · Library | [Repo](https://github.com/Aysnc-Labs/llm-eval) |
| [AWS Agent Evaluation](https://awslabs.github.io/agent-evaluation/) | Generative AI-powered framework from AWS Labs to test virtual agents via multi-turn conversations and CI-friendly workflows. | CLI · Framework · Library | [Docs](https://awslabs.github.io/agent-evaluation/) / [Repo](https://github.com/awslabs/agent-evaluation) |
| [DeepEval](https://deepeval.com) | Python framework for unit testing and benchmarking LLM applications, RAG systems, and agents with research-backed metrics. | CLI · Framework · Library | [Website](https://deepeval.com) / [Repo](https://github.com/confident-ai/deepeval) |
| [DeepTeam](https://github.com/confident-ai/deepteam) | Open-source LLM red teaming framework for simulating attacks and evaluating safety of LLM systems using DeepEval metrics. | CLI · Framework · Library | [Repo](https://github.com/confident-ai/deepteam) |
| [Guardrails AI](https://github.com/ShreyaR/guardrails) | Python library for enforcing structured outputs, validations, and safety constraints on LLM and agent responses. | Framework · Library · Local | [Docs](https://www.guardrailsai.com) / [Repo](https://github.com/ShreyaR/guardrails) |
| [LangChain OpenEvals](https://github.com/langchain-ai/openevals) | Open-source collection of ready-made evaluators for LLM applications in the LangChain ecosystem. | Framework · Library | [Repo](https://github.com/langchain-ai/openevals) |
| [LangFair](https://cvs-health.github.io/langfair/) | Python library for use-case level LLM bias and fairness assessment using bring-your-own-prompts workflows. | Framework · Library | [Docs](https://cvs-health.github.io/langfair/) / [Repo](https://github.com/cvs-health/langfair) |
| [Langfuse](https://langfuse.com/docs) | Open-source LLM engineering platform for observability, tracing, prompt management, datasets, and evaluations. | API · Web · Hybrid | [Docs](https://langfuse.com/docs) / [Repo](https://github.com/langfuse/langfuse) |
| [LangSmith Evaluations](https://www.langchain.com/langsmith/evaluation) | Hosted evaluation and tracing platform for LLM apps and agents with dataset-based and online eval workflows. | API · Framework · Web | [Website](https://www.langchain.com/langsmith/evaluation) / [Docs](https://docs.smith.langchain.com) |
| [LLM Evaluation Framework (Inference-Time)](https://github.com/mmjerge/LLM-Evaluation-Framework) | Research framework implementing multiple inference-time methods to evaluate LLM reliability across reasoning strategies. | Framework · Library | [Repo](https://github.com/mmjerge/LLM-Evaluation-Framework) |
| [nuclia-eval](https://pypi.org/project/nuclia-eval/) | Python library for evaluating RAG experiences with Nuclia’s REMi models using RAG triad metrics. | Framework · Library | [Website](https://pypi.org/project/nuclia-eval/) / [Repo](https://github.com/nuclia/nuclia-eval) |
| [Open RAG Eval](https://www.vectara.com/blog/introducing-open-rag-eval-the-open-source-framework-for-comparing-rag-solutions) | Python toolkit from Vectara for evaluating and comparing RAG pipelines using TREC-RAG style metrics. | CLI · Framework · Library | [Website](https://www.vectara.com/blog/introducing-open-rag-eval-the-open-source-framework-for-comparing-rag-solutions) / [Docs](https://docs.vectara.com/docs/hallucination-and-evaluation/open-eval-framework) / [Repo](https://github.com/vectara/open-rag-eval) |
| [OpenAI HumanEval Harness](https://github.com/openai/human-eval) | Evaluation harness and dataset for assessing LLM code generation via functional correctness tests. | CLI · Framework · Library | [Repo](https://github.com/openai/human-eval) |
| [Promptfoo](https://www.promptfoo.dev) | Open-source framework and CLI for testing prompts, models, RAG pipelines, and LLM security via automated evals and red teaming. | CLI · Framework · Library · Web | [Website](https://www.promptfoo.dev) / [Docs](https://www.promptfoo.dev/docs) / [Repo](https://github.com/promptfoo/promptfoo) |
| [PyHDL-Eval](https://github.com/cornell-brg/pyhdl-eval) | Domain-specific LLM evaluation framework for assessing hardware design code generation using Python-embedded DSLs and RTL tasks. | CLI · Framework · Library | [Repo](https://github.com/cornell-brg/pyhdl-eval) |
| [RAG Evaluation Harnesses](https://github.com/RulinShao/RAG-evaluation-harnesses) | Evaluation harness adapted from lm-evaluation-harness for retrieval-augmented generation tasks. | CLI · Framework · Library | [Repo](https://github.com/RulinShao/RAG-evaluation-harnesses) |
| [RAGAS](https://docs.ragas.io) | Open-source toolkit for automated evaluation of RAG systems using reference-free and reference-based metrics. | CLI · Framework · Library | [Website](https://docs.ragas.io) / [Docs](https://docs.ragas.io/en/latest/) / [Repo](https://github.com/vibrantlabsai/ragas) |
| [Rhesis AI](https://www.rhesis.ai) | Open-source collaborative testing platform for LLM and agentic applications with UI, SDK, and CI integration. | API · CLI · Framework · Web | [Website](https://www.rhesis.ai) / [Docs](https://docs.rhesis.ai) / [Repo](https://github.com/rhesis-ai/rhesis) |
| [Unitxt](https://www.unitxt.ai) | IBM-backed library and catalog for textual data preparation and evaluation of generative language models across many tasks. | CLI · Framework · Library | [Website](https://www.unitxt.ai) / [Docs](https://www.unitxt.ai/en/main/docs/introduction.html) / [Repo](https://github.com/ibm/unitxt) |
| [Vectara Open Evaluation UI](https://www.vectara.com/blog/open-evaluation) | Web UI for loading reports from Open RAG Eval and comparing RAG configurations across queries and metrics. | Framework · Web | [Website](https://www.vectara.com/blog/open-evaluation) / [Docs](https://docs.vectara.com/docs/hallucination-and-evaluation/open-eval-framework) |
### Self-hosted AI dev stacks
Self-hostable platforms and infrastructure for AI developer workflows.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [AnythingLLM](https://useanything.com) | Self-hosted RAG and agent platform with no-code agent builder and Docker Compose deployment options. | API · CLI · Web · Hybrid | [Website](https://useanything.com) / [Docs](https://docs.useanything.com) / [Repo](https://github.com/Mintplex-Labs/anything-llm) |
| [Athenaeum](https://github.com/herakles-dev/athenaeum#readme) | Self-hosted semantic library platform with embeddings, chat UI, pgvector, and MCP server support. | API · MCP · Web · Self-hosted | [Docs](https://github.com/herakles-dev/athenaeum#readme) / [Repo](https://github.com/herakles-dev/athenaeum) |
| [Clawix AI Platform](https://github.com/ClawixAI/clawix#readme) | Open-source, self-hosted multi-agent AI orchestration platform running agents in isolated Docker containers. | CLI · Web · Self-hosted | [Docs](https://github.com/ClawixAI/clawix#readme) / [Repo](https://github.com/ClawixAI/clawix) |
| [DevBox AI Dev Stack](https://github.com/gl0bal01/devbox#readme) | Zero-trust dev environment repository including an AI dev stack installer for Docker-based tools on a VPS. | CLI · Self-hosted | [Docs](https://github.com/gl0bal01/devbox#readme) / [Repo](https://github.com/gl0bal01/devbox) |
| [Dify](https://dify.ai) | Open-source LLMOps platform with visual studio for chatbots, workflows, agents, and RAG that supports self-hosted deployment. | API · Web · Hybrid | [Website](https://dify.ai) / [Docs](https://docs.dify.ai) / [Repo](https://github.com/langgenius/dify) |
| [Harbor CLI Stack](https://github.com/harbor-ai/harbor#readme) | CLI tool that spins up a local LLM stack (Ollama, Open WebUI, others) with a single command using container orchestration. | CLI · Template · Local | [Docs](https://github.com/harbor-ai/harbor#readme) / [Repo](https://github.com/harbor-ai/harbor) |
| [Jan Server](https://jan.ai) | Self-hosted agentic AI platform powered by local models with Docker Compose-based infrastructure files. | API · CLI · Framework · Web · Self-hosted | [Website](https://jan.ai) / [Docs](https://github.com/janhq/server#readme) / [Repo](https://github.com/janhq/server) |
| [Langfuse](https://langfuse.com/docs) | Open-source LLM engineering platform for observability, tracing, prompt management, datasets, and evaluations. | API · Web · Hybrid | [Docs](https://langfuse.com/docs) / [Repo](https://github.com/langfuse/langfuse) |
| [Local LLM Docker (mythrantic)](https://github.com/mythrantic/ollama-docker#readme) | Docker Compose setup for running Ollama and a web UI in containers with GPU optional. | Web · Self-hosted | [Docs](https://github.com/mythrantic/ollama-docker#readme) / [Repo](https://github.com/mythrantic/ollama-docker) |
| [Nosia](https://nosia.ai) | Self-hosted RAG platform with OpenAI-compatible API, Docker Compose deployment, and web UI for chat over private documents. | API · CLI · Web · Self-hosted | [Website](https://nosia.ai) / [Docs](https://nosia.ai/readme/) |
| [Nosia Installer Stack](https://get.nosia.ai) | Scripted Docker Compose stack that installs Nosia plus dependencies for self-hosted RAG and chat on local infrastructure. | CLI · Web · Self-hosted | [Website](https://get.nosia.ai) / [Docs](https://nosia.ai/readme/) |
| [Onyx](https://onyx.dotenv.dev) | Open-source self-hostable AI platform offering chat UI with agents, RAG, MCP tools, and multi-provider model support. | API · MCP · Web · Self-hosted | [Website](https://onyx.dotenv.dev) / [Docs](https://github.com/onyx-dot-app/onyx#readme) / [Repo](https://github.com/onyx-dot-app/onyx) |
| [Open WebUI Platform](https://openwebui.com) | Self-hosted AI platform and UI that supports Ollama and OpenAI-compatible APIs and can run entirely offline. | API · Web · Self-hosted | [Website](https://openwebui.com) / [Docs](https://docs.openwebui.com) / [Repo](https://github.com/open-webui/open-webui) |
| [OpenRAG](https://github.com/langflow-ai/openrag) | Open-source RAG stack combining Langflow, Docling, and OpenSearch with single-command Docker Compose deployment. | API · Web · Self-hosted | [Docs](https://github.com/langflow-ai/openrag#readme) / [Repo](https://github.com/langflow-ai/openrag) |
| [Paddler](https://github.com/intentee/paddler#readme) | Open-source LLMOps platform for hosting and scaling AI models in your own infrastructure. | API · CLI · Web · Self-hosted | [Docs](https://github.com/intentee/paddler#readme) / [Repo](https://github.com/intentee/paddler) |
| [Pleng](https://pleng.dev) | Self-hosted AI platform engineer that installs a Docker-based PaaS with AI agents and automation on your own cloud. | CLI · Web · Self-hosted | [Website](https://pleng.dev) / [Docs](https://github.com/mutonby/pleng#readme) / [Repo](https://github.com/mutonby/pleng) |
| [Redis + Ollama RAG Stack](https://github.com/TtheBC01/redis-ollama-RAG#readme) | Docker-based stack using RedisVL, Ollama, FastAPI, and RQ worker to build a local RAG pipeline. | API · CLI · Self-hosted | [Docs](https://github.com/TtheBC01/redis-ollama-RAG#readme) / [Repo](https://github.com/TtheBC01/redis-ollama-RAG) |
| [Refact.ai](https://refact.ai/) | Coding agent for IDEs and enterprises that can automate coding, debugging, testing, and documentation tasks. | IDE · Web · Hybrid | [Website](https://refact.ai/) / [Docs](https://docs.refact.ai/) / [Repo](https://github.com/smallcloudai/refact-vscode) |
| [Ruflo](https://github.com/ruvnet/ruflo) | Enterprise-grade multi-agent orchestration framework for Claude that deploys 60+ specialized AI agents with shared memory, RAG, and swarm coordination across machines and teams. | API · CLI · Web · Self-hosted | [Docs](https://github.com/ruvnet/ruflo#readme) / [Repo](https://github.com/ruvnet/ruflo) |
| [Scalable Agentic RAG Platform (FareedKhan-dev)](https://github.com/FareedKhan-dev/scalable-rag-pipeline#readme) | Production-grade agentic RAG platform with Kubernetes, Ray, LangGraph, and multi-plane architecture. | CLI · Self-hosted | [Docs](https://github.com/FareedKhan-dev/scalable-rag-pipeline#readme) / [Repo](https://github.com/FareedKhan-dev/scalable-rag-pipeline) |
| [Self-hosted AI Package](https://sourceforge.net/projects/self-hosted-ai-package.mirror/) | Open-source Docker Compose starter kit bundling Ollama, n8n, Supabase, Open WebUI, Flowise, Neo4j, Langfuse, and related tools. | API · Web · Self-hosted | [Website](https://sourceforge.net/projects/self-hosted-ai-package.mirror/) / [Repo](https://github.com/coleam00/ai-agents-masterclass) |
| [Self-hosted AI Starter Kit (n8n)](https://docs.n8n.io/hosting/starter-kits/ai-starter-kit/) | Docker Compose-based local AI and low-code stack bundling n8n, Ollama, Qdrant, PostgreSQL, and related services. | API · CLI · Web · Self-hosted | [Docs](https://docs.n8n.io/hosting/starter-kits/ai-starter-kit/) / [Repo](https://github.com/n8n-io/self-hosted-ai-starter-kit) |
| [Synaplan AI Platform](https://synaplan.com/solutions/developers) | Open-source, self-hosted AI platform with full stack deployment via Docker Compose and local inference via Ollama. | API · Web · Self-hosted | [Website](https://synaplan.com/solutions/developers) / [Docs](https://synaplan.com/docs) |
| [Tabby](https://www.tabbyml.com/) | Self-hosted AI coding assistant for teams that want private code assistance and repository-aware development. | API · IDE · Self-hosted | [Website](https://www.tabbyml.com/) / [Docs](https://tabby.tabbyml.com/docs/) / [Repo](https://github.com/TabbyML/tabby) |
| [Winy RAG Sample Stack](https://github.com/mfranzon/winy) | Sample RAG application with Ollama, Qdrant, and Streamlit web app orchestrated via Docker Compose. | Web · Self-hosted | [Docs](https://github.com/mfranzon/winy#readme) / [Repo](https://github.com/mfranzon/winy) |
### Local LLM developer tools
Tools that help developers run or integrate local models in coding workflows.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ#readme) | Python library for GPTQ weight-only quantization of Transformer language models for efficient local inference. | Library · Local | [Docs](https://github.com/AutoGPTQ/AutoGPTQ#readme) / [Repo](https://github.com/AutoGPTQ/AutoGPTQ) |
| [ChromaDB](https://www.trychroma.com) | Lightweight vector database and Python library for local embeddings storage and RAG-style similarity search. | API · Library · Local | [Website](https://www.trychroma.com) / [Docs](https://docs.trychroma.com) / [Repo](https://github.com/chroma-core/chroma) |
| [Docker Model Runner](https://www.docker.com/products/model-runner) | Docker Desktop-integrated local model runtime that runs GGUF models via an OpenAI-compatible API. | API · CLI · Local | [Website](https://www.docker.com/products/model-runner) / [Docs](https://docs.docker.com/ai/model-runner/) |
| [ExLlamaV2](https://github.com/turboderp-org/exllamav2#readme) | Inference library for running GPTQ-quantized LLMs on modern consumer GPUs with high performance. | CLI · Library · Local | [Docs](https://github.com/turboderp-org/exllamav2#readme) / [Repo](https://github.com/turboderp-org/exllamav2) |
| [GPT4All](https://gpt4all.io) | Local LLM desktop client and Python library with optional OpenAI-compatible API server on localhost. | API · Desktop · Library · Local | [Website](https://gpt4all.io) / [Docs](https://docs.gpt4all.io) / [Repo](https://github.com/nomic-ai/gpt4all) |
| [Haystack](https://github.com/deepset-ai/haystack) | Open-source framework for building RAG pipelines, agents, and semantic search over private data. | API · Framework · Local | [Docs](https://docs.haystack.deepset.ai) / [Repo](https://github.com/deepset-ai/haystack) |
| [Intel Neural Compressor](https://github.com/intel/neural-compressor) | Open-source compression toolkit supporting quantization and pruning for deep learning and LLM workloads. | Library · Local | [Docs](https://intel.github.io/neural-compressor) / [Repo](https://github.com/intel/neural-compressor) |
| [KoboldCpp](https://koboldcpp.com) | Single-file local LLM server and web UI for GGUF models with Kobold-style API and OpenAI-like integrations. | API · CLI · Web · Local | [Website](https://koboldcpp.com) / [Docs](https://github.com/LostRuins/koboldcpp/wiki) / [Repo](https://github.com/LostRuins/koboldcpp) |
| [LiteLLM Gateway](https://github.com/BerriAI/litellm) | Drop-in proxy that unifies many LLM providers behind an OpenAI-compatible API, with logging and rate limiting. | API · CLI · Self-hosted | [Docs](https://docs.litellm.ai) / [Repo](https://github.com/BerriAI/litellm) |
| [llama-cpp-python](https://llama-cpp-python.readthedocs.io) | Python bindings and OpenAI-compatible web server for llama.cpp, exposing local models via HTTP and Python APIs. | API · CLI · Library · Self-hosted | [Docs](https://llama-cpp-python.readthedocs.io) / [Repo](https://github.com/abetlen/llama-cpp-python) |
| [llama.cpp](https://github.com/ggml-org/llama.cpp/tree/master/examples) | C/C++ LLM inference library and tools for running quantized models on CPUs and GPUs with optional HTTP and OpenAI-style servers. | API · CLI · Library · Self-hosted | [Docs](https://github.com/ggml-org/llama.cpp/tree/master/examples) / [Repo](https://github.com/ggml-org/llama.cpp) |
| [Llamafile](https://github.com/Mozilla-Ocho/llamafile/blob/main/README.md) | Single-file local LLM runtime bundling llama.cpp and web UI, with an OpenAI-compatible /v1 chat completions endpoint. | API · CLI · Web · Local | [Docs](https://github.com/Mozilla-Ocho/llamafile/blob/main/README.md) / [Repo](https://github.com/Mozilla-Ocho/llamafile) |
| [LlamaIndex](https://www.llamaindex.ai) | Framework for building RAG and agent systems that can target local LLMs and embedding backends like Ollama or llamafile. | Framework · Library · Local | [Website](https://www.llamaindex.ai) / [Docs](https://developers.llamaindex.ai) / [Repo](https://github.com/run-llama/llama_index) |
| [LLM Compressor](https://docs.vllm.ai/projects/llm-compressor/en/latest/) | Compression and quantization library for optimizing LLMs for deployment with vLLM. | Library · Local | [Docs](https://docs.vllm.ai/projects/llm-compressor/en/latest/) / [Repo](https://github.com/vllm-project/llm-compressor) |
| [llm-llamafile](https://github.com/simonw/llm-llamafile#readme) | Plugin for the `llm` CLI that lets you use a locally running llamafile server as an LLM provider. | CLI · Library · Local | [Docs](https://github.com/simonw/llm-llamafile#readme) / [Repo](https://github.com/simonw/llm-llamafile) |
| [LM Studio](https://lmstudio.ai) | Cross-platform desktop app and SDKs to discover, run, and serve local LLMs with an OpenAI-compatible server mode. | API · CLI · Desktop · Local | [Website](https://lmstudio.ai) / [Docs](https://lmstudio.ai/docs) / [Repo](https://github.com/lmstudio-ai) |
| [LMDeploy](https://lmdeploy.readthedocs.io) | OpenAI-compatible API server for deploying multimodal models with LMDeploy on GPUs, locally or via Docker. | API · CLI · Self-hosted | [Website](https://lmdeploy.readthedocs.io) / [Docs](https://lmdeploy.readthedocs.io/en/latest/multi_modal/api_server_vl.html) / [Repo](https://github.com/InternLM/lmdeploy) |
| [LocalAI](https://localai.io) | Self-hosted REST server that emulates the OpenAI API to run local ggml/llama.cpp and related models on your own hardware. | API · CLI · Self-hosted | [Website](https://localai.io) / [Docs](https://localai.io/docs) / [Repo](https://github.com/go-skynet/LocalAI) |
| [Mistral Inference](https://github.com/mistralai/mistral-inference#readme) | Official inference library for running Mistral models via CLI and Python on local or server hardware. | CLI · Library · Self-hosted | [Docs](https://github.com/mistralai/mistral-inference#readme) / [Repo](https://github.com/mistralai/mistral-inference) |
| [mistral.rs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/README.md) | Rust-based engine for fast, flexible LLM inference with OpenAI-compatible APIs, web UI, and extensive quantization options. | API · CLI · Library · Web · Self-hosted | [Docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/README.md) / [Repo](https://github.com/EricLBuehler/mistral.rs) |
| [MLC LLM](https://mlc.ai) | Universal LLM deployment engine and compiler for running quantized models natively across many hardware backends. | API · CLI · Library · Self-hosted | [Website](https://mlc.ai) / [Docs](https://llmc-en.readthedocs.io/en/stable/backend/mlcllm.html) / [Repo](https://github.com/mlc-ai/mlc-llm) |
| [MLX Engine for LM Studio](https://github.com/lmstudio-ai/mlx-engine#readme) | Apple MLX-based inference engine used by LM Studio to run quantized text and vision models locally on macOS. | Library · Local | [Docs](https://github.com/lmstudio-ai/mlx-engine#readme) / [Repo](https://github.com/lmstudio-ai/mlx-engine) |
| [mlx-lm](https://github.com/ml-explore/mlx-lm#readme) | Apple MLX-based Python package for running and fine-tuning LLMs on Apple silicon, with an HTTP server similar to OpenAI chat API. | API · CLI · Library · Local | [Docs](https://github.com/ml-explore/mlx-lm#readme) / [Repo](https://github.com/ml-explore/mlx-lm) |
| [Ollama](https://ollama.com) | Local LLM runtime and model manager that runs open models on your machine with an OpenAI-compatible Chat Completions API. | API · CLI · Local | [Website](https://ollama.com) / [Docs](https://docs.ollama.com) / [Repo](https://github.com/ollama/ollama) |
| [PydanticAI](https://github.com/pydantic/pydantic-ai) | Pydantic-based framework for building typed LLM apps and agents with validation, tools, and structured outputs. | Framework · Library · Local | [Docs](https://ai.pydantic.dev) / [Repo](https://github.com/pydantic/pydantic-ai) |
| [Tabby](https://www.tabbyml.com/) | Self-hosted AI coding assistant for teams that want private code assistance and repository-aware development. | API · IDE · Self-hosted | [Website](https://www.tabbyml.com/) / [Docs](https://tabby.tabbyml.com/docs/) / [Repo](https://github.com/TabbyML/tabby) |
| [TabbyAPI](https://github.com/theroyallab/tabbyAPI#readme) | FastAPI-based backend server for ExLlamaV2 that exposes local text generation over HTTP for coding and chat workloads. | API · Self-hosted | [Docs](https://github.com/theroyallab/tabbyAPI#readme) / [Repo](https://github.com/theroyallab/tabbyAPI) |
| [Text Generation Inference](https://huggingface.co/docs/text-generation-inference) | High-performance Rust and Python server for deploying and serving open-source LLMs via HTTP and gRPC. | API · CLI · Self-hosted | [Website](https://huggingface.co/docs/text-generation-inference) / [Docs](https://huggingface.co/docs/text-generation-inference/index) / [Repo](https://github.com/huggingface/text-generation-inference) |
| [text-generation-webui](https://github.com/oobabooga/text-generation-webui#readme) | Self-hosted Gradio/Web UI and API for running diverse local text generation models on CPUs and GPUs. | CLI · Web · Self-hosted | [Docs](https://github.com/oobabooga/text-generation-webui#readme) / [Repo](https://github.com/oobabooga/text-generation-webui) |
| [vLLM](https://vllm.ai) | High-throughput LLM inference engine with an OpenAI-compatible HTTP server for serving models locally or on servers. | API · CLI · Library · Self-hosted | [Website](https://vllm.ai) / [Docs](https://docs.vllm.ai/en/stable/serving/openai_compatible_server.html) / [Repo](https://github.com/vllm-project/vllm) |
| [WebLLM](https://webllm.mlc.ai) | In-browser LLM inference engine using WebGPU that exposes an OpenAI-compatible API surface for local models. | Library · Web · Local | [Website](https://webllm.mlc.ai) / [Docs](https://github.com/mlc-ai/web-llm#readme) / [Repo](https://github.com/mlc-ai/web-llm) |
### Repo automation tools
AI tools that automate repository checks, changes, pull requests, or maintenance.
| Tool | Good for | Experience | Links |
| --- | --- | --- | --- |
| [Amazon Q Developer](https://aws.amazon.com/q/developer/) | AWS coding assistant with IDE, CLI, and GitHub agents for coding, testing, review, and transformations. | CLI · GitHub app · IDE · Hybrid | [Website](https://aws.amazon.com/q/developer/) / [Docs](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) |
| [Amp](https://ampcode.com/) | Terminal-centric coding agent with deep codebase context, editor links, and automation-oriented SDK features. | API · CLI · Hybrid | [Website](https://ampcode.com/) / [Docs](https://ampcode.com/manual) |
| [auto-changelog (cookpete)](https://github.com/cookpete/auto-changelog) | CLI tool that generates a changelog from git tags and commit history for use in release workflows. | CLI · Local | [Repo](https://github.com/cookpete/auto-changelog) |
| [automerge-action](https://github.com/marketplace/actions/merge-pull-requests-automerge-action) | GitHub Action that automatically merges pull requests labeled for automerge once checks and reviews pass. | GitHub app | [Docs](https://github.com/marketplace/actions/merge-pull-requests-automerge-action) / [Repo](https://github.com/pascalgn/automerge-action) |
| [Bito AI Code Review Agent](https://bito.ai/product/ai-code-review-agent/) | Repository review agent for GitHub, GitLab, and Bitbucket pull or merge request workflows. | GitHub app · Hosted | [Website](https://bito.ai/product/ai-code-review-agent/) / [Docs](https://docs.bito.ai/ai-code-reviews-in-git/install-run-using-bito-cloud/guide-for-github) |
| [changelog-generator (jaywcjlove)](https://github.com/jaywcjlove/changelog-gene