{"id":83786,"url":"https://github.com/nipunaranasinghe/awesome-ai-agents","name":"awesome-ai-agents","description":"A curated list of frameworks, tools, and resources for building and deploying AI agents.","projects_count":155,"last_synced_at":"2026-10-03T19:00:27.928Z","repository":{"id":274181609,"uuid":"922150731","full_name":"NipunaRanasinghe/awesome-ai-agents","owner":"NipunaRanasinghe","description":"A curated list of frameworks, tools, and resources for building and deploying AI agents.","archived":false,"fork":false,"pushed_at":"2026-09-23T08:26:42.000Z","size":6446,"stargazers_count":49,"open_issues_count":27,"forks_count":59,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-09-24T00:33:11.547Z","etag":null,"topics":["ai","ai-agent","ai-agents","awesome","awesome-agents","awesome-ai","awesome-list","awesome-lists","curated-list"],"latest_commit_sha":null,"homepage":"https://nipunaranasinghe.github.io/awesome-ai-agents","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NipunaRanasinghe.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"claude":null,"gemini":null,"cursor":null,"copilot":null,"dco":null,"cla":null,"disclosure":null}},"created_at":"2025-01-25T13:05:25.000Z","updated_at":"2026-09-23T20:53:22.000Z","dependencies_parsed_at":"2026-09-23T09:45:51.686Z","dependency_job_id":null,"html_url":"https://github.com/NipunaRanasinghe/awesome-ai-agents","commit_stats":null,"previous_names":["nipunaranasinghe/awesome-ai-agents"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/NipunaRanasinghe/awesome-ai-agents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NipunaRanasinghe%2Fawesome-ai-agents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NipunaRanasinghe%2Fawesome-ai-agents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NipunaRanasinghe%2Fawesome-ai-agents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NipunaRanasinghe%2Fawesome-ai-agents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NipunaRanasinghe","download_url":"https://codeload.github.com/NipunaRanasinghe/awesome-ai-agents/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NipunaRanasinghe%2Fawesome-ai-agents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":343072799,"owners_count":37980209,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-10-03T02:00:07.567Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-01-26T12:14:18.059Z","updated_at":"2026-10-03T19:00:27.929Z","primary_language":"Python","list_of_lists":false,"displayable":true,"categories":["🌐 Community Resources","📚 Research \u0026 Benchmarks","🚀 Specialized Agents","⚙ïļ Agent Operations","🌟 Core Frameworks","🚀 Contributors","Contributing"],"sub_categories":["📰 Newsletters","📄 Papers","ðŸ’ŧ Coding Agents","🚀 Deployment","ðŸ—Ģïļ Programming Language Agents","📊 Benchmarks","🧠 Memory","📈 Observability","🔎 Research Agents","ðŸŽĻ Creative Agents","📊 Evaluation","🔒 Security \u0026 Governance","🎙ïļ Voice Agents","🌐 Web \u0026 Computer Use Agents","🔌 Protocols","ðŸ‘Ĩ Communities"],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003c!-- title --\u003e\n\n\u003c!--lint ignore no-dead-urls--\u003e\n\n# Awesome AI Agents\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n\u003c!-- description --\u003e\n\n_A curated list of frameworks, tools, libraries, platforms, and resources for building and deploying AI agents._\n\n\u003cp\u003e\n \u003ca href=\"https://nipunaranasinghe.github.io/awesome-ai-agents/\"\u003e\u003cimg src=\"https://img.shields.io/badge/Browse_the_list_as_a_website-2ea44f?style=for-the-badge\u0026logo=githubpages\u0026logoColor=white\" height=\"40\" alt=\"Browse the list as a website\"\u003e\u003c/a\u003e\u0026nbsp;\u0026nbsp;\u003ca href=\"CHANGELOG.md\"\u003e\u003cimg src=\"https://img.shields.io/badge/What%27s_new-Changelog-0a7bbc?style=for-the-badge\u0026logo=keepachangelog\u0026logoColor=white\" height=\"40\" alt=\"What's new — Changelog\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003c!-- image --\u003e\n\n\u003ca href=\"https://github.com/NipunaRanasinghe/awesome-ai-agents\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\n \u003cimg src=\"resources/images/image.png\" alt=\"Awesome AI Agents Logo\"\u003e\n\u003c/a\u003e\n\n\u003c!-- contributors --\u003e\n\n\u003cbr\u003e\u003cbr\u003e\n\n**Built by the community** — \u003ca href=\"CONTRIBUTING.md\"\u003eadd your project\u003c/a\u003e\n\n\u003cbr\u003e\n\n\u003ca href=\"https://github.com/NipunaRanasinghe/awesome-ai-agents/graphs/contributors\"\u003e\n \u003cimg src=\"https://contrib.rocks/image?repo=NipunaRanasinghe/awesome-ai-agents\" alt=\"Contributors\"\u003e\n\u003c/a\u003e\n\n\u003c/div\u003e\n\n---\n\n## Contents\n\n- [🌟 Core Frameworks](#-core-frameworks)\n- [🚀 Specialized Agents](#-specialized-agents)\n - [ðŸ’ŧ Coding Agents](#-coding-agents)\n - [🔎 Research Agents](#-research-agents)\n - [ðŸŽĻ Creative Agents](#-creative-agents)\n - [🌐 Web \u0026 Computer Use Agents](#-web--computer-use-agents)\n - [ðŸ—Ģïļ Programming Language Agents](#-programming-language-agents)\n - [🎙ïļ Voice Agents](#-voice-agents)\n- [⚙ïļ Agent Operations](#-agent-operations)\n - [🧠 Memory](#-memory)\n - [📊 Evaluation](#-evaluation)\n - [📈 Observability](#-observability)\n - [🚀 Deployment](#-deployment)\n - [🔒 Security \u0026 Governance](#-security--governance)\n - [🔌 Protocols](#-protocols)\n- [📚 Research \u0026 Benchmarks](#-research--benchmarks)\n - [📄 Papers](#-papers)\n - [📊 Benchmarks](#-benchmarks)\n- [🌐 Community Resources](#-community-resources)\n - [ðŸ‘Ĩ Communities](#-communities)\n - [📰 Newsletters](#-newsletters)\n- [🚀 Contributors](#-contributors)\n\n---\n\n## 🌟 Core Frameworks\n\nFrameworks for building and managing AI agents.\n\n| Framework | Stars | Description |\n| -------------------------------------------------------------------------- | ------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| [AutoGen](https://github.com/microsoft/autogen) | ![](https://img.shields.io/github/stars/microsoft/autogen) | Multi-agent conversations, GPT-4 integration, customizable workflows |\n| [AutoGPT](https://github.com/Significant-Gravitas/AutoGPT) | ![](https://img.shields.io/github/stars/Significant-Gravitas/AutoGPT) | Autonomous AI agent for task completion, web browsing, and code execution |\n| [MetaGPT](https://github.com/FoundationAgents/MetaGPT) | ![](https://img.shields.io/github/stars/FoundationAgents/MetaGPT) | Simulates software company workflows, role-based agents |\n| [Neurolink](https://github.com/juspay/neurolink) | ![](https://img.shields.io/github/stars/juspay/neurolink) | Multi-provider AI agent framework, unifies 12+ LLM providers, workflow orchestration |\n| [CrewAI](https://github.com/crewAIInc/crewAI) | ![](https://img.shields.io/github/stars/crewAIInc/crewAI) | Role-based agent orchestration, task delegation |\n| [PraisonAI](https://github.com/MervinPraison/PraisonAI) | ![](https://img.shields.io/github/stars/MervinPraison/PraisonAI) | Fastest multi-agent framework (3.77Ξs), 100+ LLMs, MCP, workflows, Python \u0026 JS SDKs |\n| [LightAgent](https://github.com/wanxingai/LightAgent) | ![](https://img.shields.io/github/stars/wanxingai/LightAgent) | Lightweight Python agent framework with memory, MCP/SSE, Skills, streaming, and LightSwarm multi-agent collaboration |\n| [LangChain](https://github.com/langchain-ai/langchain) | ![](https://img.shields.io/github/stars/langchain-ai/langchain) | Tool integration, memory management, agent chaining |\n| [LangGraph](https://github.com/langchain-ai/langgraph) | ![](https://img.shields.io/github/stars/langchain-ai/langgraph) | Stateful, multi-actor applications with LLMs |\n| [SuperAGI](https://github.com/TransformerOptimus/SuperAGI) | ![](https://img.shields.io/github/stars/TransformerOptimus/SuperAGI) | Open-source AGI framework, multi-modal agents |\n| [Google ADK (Agent Development Kit)](https://github.com/google/adk-python) | ![](https://img.shields.io/github/stars/google/adk-python) | Code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents |\n| [OpenAI Assistants API (SDK)](https://github.com/openai/openai-python) | ![](https://img.shields.io/github/stars/openai/openai-python) | Build AI assistants with tools and persistent threads via SDK |\n| [AgentOps](https://github.com/AgentOps-AI/agentops) | ![](https://img.shields.io/github/stars/AgentOps-AI/agentops) | Monitoring, cost tracking, and benchmarking SDK for agents |\n| [AgentField](https://github.com/Agent-Field/agentfield) | ![](https://img.shields.io/github/stars/Agent-Field/agentfield) | Open-source control plane for AI agents at scale, with routing, memory, observability, identity, and auth |\n| [Agentset](https://github.com/agentset-ai/agentset) | ![](https://img.shields.io/github/stars/agentset-ai/agentset) | Production-ready RAG platform with agentic reasoning, hybrid search, and multimodal support |\n| [LLMStack](https://github.com/trypromptly/LLMStack) | ![](https://img.shields.io/github/stars/trypromptly/LLMStack) | No-code multi-agent framework with data workflows |\n| [Agency Swarm](https://github.com/VRSEN/agency-swarm) | ![](https://img.shields.io/github/stars/VRSEN/agency-swarm) | Reliable multi-agent orchestration using OpenAI Assistants API |\n| [AGiXT](https://github.com/Josh-XT/AGiXT) | ![](https://img.shields.io/github/stars/Josh-XT/AGiXT) | Adaptive automation platform with persistent memory |\n| [Upsonic](https://github.com/Upsonic/Upsonic) | ![](https://img.shields.io/github/stars/Upsonic/Upsonic) | Reliability layer, model context protocol, task-oriented |\n| [Taskade](https://github.com/taskade/taskade) | ![](https://img.shields.io/github/stars/taskade/taskade) | AI-native workspace for building and deploying multi-agent workflows |\n| [Taskade MCP](https://github.com/taskade/mcp) | ![](https://img.shields.io/github/stars/taskade/mcp) | Open-source MCP toolkit and integrations for building AI agents and automated workflows |\n| [AgentVerse](https://github.com/OpenBMB/AgentVerse) | ![](https://img.shields.io/github/stars/OpenBMB/AgentVerse) | Multi-agent simulation environments for research |\n| [ChatDev](https://github.com/OpenBMB/ChatDev) | ![](https://img.shields.io/github/stars/OpenBMB/ChatDev) | Collaborative software development agents |\n| [Agno](https://github.com/agno-agi/agno) | ![](https://img.shields.io/github/stars/agno-agi/agno) | Multi-agent framework, runtime, and control plane for AI products |\n| [Agentlas OS](https://github.com/agentlas-ai/Agentlas-OS) | ![][agentlas-stars] | Apache-2.0 local-first agent OS for portable agent and team packages, cross-host orchestration, MCP/A2A, and verification gates |\n| [Composio](https://github.com/ComposioHQ/composio) | ![](https://img.shields.io/github/stars/ComposioHQ/composio) | 100+ integrations for AI agents via function calling, MCP compatible |\n| [PocketFlow](https://github.com/The-Pocket/PocketFlow) | ![](https://img.shields.io/github/stars/The-Pocket/PocketFlow) | Minimalist 100-line LLM framework for agents, workflows, and RAG |\n| [CAMEL](https://github.com/camel-ai/camel) | ![](https://img.shields.io/github/stars/camel-ai/camel) | Multi-agent framework for communicative agents research |\n| [Strands Agents SDK](https://github.com/strands-agents/harness-sdk) | ![](https://img.shields.io/github/stars/strands-agents/harness-sdk) | AWS-backed model-driven agent SDK with MCP and multi-provider support |\n| [Summoner](https://github.com/Summoner-Network/summoner-agents) | ![](https://img.shields.io/github/stars/Summoner-Network/summoner-agents) | Agent-to-agent networking for server-decoupled agents over long-lived TCP sessions (Python/Rust), 50+ runnable templates |\n| [KodeAgent](https://github.com/barun-saha/kodeagent) | ![](https://img.shields.io/github/stars/barun-saha/kodeagent) | The Minimal Agent Engine to build ReAct \u0026 CodeAct agents, with support for code sandbox and observability |\n| [Hivemoot Colony](https://github.com/hivemoot/colony) | ![](https://img.shields.io/github/stars/hivemoot/colony) | Self-governing multi-agent platform; agents propose, vote, peer-review, and ship software via democratic consensus |\n| [OIXA Protocol](https://github.com/ivoshemi-sys/oixa-protocol) | ![](https://img.shields.io/github/stars/ivoshemi-sys/oixa-protocol) | Agent-to-agent economic marketplace protocol on Base with on-chain escrow and A2A integrations |\n| [smolagents](https://github.com/huggingface/smolagents) | ![](https://img.shields.io/github/stars/huggingface/smolagents) | Code-first agent library by Hugging Face, model-agnostic with MCP and sandbox support |\n| [LlamaIndex](https://github.com/run-llama/llama_index) | ![](https://img.shields.io/github/stars/run-llama/llama_index) | Data framework for LLM apps with RAG, agents, and 300+ integrations |\n| [Mastra](https://github.com/mastra-ai/mastra) | ![](https://img.shields.io/github/stars/mastra-ai/mastra) | TypeScript AI framework for agents, workflows, MCP servers, and evals |\n| [Hivekeep](https://github.com/MarlBurroW/hivekeep) | ![](https://img.shields.io/github/stars/MarlBurroW/hivekeep) | Self-hosted platform to run a team of specialized AI agents with persistent memory, a web UI, and Telegram/Slack/Discord/Matrix channels, in a single Bun and SQLite container |\n| [Orkas](https://github.com/Orkas-AI/Orkas) | ![](https://img.shields.io/github/stars/Orkas-AI/Orkas) | Local-first workspace coordinating specialist AI agents across projects |\n| [Better Agent](https://github.com/ofekron/better-agent) | ![](https://img.shields.io/github/stars/ofekron/better-agent) | Source-available workspace for running and supervising Claude, Codex, and Gemini coding-agent sessions |\n| [fractal](https://github.com/plasma-ai/fractal) | ![](https://img.shields.io/github/stars/plasma-ai/fractal) | Hierarchical coding-agent runtime with bounded autonomous loops, recursive delegation, isolated Git worktrees, persistent SQLite state, and live operator controls |\n| [YYLO](https://github.com/yylo-dev/yylo) | ![](https://img.shields.io/github/stars/yylo-dev/yylo) | Command-line orchestrator for coding agents with typed task, validation, merge, and release-readiness boundaries, a dedicated branch/worktree, and risk-based merge review |\n| [SandBase Harness](https://github.com/sandbaseai/sandbase-harness) | ![](https://img.shields.io/github/stars/sandbaseai/sandbase-harness) | Local-first, self-hosted TypeScript agent runtime and MCP bridge with sandboxed sessions and audit/replay |\n| [Tale](https://github.com/tale-project/tale) | ![](https://img.shields.io/github/stars/tale-project/tale) | Self-hosted workspace for people and AI agents, with shared project tasks, manager delegation, persistent sandbox workspaces, and human review of results |\n\n[agentlas-stars]: https://img.shields.io/github/stars/agentlas-ai/Agentlas-OS\n\n---\n\n## 🚀 Specialized Agents\n\nAgents designed for specific tasks or industries.\n\n### ðŸ’ŧ Coding Agents\n\n| Name | Stars | Description |\n| ------------------------------------------------------------ | ------------------------------------------------------------------ | ----------------------------------------------------------------------- |\n| [SWE-agent](https://github.com/SWE-agent/SWE-agent) | ![](https://img.shields.io/github/stars/SWE-agent/SWE-agent) | AI agent for software engineering tasks |\n| [GPT Pilot](https://github.com/Pythagora-io/gpt-pilot) | ![](https://img.shields.io/github/stars/Pythagora-io/gpt-pilot) | Assists in writing and debugging code |\n| [OpenHands](https://github.com/OpenHands/OpenHands) | ![](https://img.shields.io/github/stars/OpenHands/OpenHands) | Open-source AI software development agents (formerly OpenDevin) |\n| [Devika](https://github.com/stitionai/devika) | ![](https://img.shields.io/github/stars/stitionai/devika) | Agentic AI Software Engineer that writes code from natural instructions |\n| [Aider](https://github.com/Aider-AI/aider) | ![](https://img.shields.io/github/stars/Aider-AI/aider) | AI pair programming in terminal |\n| [Plandex](https://github.com/plandex-ai/plandex) | ![](https://img.shields.io/github/stars/plandex-ai/plandex) | AI coding engine for complex projects |\n| [TaskWeaver](https://github.com/microsoft/TaskWeaver) | ![](https://img.shields.io/github/stars/microsoft/TaskWeaver) | Code-first agent framework for analytical tasks |\n| [Gemini CLI](https://github.com/google-gemini/gemini-cli) | ![](https://img.shields.io/github/stars/google-gemini/gemini-cli) | Open-source AI agent bringing Gemini to the terminal with MCP support |\n| [AgenticSeek](https://github.com/Fosowl/agenticSeek) | ![](https://img.shields.io/github/stars/Fosowl/agenticSeek) | Fully local autonomous agent that browses web and codes without APIs |\n| [Cline](https://github.com/cline/cline) | ![](https://img.shields.io/github/stars/cline/cline) | Autonomous coding agent in VS Code with MCP, browser use, and terminal |\n| [Goose](https://github.com/aaif-goose/goose) | ![](https://img.shields.io/github/stars/aaif-goose/goose) | Open-source extensible AI agent by Block for engineering tasks |\n| [bolt.diy](https://github.com/stackblitz-labs/bolt.diy) | ![](https://img.shields.io/github/stars/stackblitz-labs/bolt.diy) | AI-powered full-stack web development in the browser with 19+ LLMs |\n| [Atomic Agent](https://github.com/AtomicBot-ai/atomic-agent) | ![](https://img.shields.io/github/stars/AtomicBot-ai/atomic-agent) | Local-first CLI and TUI coding agent, open-weight models, 56 tools, MCP |\n\n### 🔎 Research Agents\n\n| Name | Stars | Description |\n| --------------------------------------------------------------- | ------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |\n| [GPT Researcher](https://github.com/assafelovic/gpt-researcher) | ![](https://img.shields.io/github/stars/assafelovic/gpt-researcher) | Autonomous agent for comprehensive research |\n| [Dr. Claw](https://github.com/OpenLAIR/dr-claw) | ![](https://img.shields.io/github/stars/OpenLAIR/dr-claw) | Local research workspace with survey, ideation, experiment, publication, and promotion stages |\n| [Storm](https://github.com/stanford-oval/storm) | ![](https://img.shields.io/github/stars/stanford-oval/storm) | Multi-agent system for collaborative reasoning |\n| [DeerFlow](https://github.com/bytedance/deer-flow) | ![](https://img.shields.io/github/stars/bytedance/deer-flow) | Framework for deep research with web search and Python execution |\n| [Agon](https://github.com/AutoResearch-Factory/Agon) | ![](https://img.shields.io/github/stars/AutoResearch-Factory/Agon) | Prompt Economy orchestrator: reusable scientist/coder/auditor loops instead of per-task prompts, 18 roles, 10+ disciplines |\n| [AutoNumerics](https://github.com/Daviddjddu/Autonumerics) | ![](https://img.shields.io/github/stars/Daviddjddu/Autonumerics) | Writes, debugs, and validates classical PDE numerical solvers from plain-language problem descriptions |\n| [Caesar](https://github.com/jasonzliang/caesar-agent) | ![](https://img.shields.io/github/stars/jasonzliang/caesar-agent) | Builds a knowledge graph while exploring the web, then refines drafts via adversarial synthesis |\n| [P2PCLAW](https://github.com/Agnuxo1/OpenCLAW-P2P) | ![](https://img.shields.io/github/stars/Agnuxo1/OpenCLAW-P2P) | Decentralized P2P agent swarm for open scientific research |\n| [CAJAL](https://github.com/Agnuxo1/CAJAL) | ![](https://img.shields.io/github/stars/Agnuxo1/CAJAL) | Local scientific paper generation agent with IMRaD structure and citations |\n\n### ðŸŽĻ Creative Agents\n\n| Name | Stars | Description |\n| -------------------------------------------------------------- | --------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |\n| [ShortGPT](https://github.com/RayVentura/ShortGPT) | ![](https://img.shields.io/github/stars/RayVentura/ShortGPT) | Short-form video generation agent |\n| [AI-town](https://github.com/a16z-infra/ai-town) | ![](https://img.shields.io/github/stars/a16z-infra/ai-town) | Virtual world simulation with AI agents |\n| [BulkPublish](https://github.com/azeemkafridi/bulkpublish-api) | ![](https://img.shields.io/github/stars/azeemkafridi/bulkpublish-api) | API and agent skills for drafting, scheduling, and publishing social media content |\n\n### 🌐 Web \u0026 Computer Use Agents\n\n| Name | Stars | Description |\n| --------------------------------------------------------------- | -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |\n| [Browser Use](https://github.com/browser-use/browser-use) | ![](https://img.shields.io/github/stars/browser-use/browser-use) | Make websites accessible for AI agents, automate tasks with ease |\n| [NanoBrowser](https://github.com/nanobrowser/nanobrowser) | ![](https://img.shields.io/github/stars/nanobrowser/nanobrowser) | TypeScript-based AI browsing agent |\n| [Firecrawl](https://github.com/firecrawl/firecrawl) | ![](https://img.shields.io/github/stars/firecrawl/firecrawl) | Turn websites into LLM-ready markdown or structured data |\n| [Crawl4AI](https://github.com/unclecode/crawl4ai) | ![](https://img.shields.io/github/stars/unclecode/crawl4ai) | Open-source LLM-friendly web crawler and scraper |\n| [Stagehand](https://github.com/browserbase/stagehand) | ![](https://img.shields.io/github/stars/browserbase/stagehand) | AI browser automation framework with natural language and code |\n| [Xquik](https://github.com/Xquik-dev/x-twitter-scraper) | ![](https://img.shields.io/github/stars/Xquik-dev/x-twitter-scraper) | X/Twitter data and action API (REST, MCP, webhooks) that agents call for search, monitoring, and posting |\n| [Skyvern](https://github.com/Skyvern-AI/skyvern) | ![](https://img.shields.io/github/stars/Skyvern-AI/skyvern) | Browser automation agent using LLMs and computer vision to complete web workflows |\n| [Playwright MCP](https://github.com/microsoft/playwright-mcp) | ![](https://img.shields.io/github/stars/microsoft/playwright-mcp) | MCP server exposing Playwright browser automation to AI agents |\n| [Agent S](https://github.com/simular-ai/Agent-S) | ![](https://img.shields.io/github/stars/simular-ai/Agent-S) | Open framework for computer-use agents that operate desktop GUIs like a human |\n| [UI-TARS Desktop](https://github.com/bytedance/UI-TARS-desktop) | ![](https://img.shields.io/github/stars/bytedance/UI-TARS-desktop) | GUI agent by ByteDance that controls desktop and browser via natural language, built on the UI-TARS vision model |\n| [agent-qa](https://github.com/vostride/agent-qa) | ![](https://img.shields.io/github/stars/vostride/agent-qa) | Self-improving QA agent for natural-language web and mobile tests |\n\n### ðŸ—Ģïļ Programming Language Agents\n\nAgents and frameworks specialized for specific programming languages.\n\n| Name | Language | Stars | Description |\n| ------------------------------------------------------------------------ | ---------- | ------------------------------------------------------------------------ | ---------------------------------------------- |\n| [TypeChat](https://github.com/microsoft/TypeChat) | TypeScript | ![](https://img.shields.io/github/stars/microsoft/TypeChat) | Type-safe LLM outputs using TypeScript types |\n| [LangChain.js](https://github.com/langchain-ai/langchainjs) | JavaScript | ![](https://img.shields.io/github/stars/langchain-ai/langchainjs) | JS version of LangChain |\n| [Semantic Kernel](https://github.com/microsoft/semantic-kernel) | C#/.NET | ![](https://img.shields.io/github/stars/microsoft/semantic-kernel) | Integrate LLMs into .NET apps |\n| [LangChain4j](https://github.com/langchain4j/langchain4j) | Java | ![](https://img.shields.io/github/stars/langchain4j/langchain4j) | Java implementation of LangChain |\n| [Haystack](https://github.com/deepset-ai/haystack) | Python | ![](https://img.shields.io/github/stars/deepset-ai/haystack) | Search and question answering agents |\n| [LlamaIndex.js](https://github.com/run-llama/LlamaIndexTS) | TypeScript | ![](https://img.shields.io/github/stars/run-llama/LlamaIndexTS) | JS version of LlamaIndex |\n| [LangChain.rb](https://github.com/patterns-ai-core/langchainrb) | Ruby | ![](https://img.shields.io/github/stars/patterns-ai-core/langchainrb) | Ruby implementation of LangChain |\n| [LangChainGo](https://github.com/tmc/langchaingo) | Go | ![](https://img.shields.io/github/stars/tmc/langchaingo) | Go implementation for LLM orchestration |\n| [OpenAI Agents (Python)](https://github.com/openai/openai-agents-python) | Python | ![](https://img.shields.io/github/stars/openai/openai-agents-python) | Lightweight, provider-agnostic agent framework |\n| [Swarms-rs](https://github.com/The-Swarm-Corporation/swarms-rs) | Rust | ![](https://img.shields.io/github/stars/The-Swarm-Corporation/swarms-rs) | Swarm-based agent orchestration in Rust |\n| [AnythingLLM](https://github.com/Mintplex-Labs/anything-llm) | JavaScript | ![](https://img.shields.io/github/stars/Mintplex-Labs/anything-llm) | All-in-one AI agent builder with RAG and UI |\n\n### 🎙ïļ Voice Agents\n\nFrameworks for building real-time voice and conversational AI agents.\n\n| Name | Stars | Description |\n| --------------------------------------------------------------- | -------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| [Pipecat](https://github.com/pipecat-ai/pipecat) | ![](https://img.shields.io/github/stars/pipecat-ai/pipecat) | Open-source framework for building real-time voice and multimodal conversational agents |\n| [LiveKit Agents](https://github.com/livekit/agents) | ![](https://img.shields.io/github/stars/livekit/agents) | Framework for real-time voice AI agents with WebRTC transport, built on LiveKit |\n| [TEN Framework](https://github.com/TEN-framework/ten-framework) | ![](https://img.shields.io/github/stars/TEN-framework/ten-framework) | Open-source framework for real-time conversational voice agents with multimodal support |\n\n---\n\n## ⚙ïļ Agent Operations\n\nTools and systems for managing AI agents.\n\n### 🧠 Memory\n\n| Name | Stars | Description |\n| ---------------------------------------------------------------------- | ----------------------------------------------------------------------- | --------------------------------------------------------------------------------- |\n| [Letta (formerly MemGPT)](https://github.com/letta-ai/letta) | ![](https://img.shields.io/github/stars/letta-ai/letta) | Dynamic, adaptive agent memory system |\n| [Mem0](https://github.com/mem0ai/mem0) | ![](https://img.shields.io/github/stars/mem0ai/mem0) | Universal memory layer for AI agents |\n| [Tree Ring Memory](https://github.com/TerminallyLazy/Tree-Ring-Memory) | ![](https://img.shields.io/github/stars/TerminallyLazy/Tree-Ring-Memory) | Local-first CLI/TUI for agent memory recall, forgetting, audit, and consolidation |\n| [ChromaDB](https://github.com/chroma-core/chroma) | ![](https://img.shields.io/github/stars/chroma-core/chroma) | Vector DB for memory/context |\n| [Weaviate](https://github.com/weaviate/weaviate) | ![](https://img.shields.io/github/stars/weaviate/weaviate) | Scalable vector DB for semantic memory |\n| [Portable Handoff](https://github.com/legoambarish/portable-handoff) | ![](https://img.shields.io/github/stars/legoambarish/portable-handoff) | Local-first CLI for handing off coding-agent session context between tools |\n| [Mnemoverse](https://github.com/mnemoverse/mcp-memory-server) | ![](https://img.shields.io/github/stars/mnemoverse/mcp-memory-server) | MIT MCP memory server; a hosted engine re-ranks recall from reported outcomes |\n| [Fidelis Memory](https://github.com/hermes-labs-ai/fidelis) | ![](https://img.shields.io/github/stars/hermes-labs-ai/fidelis) | Local-first MCP memory: local vector recall, optional keyword+vector hybrid mode |\n| [Screenpipe](https://github.com/screenpipe/screenpipe) | ![](https://img.shields.io/github/stars/screenpipe/screenpipe) | Source-available screen/audio history for agents via MCP and a local API |\n| [Busabase](https://github.com/busabase/busabase) | ![](https://img.shields.io/github/stars/busabase/busabase) | Open-source agent workspace with auditable, permission-aware ChangeRequests |\n\n### 📊 Evaluation\n\n| Name | Stars | Description |\n| --------------------------------------------------------------- | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------- |\n| [AgentBench](https://github.com/THUDM/AgentBench) | ![](https://img.shields.io/github/stars/THUDM/AgentBench) | Multi-environment testing for agents |\n| [LangTrace](https://github.com/Scale3-Labs/langtrace) | ![](https://img.shields.io/github/stars/Scale3-Labs/langtrace) | Monitoring and trace visualization |\n| [agenttrace](https://github.com/luoyuctl/agenttrace) | ![](https://img.shields.io/github/stars/luoyuctl/agenttrace) | Local TUI and reports for AI coding agent session cost, latency, failures, and health |\n| [ax](https://github.com/Necmttn/ax) | ![](https://img.shields.io/github/stars/Necmttn/ax) | Local-first evidence graph for coding-agent sessions, tool calls, skills, and cost |\n| [Agent Evaluation](https://github.com/awslabs/agent-evaluation) | ![](https://img.shields.io/github/stars/awslabs/agent-evaluation) | Benchmarking agent capabilities |\n| [Simple Evals](https://github.com/openai/simple-evals) | ![](https://img.shields.io/github/stars/openai/simple-evals) | OpenAI's lightweight LLM evaluation library |\n\n### 📈 Observability\n\nTracing, monitoring, and debugging tools for agents in production.\n\n| Name | Stars | Description |\n| ---------------------------------------------------------------- | --------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- |\n| [Langfuse](https://github.com/langfuse/langfuse) | ![](https://img.shields.io/github/stars/langfuse/langfuse) | Open-source LLM engineering platform for tracing, prompt management, and evaluations |\n| [Arize Phoenix](https://github.com/Arize-ai/phoenix) | ![](https://img.shields.io/github/stars/Arize-ai/phoenix) | Open-source AI observability with OpenTelemetry tracing, evals, and agent debugging |\n| [Helicone](https://github.com/Helicone/helicone) | ![](https://img.shields.io/github/stars/Helicone/helicone) | Open-source LLM observability with one-line integration for cost and usage tracking |\n| [OpenLLMetry](https://github.com/traceloop/openllmetry) | ![](https://img.shields.io/github/stars/traceloop/openllmetry) | OpenTelemetry-based instrumentation for LLM and agent frameworks |\n| [Laminar](https://github.com/lmnr-ai/lmnr) | ![](https://img.shields.io/github/stars/lmnr-ai/lmnr) | Open-source platform for tracing and evaluating AI agents |\n| [Noveum Trace](https://github.com/Noveum/noveum-trace) | ![](https://img.shields.io/github/stars/Noveum/noveum-trace) | Python SDK for tracing LLM calls and agent workflows in the hosted Noveum platform |\n| [OrcaReplay](https://github.com/Continuum-AI-Corp/OrcaReplay) | ![](https://img.shields.io/github/stars/Continuum-AI-Corp/OrcaReplay) | Records a coding-agent run below the harness and replays it offline byte-for-byte |\n| [OpenClaw Monitor](https://github.com/flik2002/openclaw-monitor) | ![](https://img.shields.io/github/stars/flik2002/openclaw-monitor) | Open-source monitoring dashboard for OpenClaw AI agents — token usage, session tracking, 7-day trends |\n| [Bifrost](https://github.com/maximhq/bifrost) | ![](https://img.shields.io/github/stars/maximhq/bifrost) | OpenAI-compatible LLM gateway with multi-provider routing, failover, and tracing |\n\n### 🚀 Deployment\n\n| Name | Stars | Description |\n| --------------------------------------------------- | ---------------------------------------------------------------- | -------------------------------------------- |\n| [Daytona](https://github.com/daytonaio/daytona) | ![](https://img.shields.io/github/stars/daytonaio/daytona) | Elastic infrastructure for AI-generated code |\n| [E2B](https://github.com/e2b-dev/E2B) | ![](https://img.shields.io/github/stars/e2b-dev/E2B) | Secure sandboxed environments for agents |\n| [OctoAI](https://github.com/octoai/octoAI) | ![](https://img.shields.io/github/stars/octoai/octoAI) | Scalable infrastructure for agent deployment |\n| [Modal](https://github.com/modal-labs/modal-client) | ![](https://img.shields.io/github/stars/modal-labs/modal-client) | Serverless runtime for AI workloads |\n\n### 🔒 Security \u0026 Governance\n\n| Name | Stars | Description |\n| --------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |\n| [Agent Governance Toolkit](https://github.com/microsoft/agent-governance-toolkit) | ![](https://img.shields.io/github/stars/microsoft/agent-governance-toolkit) | Policy enforcement, zero-trust identity, and execution sandboxing for autonomous AI agents |\n| [Garak](https://github.com/NVIDIA/garak) | ![](https://img.shields.io/github/stars/NVIDIA/garak) | LLM vulnerability scanner - probes for prompt injection, data leakage, and hallucination |\n| [Presidio](https://github.com/data-privacy-stack/presidio) | ![](https://img.shields.io/github/stars/data-privacy-stack/presidio) | PII detection, redaction, and anonymization across text, images, and structured data |\n| [Guardrails AI](https://github.com/guardrails-ai/guardrails) | ![](https://img.shields.io/github/stars/guardrails-ai/guardrails) | Output validation and guardrails for LLM responses |\n| [NeMo Guardrails](https://github.com/NVIDIA-NeMo/Guardrails) | ![](https://img.shields.io/github/stars/NVIDIA-NeMo/Guardrails) | Programmable guardrails for LLM-based conversational systems |\n| [LLM Guard](https://github.com/protectai/llm-guard) | ![](https://img.shields.io/github/stars/protectai/llm-guard) | Security toolkit for scanning and sanitizing LLM prompts and outputs |\n| [Polaxis](https://github.com/nishant6118/Polaxis-SDK-MCP) | ![](https://img.shields.io/github/stars/nishant6118/Polaxis-SDK-MCP) | Pre-execution runtime firewall for AI agents - 7-layer threat detection and spend controls |\n| [sofagent](https://github.com/KongFangXun/sofagent) | ![](https://img.shields.io/github/stars/KongFangXun/sofagent) | Commit-time audit harness for coding agents - git-diff rules, HMAC audit trail, rollback |\n| [hermes-jailbench](https://github.com/hermes-labs-ai/hermes-jailbench) | ![](https://img.shields.io/github/stars/hermes-labs-ai/hermes-jailbench) | Deterministic jailbreak regression benchmark for known-pattern attacks |\n\n### 🔌 Protocols\n\nOpen protocols and implementations for agent-to-tool and agent-to-agent interoperability.\n\n| Name | Stars | Description |\n| -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| [Model Context Protocol](https://github.com/modelcontextprotocol/modelcontextprotocol) | ![](https://img.shields.io/github/stars/modelcontextprotocol/modelcontextprotocol) | Anthropic's open protocol standardizing how AI agents connect to tools and data sources |\n| [MCP Servers](https://github.com/modelcontextprotocol/servers) | ![](https://img.shields.io/github/stars/modelcontextprotocol/servers) | Official collection of reference MCP server implementations |\n| [A2A](https://github.com/a2aproject/A2A) | ![](https://img.shields.io/github/stars/a2aproject/A2A) | Open protocol started by Google for agent-to-agent communication across frameworks |\n| [FastMCP](https://github.com/PrefectHQ/fastmcp) | ![](https://img.shields.io/github/stars/PrefectHQ/fastmcp) | Pythonic framework for building MCP servers and clients |\n\n---\n\n## 📚 Research \u0026 Benchmarks\n\nKey research papers, benchmarks, and surveys on AI agents.\n\n### 📄 Papers\n\n| Title | Link | Description |\n| ----------------------------------------------------------------------- | ----------------------------------------- | --------------------------------------------------------------------------------------------------------------- |\n| The Rise of LLM-Based Agents | [arXiv](https://arxiv.org/abs/2309.07864) | Comprehensive survey on LLM-based agents |\n| Tool Learning with Foundation Models | [arXiv](https://arxiv.org/abs/2304.08354) | Tool usage in AI agents |\n| Multi-Agent Collaboration | [arXiv](https://arxiv.org/abs/2308.08262) | Collaboration in multi-agent systems |\n| Large Language Model based Multi-Agents | [arXiv](https://arxiv.org/abs/2312.01845) | Survey of progress and challenges |\n| Agentic AI Systems | [arXiv](https://arxiv.org/abs/2401.08231) | Components and applications of agentic AI |\n| A Survey on LLM-based Autonomous Agents | [arXiv](https://arxiv.org/abs/2308.11432) | Focus on autonomous LLM agents |\n| OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents | [arXiv](https://arxiv.org/abs/2504.16918) | Four-agent pipeline with bandit scheduling turns optimization problems into solver code |\n| Training Agents to Evolve with Their Harness (HAT) | [arXiv](https://arxiv.org/abs/2608.15763) | Harness-aware training for a live-commerce agent, with evaluation on changing skills, tools, prompts, and hooks |\n\n### 📊 Benchmarks\n\n| Name | Stars | Description |\n| --------------------------------------------------------------------- | ------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |\n| [ToolBench](https://github.com/OpenBMB/ToolBench) | ![](https://img.shields.io/github/stars/OpenBMB/ToolBench) | Benchmark for tool learning |\n| [SOTOPIA-π](https://github.com/sotopia-lab/sotopia-pi) | ![](https://img.shields.io/github/stars/sotopia-lab/sotopia-pi) | Social intelligence benchmark for multi-agent systems |\n| [PerspectiveGap](https://github.com/WhymustIhaveaname/PerspectiveGap) | ![](https://img.shields.io/github/stars/WhymustIhaveaname/PerspectiveGap) | Benchmark for writing orchestration prompts in multi-agent systems, 110 scenarios across 10 topologies |\n| [ClawBench](https://github.com/TIGER-AI-Lab/ClawBench) | ![](https://img.shields.io/github/stars/TIGER-AI-Lab/ClawBench) | Live-web browser-agent benchmark with 283 tasks across 163 real websites |\n\n---\n\n## 🌐 Community Resources\n\nJoin the conversation and stay updated on AI agent developments.\n\n### ðŸ‘Ĩ Communities\n\n| Name | Link | Description |\n| ------------------- | ---------------------------------------------------------- | ---------------------------------------------------- |\n| LangChain Community | [Discord](https://discord.gg/langchain) | Active developer community |\n| AutoGen Discussions | [GitHub](https://github.com/microsoft/autogen/discussions) | Microsoft AutoGen community forum |\n| AgentOps Discord | [Join](https://discord.gg/agentops) | Developer space for observability and testing agents |\n| Letta AI Community | [Discord](https://discord.gg/letta) | Discussions on adaptive memory in AI agents |\n\n### 📰 Newsletters\n\n| Name | Link | Description |\n| --------------------------- | --------------------------------------------------- | --------------------------- |\n| The Batch (DeepLearning.AI) | [Subscribe](https://www.deeplearning.ai/the-batch/) | Weekly AI industry insights |\n\n---\n\n## 🚀 Contributors\n\nA huge thank you to all our [amazing contributors](https://github.com/NipunaRanasinghe/awesome-ai-agents/graphs/contributors)!\n\nYour contributions make this project better every day.\n\n⭐ A special shoutout to all our [stargazers](https://github.com/NipunaRanasinghe/awesome-ai-agents/stargazers) for your support!\n**Star this repository** to stay updated and help grow the community of AI enthusiasts!\n\n## Contributing\n\nYour contributions are welcome! Here's how to get started:\n\n- Fork the [repository](https://github.com/NipunaRanasinghe/awesome-ai-agents/fork) and clone it locally.\n- Add your resource to the appropriate section in `README.md`.\n- Ensure the resource is:\n - Relevant to AI agents.\n - Actively maintained (updated within the last 6 months).\n - Includes a brief description and link.\n- Submit a pull request with a clear description of your changes.\n\nFor more details, see the [CONTRIBUTING.md](CONTRIBUTING.md) guide.\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/nipunaranasinghe%2Fawesome-ai-agents/projects"}