{"id":127417,"url":"https://github.com/bradagi/awesome-cli-coding-agents","name":"awesome-cli-coding-agents","description":"Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI), parallel runners, autonomous loops, and agent infrastructure. ","projects_count":167,"last_synced_at":"2026-06-12T01:00:24.215Z","repository":{"id":336988890,"uuid":"1151837992","full_name":"bradAGI/awesome-cli-coding-agents","owner":"bradAGI","description":"Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI), parallel runners, autonomous loops, and agent infrastructure. ","archived":false,"fork":false,"pushed_at":"2026-05-25T11:44:50.000Z","size":1397,"stargazers_count":448,"open_issues_count":19,"forks_count":99,"subscribers_count":5,"default_branch":"main","last_synced_at":"2026-05-25T13:30:50.018Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bradAGI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"dco":null,"cla":null}},"created_at":"2026-02-07T00:53:24.000Z","updated_at":"2026-05-25T11:44:54.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/bradAGI/awesome-cli-coding-agents","commit_stats":null,"previous_names":["bradagi/awesome-cli-coding-agents"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bradAGI/awesome-cli-coding-agents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bradAGI%2Fawesome-cli-coding-agents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bradAGI%2Fawesome-cli-coding-agents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bradAGI%2Fawesome-cli-coding-agents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bradAGI%2Fawesome-cli-coding-agents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bradAGI","download_url":"https://codeload.github.com/bradAGI/awesome-cli-coding-agents/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bradAGI%2Fawesome-cli-coding-agents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34224103,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-11T02:00:06.485Z","response_time":57,"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":"2026-04-07T20:33:02.956Z","updated_at":"2026-06-12T01:00:24.217Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Terminal-native coding agents","Harnesses \u0026 orchestration"],"sub_categories":["Open Source","Closed Source","Agent infrastructure","Session managers \u0026 parallel runners","Orchestrators \u0026 autonomous loops","OpenClaw ecosystem"],"readme":"# Awesome CLI Coding Agents\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"banner.png\" alt=\"Awesome CLI Coding Agents\" width=\"100%\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://awesome.re\"\u003e\u003cimg src=\"https://awesome.re/badge.svg\" alt=\"Awesome\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/bradAGI/awesome-cli-coding-agents/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/bradAGI/awesome-cli-coding-agents?style=social\" alt=\"Stars\"\u003e\u003c/a\u003e\n  \u003ca href=\"#contributing\"\u003e\u003cimg src=\"https://img.shields.io/badge/PRs-welcome-brightgreen.svg\" alt=\"PRs Welcome\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/bradAGI/awesome-cli-coding-agents/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/bradAGI/awesome-cli-coding-agents\" alt=\"License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nA curated list of **80+ CLI coding agents** — AI-powered tools that live in your terminal, read/edit repos, and run commands — plus the **harnesses** that orchestrate, sandbox, or extend them.\n\n\u003e **Last updated:** 2026-06-08\n\n### What is a CLI coding agent?\n\nA CLI coding agent is an AI-powered tool that runs in your terminal and can autonomously read, write, and execute code in your repository. Unlike chat-based assistants, these agents have direct access to your filesystem, shell, and dev tools — they can edit files, run tests, commit changes, and iterate on errors. Think of them as AI pair programmers that live where you already work: the command line.\n\n---\n\n## Contents\n\n- [Terminal-native coding agents](#terminal-native-coding-agents)\n  - [Open Source](#open-source)\n  - [OpenClaw ecosystem](#openclaw-ecosystem)\n  - [Closed Source](#closed-source)\n\n- [Harnesses \u0026 orchestration](#harnesses--orchestration)\n  - [Session managers \u0026 parallel runners](#session-managers--parallel-runners)\n  - [Orchestrators \u0026 autonomous loops](#orchestrators--autonomous-loops)\n  - [Agent infrastructure](#agent-infrastructure)\n\n- [Contributing](#contributing)\n\n---\n\n## Terminal-native coding agents\n\n### Open Source\n\nForkable, extensible, and community-driven. Sorted by GitHub stars. Provider tags `[Company]` indicate the backing organization.\n\n- **[Claw Code](https://github.com/ultraworkers/claw-code)** `⭐ 193k` — Clean-room Python/Rust rewrite of Claude Code architecture using oh-my-codex; fastest repo in GitHub history to 100K stars. Born from the March 2026 Claude Code source leak. MIT.\n\n- **[Hermes Agent](https://github.com/NousResearch/hermes-agent)** `⭐ 187k` — Nous Research's self-improving CLI agent with persistent memory, automated skill creation, sandboxed code execution via Unix socket RPC, and multi-platform reach (Telegram/Slack/Discord/WhatsApp); supports 300+ models across multiple providers.\n\n- **[OpenCode](https://github.com/anomalyco/opencode)** `⭐ 172k` — Terminal-native coding agent with 75+ provider support, LSP integration, and privacy-first design (formerly opencode-ai; now at opencode.ai).\n\n- **[Gemini CLI](https://github.com/google-gemini/gemini-cli)** `⭐ 105k` `[Google]` — Google's terminal agent powered by Gemini, with tools for repo work and research. Apache-2.0.\n\n- **[Codex CLI](https://github.com/openai/codex)** `⭐ 89.6k` `[OpenAI]` — OpenAI's local coding agent for reading/editing/running code, with an interactive TUI and tool execution. Apache-2.0.\n\n- **[OpenHands](https://github.com/All-Hands-AI/OpenHands)** `⭐ 76.2k` — Open-source agentic developer environment (formerly OpenDevin) with CLI and web entrypoints; also has a lightweight [CLI-only package](https://github.com/OpenHands/OpenHands-CLI).\n\n- **[Open Interpreter](https://github.com/OpenInterpreter/open-interpreter)** `⭐ 63.9k` — Terminal tool that can execute code and actions; often used as a \"do things on my machine\" agent.\n\n- **[Cline CLI](https://github.com/cline/cline)** `⭐ 62.9k` — Model-agnostic autonomous agent for planning, file edits, command execution, and browser use.\n\n- **[Pi](https://github.com/badlogic/pi-mono)** `⭐ 60.8k` — Minimal, adaptable terminal coding harness from the pi-mono toolkit; unified LLM API, TUI, skills, and MCP support.\n\n- **[Goose](https://github.com/block/goose)** `⭐ 47.8k` — Local, extensible agent that can execute, edit, and test; designed to run on-device and integrate with MCP.\n\n- **[Aider](https://github.com/Aider-AI/aider)** `⭐ 45.9k` — Pair-programming agent for editing files via diffs/patches, with strong git and multi-file workflows.\n\n- **[Continue CLI](https://github.com/continuedev/continue)** `⭐ 33.6k` — Open-source terminal extension for multi-model coding with local/privacy focus.\n\n- **[Crush](https://github.com/charmbracelet/crush)** `⭐ 25.1k` — Charmbracelet's glamorous agentic coding TUI in Go; multi-provider, LSP-aware, with rich terminal UI.\n\n- **[Qwen Code](https://github.com/QwenLM/qwen-code)** `⭐ 25k` `[Alibaba]` — Alibaba Qwen's official CLI agent for Qwen coder models (workflow tool + repo operations). Apache-2.0.\n\n- **[Roo Code CLI](https://github.com/RooCodeInc/Roo-Code)** `⭐ 24.2k` — Multi-mode CLI agent (architect/code/debug/orchestrator modes); Claude-like terminal interface with skills and checkpoints.\n\n- **[Kilo Code CLI](https://github.com/Kilo-Org/kilocode)** `⭐ 19.9k` — Agentic engineering platform with CLI; orchestrator mode, 100s of LLMs, skills, and checkpointing.\n\n- **[SWE-agent](https://github.com/SWE-agent/SWE-agent)** `⭐ 19.5k` — Agent for resolving real repo issues/PR tasks; frequently used in SWE-bench-style workflows.\n\n- **[Plandex](https://github.com/plandex-ai/plandex)** `⭐ 15.4k` — \"Plan-first\" CLI agent for building features across multiple files with structured steps and 2M token context.\n\n- **[Smol Developer](https://github.com/smol-ai/developer)** `⭐ 12.2k` — Embeddable developer agent that generates entire codebases from a prompt; designed to be embedded in apps.\n\n- **[Trae Agent](https://github.com/bytedance/trae-agent)** `⭐ 11.6k` `[ByteDance]` — ByteDance's research-friendly CLI agent for software engineering tasks, with modular architecture and multi-LLM support. MIT.\n\n- **[Claude Engineer](https://github.com/Doriandarko/claude-engineer)** `⭐ 11.2k` — Community-driven CLI for agentic Claude workflows with file management and iterative development.\n\n- **[OH-MY-PI](https://github.com/can1357/oh-my-pi)** `⭐ 11.2k` — Terminal coding agent (\"Pi\") with a TypeScript/Rust monorepo and local-first ergonomics.\n\n- **[Claurst](https://github.com/Kuberwastaken/claurst)** `⭐ 9.8k` — Claude Code rewritten in idiomatic Rust with architectural breakdown; includes discoveries from the source leak (KAIROS persistent assistant, buddy system). MIT.\n\n- **[Kimi CLI](https://github.com/MoonshotAI/kimi-cli)** `⭐ 8.9k` `[Moonshot AI]` — Moonshot AI's CLI coding agent with skills, MCP support, and ACP IDE integration. Apache-2.0.\n\n- **[Free Code](https://github.com/paoloanzn/free-code)** `⭐ 8.4k` — Fork of Claude Code with all telemetry removed, guardrails stripped, and all experimental features enabled (KAIROS, dream mode, companion system).\n\n- **[ForgeCode](https://github.com/antinomyhq/forge)** `⭐ 7.4k` — AI pair programmer supporting 300+ models, with task management, custom agents, and large-scale refactor tooling.\n\n- **[Codebuff](https://github.com/CodebuffAI/codebuff)** `⭐ 6.3k` — Multi-agent AI coding assistant with CLI support for collaborative coding workflows.\n\n- **[Kode CLI](https://github.com/shareAI-lab/Kode-cli)** `⭐ 5.1k` — ShareAI's open-source CLI agent for terminal-native coding with multi-provider support.\n\n- **[Mistral Vibe](https://github.com/mistralai/mistral-vibe)** `⭐ 4.4k` `[Mistral]` — Mistral's CLI coding assistant for conversational repo interaction and edits. Apache-2.0.\n\n- **[gptme](https://github.com/gptme/gptme)** `⭐ 4.3k` — AI agent in your terminal with support for persistent autonomous agents. Runs code, edits files, browses the web. Build long-lived self-modifying agents with git-backed memory via [gptme-agent-template](https://github.com/gptme/gptme-agent-template).\n\n- **[Every Code](https://github.com/just-every/code)** `⭐ 3.8k` — Fork of Codex CLI with validation, automation, browser integration, multi-agents, theming, and multi-provider orchestration (OpenAI, Claude, Gemini). Apache-2.0.\n\n- **[Devon](https://github.com/entropy-research/Devon)** `⭐ 3.4k` — Open-source pair programmer with a TUI; autonomous planning, execution, and debugging in Git workflows.\n\n- **[Grok CLI](https://github.com/superagent-ai/grok-cli)** `⭐ 3.1k` — Community CLI agent built on xAI's Grok models for terminal-based coding tasks.\n\n- **[AutoCodeRover](https://github.com/AutoCodeRoverSG/auto-code-rover)** `⭐ 3.1k` — Autonomous program improvement agent; patches real GitHub issues using code search and analysis.\n\n- **[Letta Code](https://github.com/letta-ai/letta-code)** `⭐ 2.7k` — Memory-first CLI coding agent built on the Letta platform (formerly MemGPT); persistent memory across sessions, model-agnostic (Claude/GPT/Gemini), skill learning, and context repositories.\n\n- **[CodeMachine-CLI](https://github.com/moazbuilds/CodeMachine-CLI)** `⭐ 2.5k` — Community multi-agent CLI aimed at running coding workflows locally (vibe-coding oriented).\n\n- **[Codel](https://github.com/semanser/codel)** `⭐ 2.5k` — Autonomous agent for performing complex tasks via terminal; runs in Docker with a web UI.\n\n- **[RA.Aid](https://github.com/ai-christianson/RA.Aid)** `⭐ 2.2k` — Autonomous coding agent built on LangGraph with research/plan/implement pipeline; optional aider integration for near-full autonomy.\n\n- **[open-codex](https://github.com/ymichael/open-codex)** `⭐ 2.2k` — Lightweight fork of Codex CLI with multi-provider support (OpenAI, Gemini, OpenRouter, Ollama).\n\n- **[Agentless](https://github.com/OpenAutoCoder/Agentless)** `⭐ 2.1k` — Lightweight approach to autonomous software engineering without persistent agent loops.\n\n- **[Amazon Q Developer CLI](https://github.com/aws/amazon-q-developer-cli)** `⭐ 2k` `[AWS]` — AWS's agentic terminal chat for building apps, debugging, and DevOps with natural language. Apache-2.0.\n\n- **[Neovate Code](https://github.com/neovateai/neovate-code)** `⭐ 1.5k` `[Ant Group]` — Ant Group's CLI agent with plugin system, multi-model/multi-provider support, MCP integrations, and headless automation mode. MIT.\n\n- **[Groq Code CLI](https://github.com/build-with-groq/groq-code-cli)** `⭐ 729` — Customizable, lightweight CLI powered by Groq's ultra-fast inference; extensible tools/commands with multi-model support.\n\n- **[Dexto](https://github.com/truffle-ai/dexto)** `⭐ 631` — Coding agent and general agent harness with CLI/web/API modes; ships a production-ready coding agent with sub-agent spawning.\n\n- **[g3](https://github.com/dhanji/g3)** `⭐ 510` — \"Coding AI agent\" in Rust: tool-running, repo interaction, skills system, and provider abstraction.\n\n- **[claw-code-agent](https://github.com/HarnessLab/claw-code-agent)** `⭐ 502` — Python-only Claude Code rewrite with zero external dependencies; born from the March 2026 Claude Code source leak, positioned as easier to hack on than the Rust/TypeScript reimplementations.\n\n- **[Coro Code](https://github.com/Blushyes/coro-code)** `⭐ 360` — Open-source CLI coding agent, a free alternative to Claude Code; generate, debug, and manage code seamlessly.\n\n- **[LettaBot](https://github.com/letta-ai/lettabot)** `⭐ 327` — Personal AI assistant with persistent unified memory across Telegram, Slack, Discord, WhatsApp, and Signal; built on the Letta platform.\n\n- **[Mini-Kode](https://github.com/minmaxflow/mini-kode)** `⭐ 303` — An educational AI coding agent CLI, intended as a readable reference implementation.\n\n- **[nori-cli](https://github.com/tilework-tech/nori-cli)** `⭐ 133` — Multi-provider CLI built on Codex CLI; switch between Claude, Gemini, and Codex from the same native terminal.\n\n- **[cursor-agent](https://github.com/civai-technologies/cursor-agent)** `⭐ 123` — Python-based agent replicating Cursor's coding assistant capabilities; supports Claude, OpenAI, and local Ollama models.\n\n- **[openHarness](https://github.com/zhijiewong/openharness)** `⭐ 95` — Open-source Claude Code alternative. 78 slash commands, 42 tools, MCP (stdio/HTTP/SSE + OAuth 2.1), hooks, subagents, plan mode. Works with Anthropic/OpenAI/Ollama/llama.cpp/LM Studio. Ships both npm and Python SDK. MIT.\n\n- **[VibePod](https://github.com/VibePod/vibepod-cli)** `⭐ 76` — Unified CLI for running AI coding agents in isolated Docker containers; zero-config setup, local metrics, HTTP traffic tracking, and an analytics dashboard for side-by-side comparison.\n\n- **[Octomind](https://github.com/Muvon/octomind)** `⭐ 71` — Open-source, model-agnostic AI agent runtime with community tap registry (`developer:rust`, `doctor:blood`, `legal:contracts`), MCP support with runtime self-extension, 13+ providers, and adaptive compression. Written in Rust. Apache-2.0.\n\n- **[Crab Code](https://github.com/lingcoder/crab-code)** `⭐ 69` — Rust-native agentic coding CLI aligned with Claude Code's toolset and permission model; works with any LLM provider (Anthropic/OpenAI/DeepSeek/Bedrock/Vertex). 27 crates, 4,700+ tests, layered config system. Apache-2.0.\n\n- **[picocode](https://github.com/jondot/picocode)** `⭐ 52` — Minimal Rust-based coding agent focused on CI workflows and small codemods; multi-LLM with personas.\n\n- **[QQCode](https://github.com/qnguyen3/qqcode)** `⭐ 51` — Lightweight CLI coding agent in Rust focused on speed, determinism, and developer control; supports skills.\n\n- **[Smelt](https://github.com/leonardcser/smelt)** `⭐ 23` — Rust TUI coding agent; multi-provider (Anthropic, OpenAI, Ollama, GitHub Copilot, any OpenAI-compatible endpoint), four modes (Normal/Plan/Apply/Yolo), granular permission system, parallel subagents, vim keybindings, and headless scriptable mode. MIT.\n\n- **[Binharic](https://github.com/CogitatorTech/binharic-cli)** `⭐ 16` — A multi-provider \"tech-priest persona\" coding agent CLI (stylized, tool-using).\n\n- **[Darce](https://github.com/AmerSarhan/darce-cli)** `⭐ 4` — Ultralight (14 kB) multi-model CLI agent built with Ink; 7 tools, smart model routing across providers, streaming, session resume, and slash commands. MIT.\n\n- **[CLAII](https://github.com/agencyswarm/CLAII)** `⭐ 2` — CLI-first AI coding agent with multi-agent orchestration, MCP toolchains, and memory-persistent refactors.\n\n### OpenClaw ecosystem\n\nProjects built on, forked from, or inspired by [OpenClaw](https://github.com/openclaw/openclaw) — the open-source personal AI assistant. Sorted by GitHub stars.\n\n- **[OpenClaw](https://github.com/openclaw/openclaw)** `⭐ 378k` — The original personal AI assistant you run locally; CLI with onboarding wizard, skills, tools, and multi-channel support (WhatsApp/Slack/Discord). MIT.\n\n- **[nanobot](https://github.com/HKUDS/nanobot)** `⭐ 43.9k` — Ultra-lightweight ~4,000-line Python rewrite of OpenClaw; tool use, persistent memory, scheduled tasks, and multi-channel support (Telegram/Discord/WhatsApp). MIT.\n\n- **[ZeroClaw](https://github.com/zeroclaw-labs/zeroclaw)** `⭐ 31.8k` — Fully autonomous AI agent runtime in Rust; trait-driven pluggable architecture (providers, tools, memory, channels), runs on minimal hardware (\u003c5MB RAM), multi-channel CLI/Telegram/Discord/Slack, with sandboxed execution and hybrid vector+keyword search.\n\n- **[NanoClaw](https://github.com/gavrielc/nanoclaw)** `⭐ 29.7k` — Security-first lightweight alternative to OpenClaw; runs agents in Apple containers/Docker with sandboxed execution, built on Anthropic's Agents SDK.\n\n- **[PicoClaw](https://github.com/sipeed/picoclaw)** `⭐ 29.3k` — Ultra-lightweight personal AI assistant in Go inspired by OpenClaw; runs on $10 hardware with less than 10MB RAM.\n\n- **[IronClaw](https://github.com/nearai/ironclaw)** `⭐ 12.4k` — OpenClaw rewritten in Rust by NEAR AI; WASM sandbox isolation, capability-based permissions, and prompt injection defense.\n\n- **[NullClaw](https://github.com/nullclaw/nullclaw)** `⭐ 7.7k` — Fastest, smallest OpenClaw-compatible agent in Zig; 678KB static binary, ~1MB RAM, \u003c2ms startup, 23+ providers, 18 channels. MIT.\n\n- **[Clawith](https://github.com/dataelement/Clawith)** `⭐ 4k` — \"OpenClaw for Teams\" — multi-agent collaboration platform that scales OpenClaw to organizations. Apache-2.0.\n\n- **[claw0](https://github.com/shareAI-lab/claw0)** `⭐ 2.9k` — 0-to-1 tutorial companion for the OpenClaw ecosystem; walks through building an agent harness from scratch, covering planning, context compression, and task persistence.\n\n- **[Moltis](https://github.com/moltis-org/moltis)** `⭐ 2.7k` — Secure, auditable Rust-native alternative to OpenClaw; zero unsafe code, 2,300+ tests, built-in voice I/O, MCP servers, and multi-channel access. MIT.\n\n- **[GitClaw](https://github.com/open-gitagent/gitclaw)** `⭐ 524` — Git-native AI agent framework where agent identity, rules, memory, tools, and skills are all version-controlled files. MIT.\n\n- **[LionClaw](https://github.com/moshthepitt/lionclaw)** `⭐ 8` — Secure-first local AI CLI with a small auditable kernel, durable sessions, and installable skills. MIT.\n\n### Closed Source\n\nProprietary agents — usable but not forkable or extensible at the source level.\n\n- **[Claude Code](https://github.com/anthropics/claude-code)** `⭐ 131k` `[Anthropic]` — Anthropic's repo-aware terminal agent for code edits, refactors, and git workflows. Source-available, no OSS license.\n\n- **[Warp](https://github.com/warpdotdev/Warp)** `⭐ 61.3k` `[Warp]` — Modern terminal with built-in AI agent mode; understands tasks, runs commands, edits files, and orchestrates multi-step workflows.\n\n- **[GitHub Copilot in the CLI](https://github.com/github/copilot-cli)** `⭐ 10.7k` `[GitHub]` — GitHub's agentic CLI for repo/PR/issue workflows, command suggestions, and headless automation.\n\n- **[Command Code](https://github.com/CommandCodeAI/command-code)** `⭐ 3.3k` `[CommandCode]` — CLI coding agent that continuously learns your coding style via taste-1 neuro-symbolic AI; adapts to preferences over time with project-specific taste profiles.\n\n- **[Droid](https://github.com/Factory-AI/factory)** `⭐ 931` `[Factory]` — Factory's multi-model CLI coding agent; #1 on Terminal-Bench, specialized droids for different tasks, headless CI mode, and multi-interface support (CLI/IDE/Slack/Linear).\n\n- **[FetchCoder](https://github.com/fetchai/fetchcoder-releases)** `⭐ 2` `[Fetch.ai]` — Terminal coding agent powered by ASI1, with interactive TUI, CLI, and API server modes plus MCP integration.\n\n- **[Amp](https://sourcegraph.com/amp)** `[Sourcegraph]` — Sourcegraph's AI coding agent with a CLI for implementing tasks across real codebases.\n\n- **[Junie CLI](https://junie.jetbrains.com)** `[JetBrains]` — JetBrains' LLM-agnostic CLI coding agent (EAP); supports GPT-5, Claude, Gemini, Grok with plan mode and CI/CD headless usage.\n\n- **[Cortex Code CLI](https://www.snowflake.com/en/product/cortex-code/)** `[Snowflake]` — Snowflake's data-native AI coding agent CLI for building pipelines, analytics, and AI apps with enterprise governance.\n\n- **[Devin](https://devin.ai)** `[Cognition]` — Cognition's autonomous AI software engineer with full shell/browser access, self-healing code, and PR collaboration.\n\n- **[Cursor CLI](https://cursor.com/cli)** `[Cursor]` — Cursor's official command-line agent (`agent`) with shell mode, headless/CI support, parallel agents, and multi-model access.\n\n- **[Tabnine CLI](https://docs.tabnine.com/main/getting-started/tabnine-cli)** `[Tabnine]` — AI-powered terminal coding assistant with agentic workflows; distributed as a Docker container, requires enterprise license.\n\n- **[Mentat CLI](https://mentat.ai/docs/cli)** `[Mentat]` — Cloud-native coding agent CLI for managing remote Mentat agents from your terminal; auto-detects repo/branch context.\n\n---\n\n## Harnesses \u0026 orchestration\n\n### Session managers \u0026 parallel runners\n\nTools for running and managing multiple agent sessions side-by-side. Sorted by GitHub stars.\n\n- **[vibe-kanban](https://github.com/BloopAI/vibe-kanban)** `⭐ 26.9k` — Kanban interface for administering AI coding agents.\n\n- **[cmux](https://github.com/manaflow-ai/cmux)** `⭐ 21.5k` — Open-source platform for running multiple coding agents in parallel.\n\n- **[Superset](https://github.com/superset-sh/superset)** `⭐ 11.6k` — A terminal built for coding agents; orchestrates parallel agent sessions.\n\n- **[Claude Squad](https://github.com/smtg-ai/claude-squad)** `⭐ 7.7k` — tmux-based harness to run and manage multiple Claude Code sessions side-by-side.\n\n- **[Emdash](https://github.com/generalaction/emdash)** `⭐ 4.8k` — Run multiple coding agents concurrently with coordinated workflows.\n\n- **[CodexMonitor](https://github.com/Dimillian/CodexMonitor)** `⭐ 4k` — Coordinate multiple Codex agents across local workspaces.\n\n- **[Toad](https://github.com/batrachianai/toad)** `⭐ 3.2k` — Agent orchestrator for running and managing parallel CLI coding sessions.\n\n- **[Crystal](https://github.com/stravu/crystal)** `⭐ 3.1k` — Execute multiple Codex and Claude Code sessions in parallel git worktrees.\n\n- **[agent-deck](https://github.com/asheshgoplani/agent-deck)** `⭐ 2.7k` — Terminal session manager for AI coding agents — one TUI for Claude, Gemini, OpenCode, Codex, and more. Worktree-aware, MCP integration, 8+ contributors. MIT.\n\n- **[agent-of-empires](https://github.com/njbrake/agent-of-empires)** `⭐ 2.5k` — Manage multiple Claude Code, OpenCode, Codex CLI, Gemini CLI, Pi, Copilot CLI, Mistral Vibe, and Factory Droid agents from a TUI or web UI (mobile-friendly). Rust, uses tmux + git worktrees. MIT.\n\n- **[mux](https://github.com/coder/mux)** `⭐ 1.8k` — Desktop application for isolated, parallel agentic development.\n\n- **[supacode](https://github.com/supabitapp/supacode)** `⭐ 1.1k` — Native macOS coding agent orchestrator.\n\n- **[jean](https://github.com/coollabsio/jean)** `⭐ 1k` — Administer multiple projects, worktrees, and sessions with Claude CLI.\n\n- **[Parallel Code](https://github.com/johannesjo/parallel-code)** `⭐ 708` — Desktop app for running multiple AI coding agents (Claude Code, Codex CLI, Gemini CLI) simultaneously in isolated git worktrees.\n\n- **[CLI Agent Orchestrator (CAO)](https://github.com/awslabs/cli-agent-orchestrator)** `⭐ 688` — AWS's hierarchical multi-agent orchestration via tmux with intelligent task delegation patterns.\n\n- **[Catnip](https://github.com/wandb/catnip)** `⭐ 485` — Containerized environment + worktree automation for running multiple coding agents in parallel (optimized for Claude Code).\n\n- **[ntm](https://github.com/Dicklesworthstone/ntm)** `⭐ 342` — Named Tmux Manager — spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette.\n\n- **[vibe-tree](https://github.com/sahithvibudhi/vibe-tree)** `⭐ 258` — Execute Claude Code tasks in parallel git worktrees.\n\n- **[amux](https://github.com/mixpeek/amux)** `⭐ 226` — Agent multiplexer for running dozens of parallel Claude Code sessions with web dashboard, self-healing watchdog, kanban board, agent-to-agent REST API, and mobile PWA. Single Python file, Python 3 + tmux. MIT.\n\n- **[AgentPipe](https://github.com/kevinelliott/agentpipe)** `⭐ 133` — CLI/TUI app that orchestrates multi-agent conversations by enabling different AI CLI tools (Claude Code, Gemini, Qwen, etc.) to communicate in shared rooms. MIT.\n\n- **[amux](https://github.com/andyrewlee/amux)** `⭐ 122` — Terminal UI designed for running multiple coding agents in parallel.\n\n- **[CliDeck](https://github.com/rustykuntz/clideck)** `⭐ 105` — WhatsApp-like browser dashboard for managing multiple CLI coding agents (Claude Code, Codex, Gemini CLI, OpenCode) with live status detection, session resume, autopilot routing, and full control from a phone while away. MIT.\n\n- **[multi-agent-workflow-kit](https://github.com/laris-co/multi-agent-workflow-kit)** `⭐ 11` — Orchestrate parallel AI agents in isolated git worktrees with shared tmux visibility.\n\n- **[CLITrigger](https://github.com/HyperAITeam/CLITrigger)** `⭐ 8` — Self-hosted web UI for orchestrating Claude Code, Codex, and Gemini CLIs in parallel git worktrees. Features multi-agent discussion mode (architect/developer/reviewer debate before implementation), cross-project Morning Review Queue, scheduled execution with rate-limit auto-recovery, and a built-in Git client. MIT.\n\n- **[PATAPIM](https://patapim.ai)** — Terminal IDE with a 9-terminal grid for running multiple CLI coding agents simultaneously; features AI state detection, built-in Whisper voice dictation, LAN remote access, and an embedded MCP browser. Built with Electron and node-pty. Freemium.\n\n### Orchestrators \u0026 autonomous loops\n\nMulti-agent coordination, swarm patterns, and autonomous execution loops. Sorted by GitHub stars.\n\n- **[claude-flow](https://github.com/ruvnet/claude-flow)** `⭐ 58.5k` — Deploy multi-agent swarms with coordinated workflows.\n\n- **[gastown](https://github.com/steveyegge/gastown)** `⭐ 15.8k` — Multi-agent orchestration with persistent work tracking.\n\n- **[ralph-orchestrator](https://github.com/mikeyobrien/ralph-orchestrator)** `⭐ 2.9k` — Hat-based system maintaining agents in a loop until task completion.\n\n- **[ralph-tui](https://github.com/subsy/ralph-tui)** `⭐ 2.4k` — Direct AI agents through task lists with autonomous execution.\n\n- **[AgentsMesh](https://github.com/AgentsMesh/AgentsMesh)** `⭐ 2.2k` — AI Agent Workforce Platform: remote AI workstations (AgentPods) with PTY sandbox + git worktree isolation, multi-agent collaboration via channels and pod bindings, built-in Kanban with MR/PR integration. Self-hosted with BYOK. Supports Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode. BSL-1.1.\n\n- **[loom](https://github.com/ghuntley/loom)** `⭐ 1.3k` — Infrastructure enabling autonomous loops to evolve products via multi-agent coordination.\n\n- **[Bernstein](https://github.com/chernistry/bernstein)** `⭐ 559` — Deterministic Python orchestrator — spawns parallel AI coding agents (Claude Code, Codex CLI, Gemini CLI), verifies with tests, auto-commits.\n\n- **[Aeon](https://github.com/aaronjmars/aeon)** `⭐ 492` — Autonomous agent framework that runs unattended on GitHub Actions; orchestrates Claude Code across 90+ skills (research, dev, crypto, productivity) on cron or reactive triggers, with quality scoring (1–5 via Haiku), persistent memory, and a self-healing loop. MCP + A2A integrations. MIT.\n\n- **[wreckit](https://github.com/mikehostetler/wreckit)** `⭐ 128` — Apply the Ralph Wiggum Loop pattern across your roadmap for autonomous agent execution.\n\n- **[kodo](https://github.com/ikamensh/kodo)** `⭐ 106` — Autonomous multi-agent coding orchestrator that directs Claude Code, Codex, and Gemini CLI through work cycles with independent architect and tester verification. SWE-bench verified.\n\n- **[ORCH](https://github.com/oxgeneral/ORCH)** `⭐ 74` — CLI orchestrator that manages Claude Code, Codex, and Cursor as a typed task queue with state machine (todo→in_progress→review→done), auto-retry, inter-agent messaging, and TUI dashboard.\n\n- **[OpenCastle](https://github.com/monkilabs/opencastle)** `⭐ 48` — Multi-agent orchestration framework that turns AI coding assistants (Copilot, Cursor, Claude Code, OpenCode, Windsurf, Codex CLI) into 19 coordinated specialist agents. CLI-driven (`npx opencastle init`), with task decomposition, parallel work, and quality gates. MIT.\n\n- **[great_cto](https://github.com/avelikiy/great_cto)** `⭐ 39` — Engineering-management layer of 34 specialist AI agents covering the full SDLC (architect, PM, senior-dev, reviewer, QA, security, devops, L3-support + 18 archetype-specific reviewers) with auto-detected archetypes and compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Runs in Claude Code, Cursor, Codex CLI, Aider, and Continue via AGENTS.md + MCP. MIT.\n\n- **[The Factory](https://github.com/akashgit/remote-factory)** `⭐ 36` — Self-evolving meta-harness for autonomous software dev and research; turns any codebase into an auto-research project, auto-discovers eval dimensions, generates scoring harness, and runs keep/revert experiment loops with monotonic-improvement guards. Multi-contributor. MIT.\n\n- **[Forge](https://github.com/LucasDuys/forge)** `⭐ 29` — Autonomous spec-driven development loop for Claude Code; three-command pipeline (brainstorm specs, plan task DAGs, execute autonomously) with context survival, backpropagation that traces bugs to spec gaps, and Claude-on-Claude code review. MIT.\n\n- **[agx](https://github.com/ramarlina/agx)** `⭐ 22` — Checkpoint-based execution engine for AI coding agents; durable Wake→Work→Sleep loops that resume instantly across sessions. Supports Claude Code, Codex CLI, Gemini CLI, and Ollama. CLI + web dashboard + macOS app.\n\n- **[Galley](https://github.com/shinpr/galley)** `⭐ 10` — Local-first runtime for supervised AI coding tasks: isolated git worktrees, supervisor review against acceptance criteria, retry/escalate loops, on-disk run evidence, and PR handoff. Supports Codex CLI and Claude Code. Go, MIT.\n\n- **[Relay](https://github.com/jcast90/relay)** `⭐ 4` — Local-first orchestrator that runs inside your existing Claude or Codex CLI via MCP; classifies a request, decomposes it into tickets with a dependency DAG, dispatches across one or more repos, and supervises with live PR tracking + approval gates. CLI, TUI (ratatui), and GUI (Tauri) dashboards share `~/.relay/` state. MIT.\n\n- **[sage](https://github.com/youwangd/SageCLI)** `⭐ 3` — Pure bash agent orchestrator (zero frameworks) with runtime-agnostic support (Claude Code, Cline, Codex, Gemini CLI, ACP), wave-based plan execution, git worktree isolation, MCP integration, skills system, headless CI mode, and 295 bats tests. MIT.\n\n### Agent infrastructure\n\nSandboxes, routers, browser/terminal automation, and extension tools. Sorted by GitHub stars.\n\n- **[agent-browser](https://github.com/vercel-labs/agent-browser)** `⭐ 35.6k` — Headless browser automation CLI for agents (useful as a tool plugin for coding agents).\n\n- **[claude-code-router](https://github.com/musistudio/claude-code-router)** `⭐ 34.8k` — Use Claude Code as a foundation while routing to alternative providers/endpoints.\n\n- **[NemoClaw](https://github.com/NVIDIA/NemoClaw)** `⭐ 21.1k` `[NVIDIA]` — CLI tool for securely provisioning and managing sandboxed OpenClaw agent environments; enforces network, filesystem, and process-level security policies via OpenShell runtime. Apache-2.0.\n\n- **[OpenWork](https://github.com/different-ai/openwork)** `⭐ 15.9k` — Open-source alternative to Claude Cowork for teams; local-first desktop app powered by OpenCode with one-click setup. MIT.\n\n- **[open-claude-cowork](https://github.com/ComposioHQ/open-claude-cowork)** `⭐ 4.2k` — Open-source version of Claude Cowork with 500+ SaaS app integrations.\n\n- **[toprank](https://github.com/nowork-studio/toprank)** `⭐ 2.8k` — Claude Code plugin with 9 SEO and Google Ads skills. Connects Google Search Console, PageSpeed Insights, and the Google Ads API, then ships fixes (meta tags, JSON-LD schema, keyword bids) directly to source code or CMS. Open-source, MIT.\n\n- **[OneCLI](https://github.com/onecli/onecli)** `⭐ 2.3k` — Open-source credential vault for AI agents; Rust HTTP gateway injects API keys transparently so agents never handle raw secrets. Per-agent scoped tokens, AES-256-GCM encryption at rest. Apache-2.0.\n\n- **[Claude Code Tools](https://github.com/pchalasani/claude-code-tools)** `⭐ 1.8k` — Utilities around Claude Code workflows (automation helpers, helpers for common tasks).\n\n- **[Coasts](https://github.com/coast-guard/coasts)** `⭐ 398` — Containerized host orchestration for git worktrees; isolates ports, networks, and services per environment using DinD/Sysbox/Podman. MIT.\n\n- **[subtask](https://github.com/zippoxer/subtask)** `⭐ 333` — Claude Skill for delegating tasks with subagents in Git worktrees.\n\n- **[claude-cmd](https://github.com/kiliczsh/claude-cmd)** `⭐ 304` — Terminal wrapper for interacting with Claude models; often used as a building block in harness scripts.\n\n- **[kasetto](https://github.com/pivoshenko/kasetto)** `⭐ 105` — A declarative AI agent environment manager, written in Rust.\n\n- **[skill-optimizer](https://github.com/fastxyz/skill-optimizer)** `⭐ 64` — CLI tool that benchmarks SDK, CLI, and MCP guidance docs (SKILL.md) across multiple LLMs using static action + argument matching. Iteratively rewrites docs until every configured model meets a PASS/FAIL score floor. MIT.\n\n- **[AgentPlane](https://github.com/basilisk-labs/agentplane)** `⭐ 58` — Local CLI that wraps Claude Code, Codex, Cursor, and Aider work in an auditable Git-native workflow (task → plan → approve → implement → verify → finish). All state stays in `.agentplane/` inside the repo; no hosted runtime. MIT.\n\n- **[agent-lsp](https://github.com/blackwell-systems/agent-lsp)** `⭐ 53` — MCP server giving any CLI coding agent type-aware language intelligence: 50+ LSP tools, speculative execution (preview edits without touching disk), 21 skills, 30 CI-verified languages. Measured 5–34× token savings vs grep/read. Works with Claude Code, Codex, Gemini CLI, Goose, and any MCP client. Go, MIT.\n\n- **[Untether](https://github.com/littlebearapps/untether)** `⭐ 50` — Telegram bridge for 6 CLI coding agents (Claude Code, Codex, OpenCode, Pi, Gemini CLI, Amp); remote task control via voice or text, progress streaming, interactive permissions, and cost tracking. MIT.\n\n- **[claudebox](https://github.com/numtide/claudebox)** `⭐ 48` — Sandboxed environment for Claude Code (focused on isolation/safety).\n\n- **[Nex](https://github.com/nex-crm/nex-as-a-skill)** `⭐ 45` — Organizational context and memory for AI agents; connects email, Slack, CRM, and 100+ tools into one knowledge graph with a 60-tool MCP server (`npx @nex-ai/nex`) and persistent memory across agent sessions. MIT.\n\n- **[Wit](https://github.com/amaar-mc/wit)** `⭐ 43` — Coordination protocol that prevents merge conflicts between parallel AI agents. Locks specific functions (not files) via Tree-sitter AST parsing; agents declare intents, acquire symbol-level locks, and get conflict warnings before writing code. JSON-RPC daemon. MIT.\n\n- **[Agent FM](https://github.com/agentfm-ai/agent-fm)** `⭐ 42` — Local macOS menubar app that narrates Claude Code and Codex sessions with a Global Mix, blocker alerts, and BYOK voice; built with Electron. Apache-2.0.\n\n- **[brood-box](https://github.com/stacklok/brood-box)** `⭐ 40` — Hardware-isolated microVM sandbox for AI coding agents (Claude Code, Codex, OpenCode) with COW snapshot isolation, egress control, and MCP authorization.\n\n- **[AgentLint](https://github.com/0xmariowu/AgentLint)** `⭐ 35` — 33 evidence-backed checks for AI-friendly repos. Scans file structure, instruction quality, build setup, session continuity, and security posture. Claude Code plugin with auto-fix. Your AI agent is only as good as your repo.\n\n- **[AgentManager](https://github.com/kevinelliott/agentmanager)** `⭐ 26` — Lightweight CLI for managing multiple agent runs/sessions and workflows.\n\n- **[EchoCoding](https://github.com/launsion-boop/EchoCoding)** `⭐ 25` — Audio layer for CLI coding agents with hook-triggered SFX, ambient soundscape, and optional cloud TTS/ASR voice interaction for Codex and Claude Code workflows.\n\n- **[AgentTier](https://github.com/agenttier/agenttier)** `⭐ 19` — Kubernetes-native sandbox runtime for AI coding agents. A `Sandbox` CRD provisions a Pod + PVC + NetworkPolicy with optional gVisor isolation; the `agenttier` Go CLI runs agent invocations that stream stdout/stderr/exit as SSE. Ships reference templates for Claude Code + Bedrock and LangGraph. Apache-2.0.\n\n- **[agent-terminal](https://github.com/jasonkneen/agent-terminal)** `⭐ 10` — Headless terminal automation for AI agents using node-pty; capture output and send input programmatically.\n\n- **[lifeos-cli](https://github.com/liujuanjuan1984/lifeos-cli)** `⭐ 9` — Terminal-native LifeOS for managing intentions, habits, and timelogs; provides structured persistent context for agentic workflows.\n\n- **[zosma-qa](https://github.com/zosmaai/zosma-qa)** `⭐ 8` — Generates QA agent prompts (planner, generator, healer, analyzer) for CLI coding tools (OpenCode, Claude Code, VS Code Copilot); scaffolds autonomous test workflows across Playwright, Appium, and k6.\n\n- **[Praman](https://github.com/mrkanitkar/playwright-praman)** `⭐ 7` — Playwright plugin with CLI agents (planner, generator, healer) for SAP UI5/Fiori test automation; 199 typed control proxies, OData V2/V4, AI-driven test generation via MCP. Apache-2.0.\n\n- **[gate4agent](https://github.com/ZENG3LD/gate4agent)** `⭐ 7` `[ZENG3LD]` — Universal Rust transport library for CLI AI agents (Claude Code, Codex, Gemini, OpenCode). Pipe/NDJSON, PTY, and ACP (JSON-RPC 2.0) modes with tokio broadcast fan-out. MIT.\n\n- **[Agentic Engineering Framework](https://github.com/DimitriGeelen/agentic-engineering-framework)** `⭐ 6` — Provider-neutral governance framework for CLI coding agents. Structural enforcement of task-driven workflows, context budget management, antifragile healing loops, and audit compliance. Works with Claude Code, Aider, Cursor, and any file-based agent.\n\n- **[pi-builder](https://github.com/arosstale/pi-builder)** `⭐ 5` — TypeScript monorepo that wraps any installed CLI coding agent (Claude Code, Aider, OpenCode, Codex, Gemini CLI, Goose, Plandex, SWE-agent, Crush, gptme) behind a single interface; capability-based routing, health caching, fallback chains, SQLite persistence, and a streaming OrchestratorService. MIT.\n\n- **[Not Human Search](https://github.com/unitedideas/nothumansearch)** `⭐ 5` — Search engine for AI agents that ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin); 8,000+ indexed sites exposed via MCP server, REST API, and full-text search. Lets agents discover and verify external services before wiring them into a repo. MIT.\n\n- **[OSOP](https://github.com/Archie0125/osop-agent-rules)** `⭐ 2` — Universal workflow logging protocol for CLI coding agents; produces `.osop` workflow definitions and `.osoplog.yaml` execution records. Supports Claude Code, Codex, Cursor, Windsurf, Aider, Cline, Roo Code, Devin, and OpenClaw. Includes a [visual editor](https://osop-editor.vercel.app) and [spec](https://github.com/Archie0125/osop-spec).\n\n- **[claude-northstar](https://github.com/Nisarg38/claude-northstar)** `⭐ 1` — Transforms CLI agents from task executors into autonomous project partners.\n\n- **[linear-cli](https://github.com/phnx-labs/linear-cli)** `⭐ 1` — Single-file Python CLI for Linear (the issue tracker), zero dependencies. Designed for use as a subagent tool by Claude Code, Codex, Gemini, or Cursor; ships a SKILL.md for drop-in Claude Code integration. MIT.\n\n---\n\n## Contributing\n\nPRs welcome! To add an entry, please ensure it meets these criteria:\n\n**Inclusion requirements:**\n- Must have a **CLI or terminal interface** (IDE-only tools don't qualify)\n- Must be able to **read/write code or run commands** autonomously\n- Link must point to a **valid, active** project (no dead repos)\n\n**Entry format:**\n1. **Name + link** (GitHub preferred)\n2. **Star count** (for GitHub repos)\n3. **1–2 line description** — what it does, who it's for\n\n**Optional:** provider tag `[Company]`, license, or a \"why it's interesting\" note (diffs, LSP, sandboxing, multi-agent, MCP/skills, etc).\n\nEntries are sorted by GitHub stars within each section. Place your entry in the correct position.\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/bradagi%2Fawesome-cli-coding-agents/projects"}