Awesome CLI Coding Agents

May 11, 2026 · View on GitHub

Awesome CLI Coding Agents

Awesome Stars PRs Welcome License

A 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.

Last updated: 2026-05-11

What is a CLI coding agent?

A 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.

Contents

Terminal-native coding agents

Open Source

Forkable, extensible, and community-driven. Sorted by GitHub stars. Provider tags [Company] indicate the backing organization.

  • Claw Code ⭐ 191k — 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.

  • OpenCode ⭐ 158k — Terminal-native coding agent with 75+ provider support, LSP integration, and privacy-first design (formerly opencode-ai; now at opencode.ai).

  • Hermes Agent ⭐ 144k — 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.

  • Gemini CLI ⭐ 104k [Google] — Google's terminal agent powered by Gemini, with tools for repo work and research. Apache-2.0.

  • Codex CLI ⭐ 81.8k [OpenAI] — OpenAI's local coding agent for reading/editing/running code, with an interactive TUI and tool execution. Apache-2.0.

  • OpenHands ⭐ 73.1k — Open-source agentic developer environment (formerly OpenDevin) with CLI and web entrypoints; also has a lightweight CLI-only package.

  • Open Interpreter ⭐ 63.5k — Terminal tool that can execute code and actions; often used as a "do things on my machine" agent.

  • Cline CLI ⭐ 61.6k — Model-agnostic autonomous agent for planning, file edits, command execution, and browser use.

  • Pi ⭐ 47.9k — Minimal, adaptable terminal coding harness from the pi-mono toolkit; unified LLM API, TUI, skills, and MCP support.

  • Goose ⭐ 45k — Local, extensible agent that can execute, edit, and test; designed to run on-device and integrate with MCP.

  • Aider ⭐ 44.6k — Pair-programming agent for editing files via diffs/patches, with strong git and multi-file workflows.

  • Continue CLI ⭐ 33.1k — Open-source terminal extension for multi-model coding with local/privacy focus.

  • Qwen Code ⭐ 24.3k [Alibaba] — Alibaba Qwen's official CLI agent for Qwen coder models (workflow tool + repo operations). Apache-2.0.

  • Crush ⭐ 24.1k — Charmbracelet's glamorous agentic coding TUI in Go; multi-provider, LSP-aware, with rich terminal UI.

  • Roo Code CLI ⭐ 24k — Multi-mode CLI agent (architect/code/debug/orchestrator modes); Claude-like terminal interface with skills and checkpoints.

  • SWE-agent ⭐ 19.2k — Agent for resolving real repo issues/PR tasks; frequently used in SWE-bench-style workflows.

  • Kilo Code CLI ⭐ 19.2k — Agentic engineering platform with CLI; orchestrator mode, 100s of LLMs, skills, and checkpointing.

  • Plandex ⭐ 15.4k — "Plan-first" CLI agent for building features across multiple files with structured steps and 2M token context.

  • Smol Developer ⭐ 12.2k — Embeddable developer agent that generates entire codebases from a prompt; designed to be embedded in apps.

  • Trae Agent ⭐ 11.5k [ByteDance] — ByteDance's research-friendly CLI agent for software engineering tasks, with modular architecture and multi-LLM support. MIT.

  • Claude Engineer ⭐ 11.2k — Community-driven CLI for agentic Claude workflows with file management and iterative development.

  • Claurst ⭐ 9.6k — Claude Code rewritten in idiomatic Rust with architectural breakdown; includes discoveries from the source leak (KAIROS persistent assistant, buddy system). MIT.

  • Kimi CLI ⭐ 8.5k [Moonshot AI] — Moonshot AI's CLI coding agent with skills, MCP support, and ACP IDE integration. Apache-2.0.

  • Free Code ⭐ 8.3k — Fork of Claude Code with all telemetry removed, guardrails stripped, and all experimental features enabled (KAIROS, dream mode, companion system).

  • ForgeCode ⭐ 7.3k — AI pair programmer supporting 300+ models, with task management, custom agents, and large-scale refactor tooling.

  • Kode CLI ⭐ 5k — ShareAI's open-source CLI agent for terminal-native coding with multi-provider support.

  • Codebuff ⭐ 4.8k — Multi-agent AI coding assistant with CLI support for collaborative coding workflows.

  • 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.

  • OH-MY-PI ⭐ 4.3k — Terminal coding agent ("Pi") with a TypeScript/Rust monorepo and local-first ergonomics.

  • Mistral Vibe ⭐ 4.1k [Mistral] — Mistral's CLI coding assistant for conversational repo interaction and edits. Apache-2.0.

  • Every Code ⭐ 3.7k — Fork of Codex CLI with validation, automation, browser integration, multi-agents, theming, and multi-provider orchestration (OpenAI, Claude, Gemini). Apache-2.0.

  • Devon ⭐ 3.4k — Open-source pair programmer with a TUI; autonomous planning, execution, and debugging in Git workflows.

  • AutoCodeRover ⭐ 3.1k — Autonomous program improvement agent; patches real GitHub issues using code search and analysis.

  • Grok CLI ⭐ 3k — Community CLI agent built on xAI's Grok models for terminal-based coding tasks.

  • CodeMachine-CLI ⭐ 2.5k — Community multi-agent CLI aimed at running coding workflows locally (vibe-coding oriented).

  • Letta Code ⭐ 2.5k — 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.

  • Codel ⭐ 2.4k — Autonomous agent for performing complex tasks via terminal; runs in Docker with a web UI.

  • RA.Aid ⭐ 2.2k — Autonomous coding agent built on LangGraph with research/plan/implement pipeline; optional aider integration for near-full autonomy.

  • open-codex ⭐ 2.2k — Lightweight fork of Codex CLI with multi-provider support (OpenAI, Gemini, OpenRouter, Ollama).

  • Agentless ⭐ 2k — Lightweight approach to autonomous software engineering without persistent agent loops.

  • Amazon Q Developer CLI ⭐ 2k [AWS] — AWS's agentic terminal chat for building apps, debugging, and DevOps with natural language. Apache-2.0.

  • 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.

  • Groq Code CLI ⭐ 727 — Customizable, lightweight CLI powered by Groq's ultra-fast inference; extensible tools/commands with multi-model support.

  • Dexto ⭐ 617 — Coding agent and general agent harness with CLI/web/API modes; ships a production-ready coding agent with sub-agent spawning.

  • g3 ⭐ 511 — "Coding AI agent" in Rust: tool-running, repo interaction, skills system, and provider abstraction.

  • claw-code-agent ⭐ 470 — 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.

  • Coro Code ⭐ 357 — Open-source CLI coding agent, a free alternative to Claude Code; generate, debug, and manage code seamlessly.

  • LettaBot ⭐ 326 — Personal AI assistant with persistent unified memory across Telegram, Slack, Discord, WhatsApp, and Signal; built on the Letta platform.

  • Mini-Kode ⭐ 301 — An educational AI coding agent CLI, intended as a readable reference implementation.

  • nori-cli ⭐ 124 — Multi-provider CLI built on Codex CLI; switch between Claude, Gemini, and Codex from the same native terminal.

  • cursor-agent ⭐ 120 — Python-based agent replicating Cursor's coding assistant capabilities; supports Claude, OpenAI, and local Ollama models.

  • openHarness ⭐ 90 — 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.

  • VibePod ⭐ 69 — 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.

  • Crab Code ⭐ 61 — 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.

  • QQCode ⭐ 52 — Lightweight CLI coding agent in Rust focused on speed, determinism, and developer control; supports skills.

  • Octomind ⭐ 52 — 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.

  • picocode ⭐ 48 — Minimal Rust-based coding agent focused on CI workflows and small codemods; multi-LLM with personas.

  • Smelt ⭐ 19 — 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.

  • Binharic ⭐ 16 — A multi-provider "tech-priest persona" coding agent CLI (stylized, tool-using).

  • Darce ⭐ 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.

  • CLAII ⭐ 2 — CLI-first AI coding agent with multi-agent orchestration, MCP toolchains, and memory-persistent refactors.

OpenClaw ecosystem

Projects built on, forked from, or inspired by OpenClaw — the open-source personal AI assistant. Sorted by GitHub stars.

  • OpenClaw ⭐ 371k — The original personal AI assistant you run locally; CLI with onboarding wizard, skills, tools, and multi-channel support (WhatsApp/Slack/Discord). MIT.

  • nanobot ⭐ 42.2k — Ultra-lightweight ~4,000-line Python rewrite of OpenClaw; tool use, persistent memory, scheduled tasks, and multi-channel support (Telegram/Discord/WhatsApp). MIT.

  • ZeroClaw ⭐ 31.2k — Fully autonomous AI agent runtime in Rust; trait-driven pluggable architecture (providers, tools, memory, channels), runs on minimal hardware (<5MB RAM), multi-channel CLI/Telegram/Discord/Slack, with sandboxed execution and hybrid vector+keyword search.

  • PicoClaw ⭐ 28.9k — Ultra-lightweight personal AI assistant in Go inspired by OpenClaw; runs on $10 hardware with less than 10MB RAM.

  • NanoClaw ⭐ 28.8k — Security-first lightweight alternative to OpenClaw; runs agents in Apple containers/Docker with sandboxed execution, built on Anthropic's Agents SDK.

  • IronClaw ⭐ 12.2k — OpenClaw rewritten in Rust by NEAR AI; WASM sandbox isolation, capability-based permissions, and prompt injection defense.

  • NullClaw ⭐ 7.5k — Fastest, smallest OpenClaw-compatible agent in Zig; 678KB static binary, ~1MB RAM, <2ms startup, 23+ providers, 18 channels. MIT.

  • Clawith ⭐ 3.6k — "OpenClaw for Teams" — multi-agent collaboration platform that scales OpenClaw to organizations. Apache-2.0.

  • 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.

  • claw0 ⭐ 2.5k — 0-to-1 tutorial companion for the OpenClaw ecosystem; walks through building an agent harness from scratch, covering planning, context compression, and task persistence.

  • GitClaw ⭐ 361 — Git-native AI agent framework where agent identity, rules, memory, tools, and skills are all version-controlled files. MIT.

  • LionClaw ⭐ 7 — Secure-first local AI CLI with a small auditable kernel, durable sessions, and installable skills. MIT.

Closed Source

Proprietary agents — usable but not forkable or extensible at the source level.

  • Claude Code ⭐ 122k [Anthropic] — Anthropic's repo-aware terminal agent for code edits, refactors, and git workflows. Source-available, no OSS license.

  • Warp ⭐ 57.5k [Warp] — Modern terminal with built-in AI agent mode; understands tasks, runs commands, edits files, and orchestrates multi-step workflows.

  • GitHub Copilot in the CLI ⭐ 10.4k [GitHub] — GitHub's agentic CLI for repo/PR/issue workflows, command suggestions, and headless automation.

  • Command Code ⭐ 3.2k [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.

  • Droid ⭐ 859 [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).

  • FetchCoder ⭐ 2 [Fetch.ai] — Terminal coding agent powered by ASI1, with interactive TUI, CLI, and API server modes plus MCP integration.

  • Amp [Sourcegraph] — Sourcegraph's AI coding agent with a CLI for implementing tasks across real codebases.

  • Junie CLI [JetBrains] — JetBrains' LLM-agnostic CLI coding agent (EAP); supports GPT-5, Claude, Gemini, Grok with plan mode and CI/CD headless usage.

  • Cortex Code CLI [Snowflake] — Snowflake's data-native AI coding agent CLI for building pipelines, analytics, and AI apps with enterprise governance.

  • Devin [Cognition] — Cognition's autonomous AI software engineer with full shell/browser access, self-healing code, and PR collaboration.

  • Cursor CLI [Cursor] — Cursor's official command-line agent (agent) with shell mode, headless/CI support, parallel agents, and multi-model access.

  • Tabnine CLI [Tabnine] — AI-powered terminal coding assistant with agentic workflows; distributed as a Docker container, requires enterprise license.

  • Mentat CLI [Mentat] — Cloud-native coding agent CLI for managing remote Mentat agents from your terminal; auto-detects repo/branch context.

Harnesses & orchestration

Session managers & parallel runners

Tools for running and managing multiple agent sessions side-by-side. Sorted by GitHub stars.

  • vibe-kanban ⭐ 26.1k — Kanban interface for administering AI coding agents.

  • cmux ⭐ 16.7k — Open-source platform for running multiple coding agents in parallel.

  • Superset ⭐ 10.6k — A terminal built for coding agents; orchestrates parallel agent sessions.

  • Claude Squad ⭐ 7.4k — tmux-based harness to run and manage multiple Claude Code sessions side-by-side.

  • Emdash ⭐ 4.3k — Run multiple coding agents concurrently with coordinated workflows.

  • CodexMonitor ⭐ 3.8k — Coordinate multiple Codex agents across local workspaces.

  • Crystal ⭐ 3k — Execute multiple Codex and Claude Code sessions in parallel git worktrees.

  • Toad ⭐ 3k — Agent orchestrator for running and managing parallel CLI coding sessions.

  • mux ⭐ 1.7k — Desktop application for isolated, parallel agentic development.

  • supacode ⭐ 1k — Native macOS coding agent orchestrator.

  • jean ⭐ 912 — Administer multiple projects, worktrees, and sessions with Claude CLI.

  • Parallel Code ⭐ 621 — Desktop app for running multiple AI coding agents (Claude Code, Codex CLI, Gemini CLI) simultaneously in isolated git worktrees.

  • CLI Agent Orchestrator (CAO) ⭐ 559 — AWS's hierarchical multi-agent orchestration via tmux with intelligent task delegation patterns.

  • Catnip ⭐ 479 — Containerized environment + worktree automation for running multiple coding agents in parallel (optimized for Claude Code).

  • vibe-tree ⭐ 254 — Execute Claude Code tasks in parallel git worktrees.

  • amux ⭐ 175 — 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.

  • AgentPipe ⭐ 124 — 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.

  • amux ⭐ 105 — Terminal UI designed for running multiple coding agents in parallel.

  • CliDeck ⭐ 73 — 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.

  • multi-agent-workflow-kit ⭐ 10 — Orchestrate parallel AI agents in isolated git worktrees with shared tmux visibility.

  • CLITrigger ⭐ 4 — 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.

  • PATAPIM — 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.

Orchestrators & autonomous loops

Multi-agent coordination, swarm patterns, and autonomous execution loops. Sorted by GitHub stars.

  • claude-flow ⭐ 48.7k — Deploy multi-agent swarms with coordinated workflows.

  • gastown ⭐ 15.1k — Multi-agent orchestration with persistent work tracking.

  • ralph-orchestrator ⭐ 2.9k — Hat-based system maintaining agents in a loop until task completion.

  • ralph-tui ⭐ 2.3k — Direct AI agents through task lists with autonomous execution.

  • AgentsMesh ⭐ 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.

  • loom ⭐ 1.3k — Infrastructure enabling autonomous loops to evolve products via multi-agent coordination.

  • Bernstein ⭐ 312 — Deterministic Python orchestrator — spawns parallel AI coding agents (Claude Code, Codex CLI, Gemini CLI), verifies with tests, auto-commits.

  • Aeon ⭐ 290 — 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.

  • wreckit ⭐ 127 — Apply the Ralph Wiggum Loop pattern across your roadmap for autonomous agent execution.

  • kodo ⭐ 94 — 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.

  • ORCH ⭐ 53 — 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.

  • OpenCastle ⭐ 43 — 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.

  • Forge ⭐ 25 — 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.

  • agx ⭐ 20 — 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.

  • sage ⭐ 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.

  • Relay ⭐ 3 — 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.

Agent infrastructure

Sandboxes, routers, browser/terminal automation, and extension tools. Sorted by GitHub stars.

  • claude-code-router ⭐ 33.8k — Use Claude Code as a foundation while routing to alternative providers/endpoints.

  • agent-browser ⭐ 32.6k — Headless browser automation CLI for agents (useful as a tool plugin for coding agents).

  • NemoClaw ⭐ 20.3k [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.

  • OpenWork ⭐ 15k — Open-source alternative to Claude Cowork for teams; local-first desktop app powered by OpenCode with one-click setup. MIT.

  • open-claude-cowork ⭐ 4.1k — Open-source version of Claude Cowork with 500+ SaaS app integrations.

  • OneCLI ⭐ 2.1k — 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.

  • toprank ⭐ 2k — 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.

  • Claude Code Tools ⭐ 1.8k — Utilities around Claude Code workflows (automation helpers, helpers for common tasks).

  • Coasts ⭐ 386 — Containerized host orchestration for git worktrees; isolates ports, networks, and services per environment using DinD/Sysbox/Podman. MIT.

  • subtask ⭐ 329 — Claude Skill for delegating tasks with subagents in Git worktrees.

  • claude-cmd ⭐ 301 — Terminal wrapper for interacting with Claude models; often used as a building block in harness scripts.

  • kasetto ⭐ 70 — A declarative AI agent environment manager, written in Rust.

  • skill-optimizer ⭐ 53 — 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.

  • AgentPlane ⭐ 48 — 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.

  • claudebox ⭐ 46 — Sandboxed environment for Claude Code (focused on isolation/safety).

  • Untether ⭐ 45 — 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.

  • 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.

  • Nex ⭐ 42 — 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.

  • brood-box ⭐ 30 — Hardware-isolated microVM sandbox for AI coding agents (Claude Code, Codex, OpenCode) with COW snapshot isolation, egress control, and MCP authorization.

  • AgentManager ⭐ 24 — Lightweight CLI for managing multiple agent runs/sessions and workflows.

  • AgentLint ⭐ 24 — 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.

  • EchoCoding ⭐ 24 — 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.

  • agent-terminal ⭐ 10 — Headless terminal automation for AI agents using node-pty; capture output and send input programmatically.

  • zosma-qa ⭐ 6 — 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.

  • lifeos-cli ⭐ 6 — Terminal-native LifeOS for managing intentions, habits, and timelogs; provides structured persistent context for agentic workflows.

  • gate4agent ⭐ 5 [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.

  • 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.

  • Praman ⭐ 5 — 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.

  • Agentic Engineering Framework ⭐ 5 — 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.

  • OSOP ⭐ 1 — 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 and spec.

  • claude-northstar ⭐ 1 — Transforms CLI agents from task executors into autonomous project partners.

  • linear-cli ⭐ 0 — 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.

  • Not Human Search ⭐ 0 — 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.

Contributing

PRs welcome! To add an entry, please ensure it meets these criteria:

Inclusion requirements:

  • Must have a CLI or terminal interface (IDE-only tools don't qualify)
  • Must be able to read/write code or run commands autonomously
  • Link must point to a valid, active project (no dead repos)

Entry format:

  1. Name + link (GitHub preferred)
  2. Star count (for GitHub repos)
  3. 1–2 line description — what it does, who it's for

Optional: provider tag [Company], license, or a "why it's interesting" note (diffs, LSP, sandboxing, multi-agent, MCP/skills, etc).

Entries are sorted by GitHub stars within each section. Place your entry in the correct position.