Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 2 of 44

gentle-shell★ 2,838

Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).

teaql-agent-kit★ 2,822

A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.

ORG2★ 2,649

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

CodeGeeX4★ 2,607

CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.

nanocoder★ 2,582

An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.

CodeMachine-CLI★ 2,518

CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️

collab-public★ 2,509

Collaborator is a place to create with agents.

codel★ 2,474

✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.

fulling★ 2,447

Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.

claude-code★ 2,380

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands. All original source code is the property of Anthropic.

app★ 2,325

The GitHub Copilot app is an agent-native desktop experience for finding, running, steering, and landing software work across your GitHub repositories.

kimchi★ 2,287

Terminal coding agent powered by Kimchi's multi-model orchestration

deepclaude★ 2,278

Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

minimax-code★ 2,269

An open-source coding agent for your terminal, powered by MiniMax.

zeroshot★ 2,207

Multi-agent graph harness for Claude Code, Codex and other coding agents. Separate agents review and test the work. Runs locally on your subscription.

deepcode-cli★ 2,186

Deep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手,支持深度思考、推理强度控制以及 Agent Skills。

mission-control★ 2,162

The world's first Autonomous Product Engine (APE): AI agents research your market, generate features, and ship code as PRs. Convoy mode, crash recovery, cost tracking, 80+ API endpoints. Self-hosted via OpenClaw Gateway.

Zoo-Code★ 2,137

Zoo Code gives you a whole dev team of AI agents in your code editor.

ATLAS★ 2,114

Adaptive Test-time Learning and Autonomous Specialization

loushang★ 2,104

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

ATLAS★ 2,093

Adaptive Test-time Learning and Autonomous Specialization

ante★ 2,048

Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.

smallcode★ 2,023

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

pi_agent_rust★ 2,004

High-performance AI coding agent CLI written in Rust with zero unsafe code

amazon-q-developer-cli★ 1,967

✨ Agentic chat experience in your terminal. Build applications using natural language.

CoreCoder★ 1,931

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.

OpenMonoAgent.ai★ 1,924

(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% open source, free forever, and installed with a single command. Proudly built on C#/.NET, because AI tooling should be infrastructure, not a subscription.

nezha★ 1,902

Code Editor for the AI Agents Era. Run multiple Claude Code and Codex agents across projects on your machine.

dev-gpt★ 1,864

Your Virtual Development Team

yoyo-evolve★ 1,832

A Truman Show of a self-evolving AI coding agent. It writes its own code. Growing up in public.

dmux★ 1,819

A dev agent multiplexer for git worktrees and coding agents.

Lody★ 1,805

Share coding agents with your team on phone and desktop

coding-agent-template★ 1,801

Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway

zero★ 1,786

The coding agent that answers to you, your model, your machine, your rules.

mux★ 1,784

A desktop app for isolated, parallel agentic development

goal-driven★ 1,766

A multi-agent system that keeps running for ~100 hours and solve a very complicated coding or math problem that can be verified

zerostack★ 1,761

Lightweight coding agent written in Rust, optimized for memory footprint and performance

pi-vs-claude-code★ 1,720

Comparison between open source PI agent and closed source Claude Code agent

zero★ 1,682

The coding agent that answers to you, your model, your machine, your rules.

Empryo★ 1,629

AI coding harness for desktop, terminal and CI. Maps your repo, edits code by symbol through AST and LSP, then runs your checks. Any model or the plan you already pay for. Get it at https://empryo.com

chipotlai-max★ 1,597

The AI coding agent that runs on stolen Chipotle compute 🌯 Fork of OpenCode with Pepper AI as default model. Community project to add providers from Home Depot, Lowes, Target, Starbucks & more.

karpathy★ 1,582

An agentic Machine Learning Engineer

MLE-agent★ 1,576

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

openharness★ 1,520

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

evo★ 1,504

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

lime★ 1,496

Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent workflows.

zeroshot★ 1,489

Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.

OpenCollab★ 1,478

A research-friendly, high-performance multi-agent collaboration coding framework.

multi-agent-coding-system★ 1,475

Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.

sandbox★ 1,406

Code editing environment with an AI copilot and real-time collaboration

opentag★ 1,378

Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cursor and more on your own machine, then replies in-thread with verified, evidence-backed results.

10x★ 1,367

⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

Tianshu-harness★ 1,356

天枢harness是一个的终端编程智能体,它要回答的核心问题是:模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环,不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境(CVM),把目标、状态、证据、资源、权限与终止条件从对话历史中外部化,由运行时持续管理。同时对deepseek v4极度优化。

little-coder★ 1,354

A coding agent optimized to smaller LLMs

helmor★ 1,306

Open-source local workbench for multi-agent software development.

codefuse-chatbot★ 1,292

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

headlong★ 1,278

An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.

PiDeck★ 1,231

PiDeck 是一个开源的桌面工作台,用于在本地项目目录中统一管理 PI | DSH | ACP Agent 会话,并支持导入 Codex、Claude 本地会话以便统一浏览和恢复。支持多项目工作区、会话历史、Git 集成、内置终端、模型配置和插件管理,基于 Electron 构建。

claudecode★ 1,224

Open Source ClaudeCode Leaked. Same functionalities as Claude Code by Anthropic. Written in Rust, Ready to use immediately for free.

openclacky★ 1,210

The Most Token-Efficient Lightweight AI Agent

Cougar-CLI★ 1,194

Cougar CLI - An AI programming agent for the command line

MiniCode★ 1,172

A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentation. Multi-language support: TypeScript , Python and Rust implementations available now.

Mysti★ 1,159

AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.

kandev★ 1,157

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

CORAL★ 1,140

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

easyeda-agent★ 1,136

嘉立创 EDA 专业版(EasyEDA Pro)开源 AI 自动化:原理图、PCB 布局布线与工程检查,支持 CLI / Agent Skill / MCP。配套 EdaDesk Desktop 内测版可下载体验。Open-source AI schematic and PCB automation for EasyEDA Pro.

SWE-AF★ 1,134

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

pydantic-deepagents★ 1,124

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

loki-mode★ 1,119

Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.

cezar★ 1,111

Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.

parallel-code★ 1,100

Run Claude Code, Codex, Copilot and other agent CLIs in parallel worktrees, then check what each one did before you merge.

deeptide★ 1,098

Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent

snow-cli★ 1,067

Agentic coding in your terminal,Simultaneously compatible with OpenAI, Gemini, and Claude.运行在终端的 AI 编程智能体,同时兼容 Deepseek、OpenAI、Gemini和Claude。

OpenAlpha_Evolve★ 1,059

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

easy-agent★ 1,031

Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.

opencrabs★ 1,031

The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry.

auto-coding-agent-demo★ 1,028

一个长达 10 小时的 AI 全自动编程实验

codeAgent★ 1,012

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.

cybercode★ 1,011

整合 Claude Code 编程能力与 Hermes Agent 自进化能力的智能体 / An AI agent combining Claude Code coding capabilities with Hermes Agent self-evolution.

phi★ 1,007

A fast coding agent, rpc plugin, sub-agents, sloppy edits, and mcp

hax★ 1,005

A minimalist, terminal-native coding agent written in C.

SuperCoder★ 1,003

Open Source Autonomous Software Development System

dscode★ 1,002

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

agentic-harness-engineering★ 982

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

cc-mini★ 976

Ultra-light Harness scaffolding for AI agents, a mini version of claude code

Whale★ 974

Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

ralph★ 952

A minimal, file‑based agent loop for autonomous coding.

opencrabs★ 945

The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry.

pi-agent-desktop★ 940

Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start coding right away.

AI-Functions★ 936

AI-Powered Function Magic: Never code again with GPT models!

clawcodex★ 928

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.

piclaw★ 921

pi coding agent in a technicolor web trenchcoat

cyrus★ 909

The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.

Wegent★ 893

Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.

PiG★ 888

PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language.

clodex-ide★ 872

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

juggler★ 868

The Juggler Code Agent

pi-pocket★ 865

A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

Pi-Bolt★ 851

⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on Node. Linux, macOS, Windows, ARM64 and Android (Termux).

pullboard★ 845

Autonomous development for real products. You set the standard. Declare your vision. Walk away. It builds.

More in Coding agents & developer tools