Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 13 of 44

Qwen2.5-Coder-7B-Instruct-AWQ★ 37

transformers safetensors qwen2 text-generation code codeqwen

plank★ 37

Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.

aar★ 37

AAR - open source Coding Agent like codex, claude-code with CLI, TUI, ACP in Python

superagent-desktop★ 37

Free, open-source Mac app for Claude Code, Codex and Antigravity. Your AI coding agent with a real browser, iOS Simulator, parallel chats on git worktrees, and an iPhone app. No API key.

nomorehappypath★ 37

Others give you an AI developer. NoMoreHappyPath gives you the software company. Open source, runs on the AI subscriptions you already have.

peforth★ 37

v2 - You describe what you want. AI writes the Forth. Powered by Python and Project K.

Codemini-CLI★ 36

Terminal-first AI workspace with coding agents, workflows and built-in web UI.

pair-gpt.nvim★ 36

an #openAI powered pair programming partner

ai-code★ 36

copilot, but worse

coding-assistant-codellama-streamlit★ 36

This project demonstrates how to utilize Codellama, a local open-source Large Language Model (LLM), and customize its behavior according to your specific requirements using a Modelfile.

nemo-agent★ 36

Your Python AI Coder!

EntwineLLM★ 36

Local LLM coding assistant extension for Visual Studio

SWE-Debate★ 36

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution [ICSE 2026]

opencode-yg★ 36

A research fork of opencode demonstrating Language Anchoring — making LLMs think consistently in your language. Verified: 95%+ Chinese thinking compliance.

lantor★ 36

Local-first, private AI agent workspace for Codex and Claude. Own your context and run agents on your Mac.

Qwen2.5-Coder-3B-Instruct-GGUF★ 36

gguf code codeqwen chat qwen qwen-coder

rimz★ 36

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

alpine-code★ 36

Open-source Desktop coding agent that's friendly to non-developers and puts you in control of everything, down to its tools.

rocmporter-agent★ 36

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

agent-workshop★ 36

Agent 工坊(Agent Workshop):给它一个 PRD、一个需求点子、或一个可落地的 Agent 方向,它推导出架构方案、组件选型与代码骨架,直到一个能在真实环境运行的产品。

lean-agents★ 36

~66% Faster, ~44% Less Tokens, The only AI coding workflow you need, Supports small models

buildforce-cli★ 35

Buildforce is the consistent, reliable and efficient framework for AI-assisted engineering

deepseek-agent★ 35

本仓库是一个关于 Agent(智能体) 的实验性 DEMO 项目,主要展示如何利用大语言模型(LLM)在计算机上执行“自动化代码编写”、“文件系统探索”等操作。项目基于 DeepSeek R1 系列模型做了一些初步探索,希望借此分享经验与心得,也为更多对 Agent 感兴趣的开发者提供参考。

Jiva★ 35

Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP servers, a built-in Skills system, and Jiva Personas - a plugin framework fully compatible with Claude Plugins.

openwork★ 35

An open-source alternative to Claude Cowork, powered by Claude Agent SDK

OpenSepia★ 35

Autonomous AI dev team — 9 Claude agents run as an agile team: plan sprints, write code, review, test, deploy. Runs 24/7 via cron.

pilot★ 35

A desktop coding agent with a GUI. Electron + React app powered by Pi Coding Agent. A chat-driven development with sandboxed file editing, git integration, dependency-aware task management, persistent memory, and an iOS/iPad companion for remote control.

sven★ 35

Agent Sven: Terminal AI Agent

NanoTeams★ 35

Free, open-source, local-first AI coding agent & multi-agent teams for macOS via Ollama or LM Studio. Autovisor, an autonomous Supervisor, creates, runs, answers & reviews tasks on its own. As MCP, MCP Servers, Bash, computer use, vision, semantic search. Zero telemetry — your code and your ideas never leave your Mac.

cindra★ 35

Desktop coding-agent interface powered by Forgecode

4x★ 35

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

TokenCode★ 35

为 Token 燃烧而生:token 越来越便宜,质量永远稀缺——与其省 token,不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优,用冗余换质量。Go 写的开源终端 Coding Agent,类 Claude Code,可接入任意模型,对团队友好。 | Born to burn tokens — they get cheaper, quality stays scarce. A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best. Claude Code-style, any model, team-ready.

yak★ 35

Yak is an autonomous coding agent for papercuts. It picks up small tasks from Slack, Linear, Sentry, and GitHub and delivers reviewable pull requests while you work on what matters.

Qwopus3.6-35B-A3B-Coder★ 35

transformers safetensors qwen3_5_moe image-text-to-text text-generation-inference unsloth

Qwen2.5-Coder-7B-Instruct-GGUF★ 35

transformers gguf code codeqwen chat qwen

Athena★ 35

Athena is a desktop control surface for AI coding agents with shared project context. Built with Electron, React, and FastAPI, it embeds native terminals for Codex, OpenCode, Claude, and Hermes with Hermes memory integration. Features MCP bridge for cross-platform workspace control, embedded PTY terminals, native session discovery, and more.

termmate★ 35

agentic AI coding assistant supporting claude code, ChatGPT codex, Antigravity, OpenCode and Pi coding agent; with API provider OpenRouter Gemini DeepSeek

AutoHelix★ 35

Agent-powered iterative optimization: put an AI agent in a verified improvement loop.

fletch★ 35

A new kind of IDE for agentic engineering

forgeo★ 35

A scheduled, agent-driven software factory. Keep a plain JSON backlog; Forgeo runs your coding agent (Claude Code, Codex, opencode) on each task and commits to main. Refactors when idle. No branches, no PRs.

zaofu★ 35

An open-source Coding Harness Platform for long-horizon, multi-agent software delivery.

prokop★ 35

Claude Code and Codex in one workspace, with agents that keep their memory and skills across projects. Open source, runs on your machine.

PtahCode★ 35

Provider-agnostic AI orchestration for Electron Desktop, Cli and VS Code. Intelligent workspace analysis, Code Execution MCP server, and project-adaptive multi-agent workflows — all natively integrated into Electron Desktop, Cli and VS Code.

Gen-Code★ 34

Open-source AI agent. Lives in your terminal.

iamnotacoder★ 34

AI code generation and improvement

mitto★ 34

Control you AI coding agents on the go (from Mac, Web, Mobile Phone, etc)

OCLoop★ 34

Loop-Driven Development with OpenCode

heyhank★ 34

Self-hosted web UI for running Claude Code agents (with optional Codex support). Multi-session chat, voice, skills, social media, telephony.

WhipDesk★ 34

Control AI Coding Agents From Your Phone

pi-daemon★ 34

Run the Pi coding agent in a persistent session with a mobile PWA secured by Cloudflare Tunnel and Access.

koder★ 34

Safe to explore. Free to build. Koder by aixplain is an AI coding harness for desktop and terminal, with permission checks, reviewable changes, and hosted or local models.

propr★ 34

Open source, self-hosted GitHub orchestration for AI coding agents. Runs Claude Code, Codex, Antigravity, OpenCode and Mistral Vibe on your server and ships every change as a reviewed pull request: issue to PR, AI code review, automated fix loops.

factorai★ 34

Agentic Development Environment (ADE) for the AI era

agentpulse★ 34

Self-hosted command center for AI coding agents (Claude Code, Codex CLI, GitHub Copilot CLI) — live dashboard, orchestration, and an MCP server for programmatic fleet control.

kubic★ 34

Agentic coding, in your control

unified-brain★ 34

System One coding agents: code-level answers at the score of a Claude Fable 5.1 agent on the same 74-point xz benchmark (68.75 vs 69 / 74) 69× cheaper and 3.4× faster (approx. 1 CENT PER QUESTION evidence gathering). No Context Loss and Memory Limits on sessions since every answer starts from the same, updatable, SQLite index.

Apex-CodeGenesis★ 33

Apex: An advanced autonomous coding agent for VS Code featuring total autonomy modes, recursive chain-of-thought reasoning, council-of-critics self-critique, persistent memory, dynamic personas, and extensive tool use capabilities.

ralph-loop★ 33

This repository implements the "Ralph" autonomous coding loop pattern, designed to be agnostic of the specific AI agent being used. Whether you use Claude, Codex, Gemini, or local models via Ollama/Qwen, Ralph Loop orchestrates the process.

waveforge★ 33

A highly structured software development workflow designed for seamless collaboration between human and AI developers.

etienne★ 33

Coding Agent Harness for custom AI agents

patchpal★ 33

An agentic coding and automation assistant, supporting both local and cloud LLMs.

agx★ 33

agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.

skillmaxxing★ 33

A phase-aware operating system for coding agents that helps them explore, ship, harden, and verify without losing the plot.

Grinta-Coding-Agent★ 33

Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.

QodeX★ 33

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with deterministic guardrails, 100+ tools, a real browser, smart vision & shareable live artifacts. Open source, Apache-2.0.

waveloom★ 33

为 DeepSeek 前缀缓存定制的终端 Code Agent(纯 Go),缓存命中率 95-99%,输入成本降至 1/50。A terminal coding agent optimized for DeepSeek prefix caching — 95-99% cache hit, 1/50th the cost.

Koda★ 33

Koda is your ideal development partner.

pi★ 33

Port of pi-mono to Python; AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pod.

amcp★ 33

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

aurict★ 33

Aurict is an open-source terminal AI coding agent built for real developer workflows: sandboxed tools, subagents, multi-provider LLMs, patch safety, and fast CLI UX.

Qwen3-Coder-Next-AWQ-4bit★ 33

transformers safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

mimofan★ 33

mimofan - AI coding agent platform

AemeathCode★ 33

从零手搓的 Coding Agent(ReAct + 工具 + 记忆 + 权限 + 上下文压缩 + 子agent + MCP),纯 Python/asyncio

pang★ 33

An agentic workflow for autonomous engineering loops

LMLocal★ 33

LM Local is an AI coding assistant for Visual Studio 2022/2026 with agentic capabilities and subagents

langgraph-harness★ 33

Self-hosted AI coding agent platform for GitLab, built with LangGraph. Reviews merge requests, resolves issues autonomously, and chats with full project context.

arbos★ 33

Arbos is a coding agent for one project. Talk to Main, watch workers, keep the work in one place.

codewords★ 33

A local-first AI coding IDE and agent for Windows. Code, search, edit, run tests, and ship with a private AI assistant powered by Ollama.

volt★ 33

The best open-source Agentic development environment.

ConeCode★ 33

A desktop coding workspace for AI agents — chat, files, editor, terminal, Git worktrees and browser preview, plus bounded, evidence-driven Recursive Self-Improvement (RSI). Electron + React + TypeScript.

Forge★ 32

Turn a single Claude Code CLI into a full AI development team — with PM, Architect, Frontend/Backend Engineers, QA, and DevOps agents orchestrated automatically.

rag-coding-assistant★ 32

An AI developer that writes LangChain Expression Language (LCEL).

phantom-agent★ 32

Autonomous AI agent for BitGN PAC1 Challenge — ~86% score with 12 hot-reloadable skills, live dashboard, and self-correcting classification

ralph-loop-optimizer★ 32

Ralph Loop Optimizer: an AI-driven framework that turns any evaluatable codebase into a self-improving optimization loop for strategies, models, prompts, and workflows

agro★ 32

Use Claude + Gemini + Aider agents from the same Specs

claude_code_agent★ 32

Agent-Driven Software Development Lifecycle (AD-SDLC) system built with Claude Agent SDK

moto★ 32

Floom's terminal IDE for AI agents: Claude control plane, Codex workers, Docker runtime, hooks, skills, memory, and browser/Gmail workflows.

ode★ 32

Work anywhere with your favorite coding agents connected, coding sessions map 1-1 to chat threads, live updates and much more!

AnyCoder★ 32

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 lines of Python.

opencode-solo★ 32

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isolated contexts, minimal permissions, adversarial verification built in. Ready to drop in.

Dream-Coder-v0-Instruct-7B★ 32

transformers safetensors Dream feature-extraction text-generation conversational

granite-8b-code-base-4k★ 32

transformers safetensors llama text-generation code granite

Qwen2.5-Coder-32B-Instruct-GPTQ-Int4★ 32

transformers safetensors qwen2 text-generation code codeqwen

qwen_free_cli★ 32

Run Qwen Code as a coding agent through an OpenAI-compatible API.

supermux★ 32

The open-source workspace for coding agents. supermux runs Claude Code, Codex, and other coding agents on your own computer or server, many sessions at once, and lets you work with them from your desktop or phone.

StemCode★ 32

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

claude-architect★ 32

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

andromity★ 32

Andromity - An Opensource AI coding agent that you and your team can Audit

tidebreak★ 32

Open-source, local-first desktop for AI coding agents and document work. Run Claude Code, Codex CLI, opencode, and Grok CLI in isolated Git worktrees.

Converter-Python-to-Rust★ 32

AI-powered desktop app for migrating Python projects to Rust. Supports multiple LLM providers (OpenAI, Anthropic, Ollama), includes 300+ library mappings, automatic dependency detection, compile verification, and iterative code refinement. Built with Tauri 2.0.

More in Coding agents & developer tools