Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 26 of 44

ralph-harness★ 5

Runs Claude Code in a loop for days. Every iteration is a fresh claude -p, and a commit ships only if your own checks pass.

Snag★ 5

Tap the screen, it gets fixed. Anyone at your company can build features, modules and fixes from inside your app; an AI coding agent turns each request into a PR.

flockr★ 5

A terminal workspace for running many coding agents side by side, across machines and from your phone

ipsupport-code★ 5

A small self-learning coding agent for your own model — any OpenAI-compatible server, local (LLMTray, LM Studio, Ollama, vLLM) or cloud. Single static Go binary, plan/auto modes, skills, permissions, Claude-Code-style TUI.

brgr★ 5

Run Claude Code, Codex, OpenCode, Cursor and more as parallel coding-agent workers in Herdr panes, orchestrated by your Codex or Claude Code session.

vanguard★ 5

Autonomous software factory: fetches tasks from GitHub/GitLab/Linear, implements them with an AI agent pipeline in a Docker sandbox, and opens draft PRs for human review.

hesper★ 5

Run Claude Code and Codex agents on every Mac you own, and steer them from one fast native window.

aulos★ 5

一个 AI 编程 Agent,使用python实现的完整学习项目:终端 REPL + Web 桌面端双入口,内置工具循环、权限体系、多 Agent 编排、会话持久化与自动压缩。

xuanwu★ 5

Run coding agents around the clock—across projects and providers—with supervision, recovery, and reviewable delivery built in.

software-factory★ 5

Local CLI for shipping GitHub issues with multi-agent planning, building, checking, and PR creation.

flow★ 5

Claude Code plugin that runs a batch of software tasks in parallel: managers plan, workers build in their own git worktrees and open PRs, one reviewer merges, checks, releases and deploys. You only make the decisions.

filo-desktop★ 5

Your own team of AI agents, on your Mac.

radian★ 5

A coding agent in one Rust binary: full-screen terminal UI and headless exec, JSONL sessions, optional OS sandbox, MCP, skills, memory.

AIWorkstation★ 5

A native macOS canvas for running and orchestrating multiple AI coding agents (Claude Code, Codex) as real PTY terminal cards — git worktree isolation, browser nodes, Focus Mode. Local-first, no backend.

zpit★ 5

TUI-based AI development cockpit that orchestrates Claude Code agents across projects with automated issue lifecycle, cross-agent channel communication, and a 5-layer safety system.

drydock★ 5

Specs in, pull requests out — an agentic pipeline for Claude Code. Git is the queue, Markdown files are the rules, and adversarial review happens before any PR exists.

Vyb★ 5

An Agentic Development Environment (ADE) for running and monitoring multiple AI coding agents in one place.

opendots-codex★ 5

Self-hosted desktop AI workspace that uses each person's own signed-in OpenAI Codex CLI session locally.

gemma-coder★ 5

Local/edge agentic coding assistant powered by Gemma 4. Drop-in rulebook from claude-code-pro-pack. Works on Raspberry Pi.

kkagent★ 5

A lightweight Rust coding agent with a clean terminal UI — a fast, low-memory alternative to Claude Code, Codex CLI, and Kimi Code.

harness-mini★ 5

A minimal outer harness for developers' long coding tasks. Files + shell: skills, sub-agents, and distilled docs. Keeps multi-session work on-task, context-light, and resumable.

clawd-code★ 5

Clawd Code — Python 智能体编程框架:多智能体协作 / 5 阶段工作流引擎 / MCP 桥接与检疫审批 / 逆向工具链 / Electron 桌面端 / 评测 harness(replay 确定性回归)

DuoForge★ 5

Claude and ChatGPT working together on your project, in one local chat. No API keys.

maestro★ 5

Free desktop app to run Claude Code, Codex, Cursor, OpenCode and other AI coding agents in parallel, each in its own git worktree. macOS, Windows, Linux. Steer every agent from your phone. A Conductor alternative.

Termux-CLI-Coding-Agents★ 5

A collection of tested CLI coding agents for Termux on Android, featuring installation guides, setup instructions, and usage documentation.

ompanion★ 5

GUI client for omp, the oh-my-pi coding agent, on this computer and remote machines over SSH and Tailscale

cairn★ 5

Self-hosted, open-source multi-agent workspace. You write the tickets, agents build them on your machines, you gate what merges.

kip★ 5

Terminal for running many Claude Code agents at once: see which one finished and how full its context is, put idle sessions to sleep to free RAM, and find any past conversation. Real PTY, native Rust, macOS and Windows.

Squadra★ 5

Multi-agent Claude Code: a coordinator agent runs squads of Claude Code agents on any of your machines, approves their safe actions and only asks you what matters. Live web dashboard, web terminal, self-hosted, zero dependencies.

lmstudio-agent-toolkit★ 5

An LM Studio plugin that turns a local model into a coding agent: files and shell, memory, git and GitHub, web search and a real browser. No API keys, nothing leaves your machine.

tim-harness★ 5

A full LLM coding agent in one browser page — 19 tools, token economy (84-90% savings), 4 visualization modes, zero backend

even-terminal-pi★ 5

A pi (@earendil-works/pi-coding-agent) provider for @evenrealities/even-terminal — run the pi coding agent on Even Realities G2 smart glasses + R1 ring.

telepath★ 5

Send coding tasks to an AI coding agent on your own machine from Telegram. Watch it work in real time, approve risky actions, and get every change as a clean, reviewable git branch. Multi-agent (Claude Code, Gemini, Codex, Aider), cross-platform, written in Go.

PiKit★ 5

A clean Android AI agent built on pi and Termux. 一个基于 pi 和 Termux 的简洁安卓 AI Agent。

snippet-service★ 5

A code-first AI agent for your terminal. Durable sessions, Mission Control, voice, and a headless daemon you steer from your phone or desktop. Bring your own model.

cxagent★ 5

A terminal AI coding agent: single-agent loop with permission-gated file, shell and http tools

Eirene★ 5

A fully autonomous AI agent for coding, automation, and deployment, on every major platform

teamree★ 5

The agentic development environment (ADE) for teams. Your whole team ships in parallel.

Moonfold★ 5

Multi-model AI coding workspace with seamless agent switching, shared context, and developer tools.

factory★ 5

Factory: a simple software factory on Herdr. Claude Code plans and builds, Codex reviews, Beads remembers, mechanical guardrails decide.

autocomp★ 5

An autonomous company as a tick loop inside Claude Code — role subagents, human approval gates on money and outreach, an append-only ledger.

phantom★ 5

Chasing open-source RSI (recursive self-improvement): a fully autonomous software factory that improves itself. Anyone can join Phantom with their own agents and compute: Claude Code, Codex, Devin, Grok and local models.

tiller★ 5

Tiller helps a team of people and coding agents deliver high-quality software fast, with the confidence to ship it.

oasis★ 5

The open-source coding agent for any model: terminal and self-hosted web app, Claude Code plugins, subagents, and work that is actually verified.

symphony-trello★ 5

Turn Trello cards into isolated, autonomous Codex implementation runs, allowing teams to manage work instead of supervising coding agents.

identra★ 5

A desktop canvas for running coding agents

fagan★ 5

Spend tokens on judgment, not typing. An MCP-native autonomous SDLC pipeline: frontier models plan and review, local models implement — engineering discipline on a $20/month budget.

devintern★ 5

Automate Jira, Linear, and GitHub Issues with Claude Code or Codex. A self-hosted worker that opens pull requests and follows up on review feedback.

repair-agent★ 4

Repository-level automated code repair agent using SWE-Bench dataset

win2race★ 4

Win-to-Race: native macOS app for orchestrating multiple coding CLIs on one task, with isolated branches, workspaces, logs and review records.

ACode★ 4

ACode is Roo Code fork with optimized automations, Roo Code gives you a whole dev team of AI agents in your code editor.

rakh★ 4

Rakh.sh AI Coding Agent

OwnKey★ 4

Code Reviewer

smart-class-back★ 4

✨ 一种基于代码生成的大语言模型 (LLM) 智能体,实现班级自主管理小程序 A code-generation-based LLM agent for autonomous class management mini-programs.✨一个基于大语言模型(LLM)的智能班级管理小程序,通过代码生成和函数调用实现多智能体协同,支持自然语言交互、成绩预测、统计分析、可视化图表等功能。创新点包括函数依赖图、智能体反问机制和动态知识库集成,系统采用Django和FastAPI混合架构,兼顾开发效率与高并发性能,为班级管理提供智能化解决方案。

contribos★ 4

AI-powered open-source contribution platform — discover issues, generate fixes with LLM agents, review diffs, and submit pull requests. Supports 8+ LLM providers, BYOK, and the A2A protocol.

Bossku-AI★ 4

Self-Learning Developer AI Orchestrator

NexGSD★ 4

From one prompt to a finished product — fully autonomous. Auto-plans, remembers across sessions (persistent context), builds end-to-end, audits security & performance, deploys. 18 agents + 39 workflows for ChatGPT, Copilot, Codex, Cursor, and other AI coding tools. Built by NexVar.

churro-coder★ 4

An opinionated open-source coding agent client. Run Claude Code, Codex, and more - locally or in the cloud.

agent-arena★ 4

UFC-style visual arena where two AI agents compete on coding tasks. Electron + React + pixel art fighters.

AI-Agent-Code-Generator★ 4

An advanced AI agent utilizes multiple LLMs for code generation

orion-agent★ 4

Multi-agent AI coding assistant with persistent memory, governed execution, and continuous learning

9octopus-cli-oss★ 4

9Octopus CLI is a powerful, open-source AI coding agent that lives in your terminal. It empowers developers to interact with Large Language Models (LLMs) directly from the command line, enabling seamless coding assistance, file manipulation, and system automation.

what-to-code★ 4

An LLM-powered web app to help developers brainstorm and kickstart new software projects!

terminal-stampede★ 4

A parallel agent runtime for your terminal. Run up to 20 AI coding agents simultaneously in tmux panes. Works with any CLI agent.

agent-relay★ 4

Autonomous build pipeline for AI coding agents. Multi-agent parallelism, adversarial review, compound learning.

converge★ 4

Long-running AI agents that adapt until outcomes converge.

agentcodehandoff★ 4

Local-first bring-your-own-agent control plane for coding agents with handoffs, supervision, routing, and recovery.

devcell★ 4

Agentic Coding, Without the Blast Radius.

MayorWest★ 4

Security-first autonomous coding for GitHub Copilot. Issue-to-merge automation with 4-layer security architecture. Full autonomy with configurable guardrails.

agent-fox★ 4

agent-fox is an autonomous spec-first coding agent.

neuraforge-ai★ 4

AI-powered development platform — 41 agents, 22 MCP servers, 36 skills across 7 stacks. Describe a feature, get production-ready code. Works with 12 platforms.

AGENTIC-AI-PROJECT★ 4

An experimental real-time collaborative coding platform exploring agentic AI within live communication workflows. CodeWeave introduces an AI participant that passively observes conversations and responds contextually when invoked (e.g., @ai), acting as an intelligent third collaborator in human-to-human and human-to-AI interactions.

metalgate-code★ 4

ACP (Agent Communication Protocol) code agent featuring in-session dynamic deterministic tool skills and optional cross-session persistent memory.

cortex★ 4

Cortex is an agentic CLI written in Rust that simulates a full software development company. You give it a natural-language idea; it orchestrates specialized AI agents to produce a complete, deployable project.

destila★ 4

An agent-based integrated development environment

appmancer★ 4

AI assistant

Advance-Code-Converter★ 4

Experience seamless code conversion and GitHub integration with our advanced tool, leveraging OpenAI. Easily convert and push code to your GitHub repository, streamlining your development process and enhancing collaboration. Boost productivity today!

Minato★ 4

OpenSource AI Assistant: Revolutionize Enterprise Software Development

open-ai-codex★ 4
DevOrch★ 4

A terminal-native, multi-provider intelligent assistant that plans, executes, and tracks developer tasks, not just answers prompts, similar to Claude Code and Gemini CLI.

Orbit-Release★ 4

Orbit: AI-native development environment

vibeharness★ 4

Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent PTY shells, sub-agents, planning, hooks, prompt caching, rate-limit-aware retry, mid-turn-checkpointed sessions. Anthropic + OpenAI.

forge★ 4

An autonomous coding agent that tells you the truth. Multi-agent LangGraph orchestrator with outcome-honesty invariants, trust ratchet, and baseline-aware merge gates.

dev-council★ 4

An experimental framework for building collaborative coding agents that design and implement software through structured debate and consensus.

swarmweaver★ 4

Autonomous coding agent with swarm orchestration—multiple agents in parallel worktrees. Six modes: greenfield, feature, refactor, fix, evolve, security. CLI + Web UI, approval gates.

agent-estate★ 4
XCoding★ 4

💻 Build and manage multiple coding projects seamlessly with XCoding, a lightweight IDE designed for focus and efficiency.

ClawCodeSharp★ 4

Claw Code in C# but even better and with OpenAI and NVIDIA NIM Support

figaro★ 4

🎭♪ Figaro, a coding agent. Pronto prontissimo.

tod★ 4

An AI agent that lives in your terminal and codes for you.

APEX★ 4

Autonomous Product Engineering eXecutor - Multi-agent orchestration platform for automated software development, built on the Claude Agent SDK.

sprintpilot★ 4

Sprint autopilot for BMad Method — drives stories from plan to PR-ready code with git worktrees, commits, and stacked PRs.

vibe-kanban★ 4

🛠️ Boost your workflow with Vibe Kanban, the tool that enhances productivity by optimizing interaction with coding agents like Claude Code and Codex.

codebot-ai★ 4

Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

ouroboros★ 4

Ouroboros: Agent first software engineering infrastructure. Autonomous AI agents plan, implement, test, review, and merge pull requests through typed contracts and constrained workflows. The system manages and improves itself.

omni-code★ 4
CodeWeave★ 4

An experimental real-time collaborative coding platform exploring agentic AI within live communication workflows. CodeWeave introduces an AI participant that passively observes conversations and responds contextually when invoked (e.g., @ai), acting as an intelligent third collaborator in human-to-human and human-to-AI interactions.

spica-cli-coding-agent★ 4

an opensourse AI coding agent

vibeCat★ 4

macOS desktop companion for solo developers — an AI coding partner that watches your screen, hears your voice, remembers context, and proactively helps. Built for Gemini Live Agent Challenge 2026.

cursorfy★ 4

A recursive dashboard. Built on the Cursor SDK and FastAPI. The agent reads its own source code, queries its own data, and edits itself when you ask it to. Two lines of Python and a script tag.

More in Coding agents & developer tools