Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 23 of 44

axon★ 6

Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

opencode-gladio★ 6

⚔️ Disciplined orchestration plugin for OpenCode — automatic 4-tier pipeline, ClarityGate, dual review, runtime fallback

clu★ 6

Autonomous AI coding agent — local-first, any language, any LLM. 24/7 daemon with task queue, heartbeat monitoring, cron scheduling, multi-agent roles, and web dashboard.

powerglide★ 6

the CLI coding agent that slides: Zig-powered multi-agent harness for extreme coding workflows. named after the Rae Sremmurd track & its namesake Lamborghini transmission. built for Barvis 🦀⚡

ralph-template★ 6

An automatic Ralph workflow for autonomous software development tasks using the OpenCode CLI tool

DresTermuxAI★ 6

Just an AI assistant for termux users with coding assistant abilities

mimo-tui★ 6

MiMo 模型的原创开源终端 AI 编程 agent · 像 Claude Code / Codex CLI 一样在终端跑 · MIT 开源不收费

thronglets★ 6

Spawn AI coding agents from Telegram. Each gets a name, pixel art avatar, and workspace. Fleet management for Cursor, Claude Code, and Codex.

levelcode★ 6

Levelcode — Open-source AI coding agent with multi-agent architecture for precise codebase editing. CLI + web UI + eval harness, built with TypeScript and Bun.

CXWorkflow★ 6

CXWorkflow is a multi-session Codex development workflow. It does not treat “more agents” as better; it uses minimum necessary concurrency to organize Codex into a predictable, recoverable, long-running development team.

cardloop★ 6

Your AI dev team on your own server, steered from your phone. Every kanban card runs a coding agent (Claude Code by default, Codex or Grok optional) in its own git worktree until it ships. 83% of this repo's commits are co-authored by AI agents. OpenSSF Best Practices: passing.

vexi★ 6

VEXI is an open-source AI coding agent for the terminal. Bring your own API keys, work with OpenAI, Anthropic, and other providers, and code faster with a lightweight, multilingual, privacy-friendly CLI.

7-24-IDE★ 6

Autonomous local AI developer agent for Windows. Plan & Build modes, real terminal execution, Monaco diff reviews, auto-checkpoints, a native Rust engine (Tree-sitter AST + BM25 search), Ollama offline mode and MCP tools — all in your own folder.

tinycode★ 6

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

Custom-PI★ 6

Your autonomous AI coding agent. Open-source. Local-first. Fully extensible.

Cantus★ 6

Cantus is a Claude-first, local-first desktop coding environment for macOS (Apple Silicon). A native Tauri 2 app pairs a Monaco editor, an integrated terminal running the Claude Code CLI in a backend PTY, per-hunk and per-line git staging, resumable Claude sessions, a .claude workflow task runner, and a local SQLite-backed learned-memory store.

Huiyu-Pi★ 6

Huiyu Pi webUI,A local open-source Agent tool that lets you build your own Harness system from scratch. Built on Pi and pi-forge, compared to IDE tools like Codex and Claude Code, context is reduced to nearly zero with massive speed improvements. Build cleanly without platform restrictions.

Xolotl-Code★ 6

Desktop AI coding-agent platform (Tauri + Rust) for racing, evaluating & orchestrating LLMs across Anthropic and open models (Kimi, MiniMax, DeepSeek, GLM, Qwen) — with a deterministic Axolotl Civilization arena the models compete in.

weft★ 6

Local-first delivery system for coding agents — turn one product goal into coordinated, review-ready changes across repositories.

cn-codex★ 6

AI 编程代理框架,支持多模型接入,并通过技能化系统统一编码与自动化工作流。

autodrive★ 6

Autonomous engineering pipeline for Claude Code — /drive runs the task lifecycle (plan → implement → review → harden → finalize → ship) with two human gates, gstack planning, and codex cross-model review.

agent-joe★ 6

Shellless and rust only llm agent

Ralph-Workflow★ 6

Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more

keel★ 6

Turn coding agents into work owners. A vendor-neutral backbone that takes a GitHub issue to a merged PR: readiness check, isolated worktree, multi-agent review, CI and evidence gates, merge window. Claude Code, Codex, Cursor, Antigravity.

octocode★ 6

AI-powered development tool for the terminal. Works with OpenAI, Anthropic, Google, and more.

MARVIN★ 6

AI pair-programming IDE for macOS — native SwiftUI app with a project-aware Claude Agent SDK runtime.

ATV-Phoenix★ 6

Intent in, outcome out. A self-healing, self-learning/hill climbing harness that drives coding agents to a proven outcome instead of a claimed one.

harness-forge★ 6

AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning

jupyter-agent-qwen3-4b-thinking★ 6

transformers safetensors qwen3 text-generation code jupyter

shirdel-coder-9b-claude-fable-5★ 6

transformers gguf qwen3_5 image-text-to-text llama.cpp Anthropic Claude Fable 5

Qwen2.5-Coder-32B-Instruct-GGUF★ 6

gguf code codeqwen chat qwen qwen-coder

Qwen2.5-Coder-32B-GGUF★ 6

gguf code qwen qwen-coder codeqwen text-generation

G-Rump★ 6

Open-source coding agentic harness for macOS — native Swift agent loop, 153 local tools, MCP client+server, persistent cross-session memory, multi-provider BYOK (Anthropic/OpenAI/Gemini/OpenRouter), approval-gated autonomy. Grumpy by design.

entheai★ 6

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

borg★ 6

A small, fast AI coding agent for your terminal. Bring your own model — Ollama, llama.cpp, LM Studio, OpenAI, OpenRouter, or any OpenAI-compatible endpoint — or use the hosted xShellz models. Single static Go binary, no API key required.

superhuman★ 6

Autonomous open-source contribution agent for Claude Code & Codex. A multi-agent harness that picks an issue, writes the fix, scores its own pull request on a 10-dimension merge-probability rubric, and iterates until a maintainer would merge it — a closed-loop, self-improving AI coding agent.

shipmates★ 6

A crew of specialist AI agents and command workflows that drive a GitHub issue to a reviewed, CI-green pull request autonomously. Multi-harness.

herdr-agent-orchestration★ 6

A Herdr-first captain/worker workflow for Hermes, Codex, Grok, OpenCode, Cline, Buzz, and other coding agents.

cursor-agent★ 6

Cursor SDK agent with first-party models, inspired by Hermes behavior and OpenClaw patterns — orchestration, CLI and gateway planning.

windmist★ 6

Open-source AI Software Engineer CLI and terminal coding assistant built in Go.

nudge★ 6

A coding agent on the go — and share with your whole team

atelier★ 6

A software factory where AI agents propose and deterministic code disposes. A Python ADW engine runs coding agents in bounded phases; a Next.js cockpit observes and controls them. Both halves meet at one SQLite trace - the single source of truth.

ancient★ 6

An AI-powered terminal coding assistant inspired by ClaudeCode CLI. Generate, edit, and refactor code directly from the command line using natural language.

factoryos★ 6

Build production software from product intent using specs, task orchestration, reusable workflows, and AI coding teams.

LoopWithAI★ 6

Multi-agent DeepSeek Harness workbench with switchable Pi, OpenAI Codex, Claude Code, and native DeepSeek Agent Loops.

rudy-os★ 6

An office of AI agents on your Mac. Wraps the CLI coding agents you already use, gives them memory, mail and a boss who routes the work.

atlas-code★ 6

ATLAS AI es un agente de codificación autónomo de código abierto que ayuda a los desarrolladores a escribir código, automatizar flujos de trabajo, interactuar con LLM y crear software directamente desde la terminal.

ralphy★ 6

Works your GitHub issue backlog overnight with Claude Code: plans, codes, commits, and closes issues, then hands you a branch to review in the morning. Never pushes, never opens a PR. Runs on your Claude subscription quota.

JackOD-9B-Coder-MTP-GGUF★ 6

gguf agentic code imatrix merge qwen3.5

nexus★ 6

Nexus — AI Coding Agent Desktop App. Free, local, open source. Actually builds things — not just chat about them.

xencode★ 6

Terminal-native Rust coding agent built for free, open-weight models. Local-first: your code stays on your machine — Ollama, llama.cpp, a free-tier Colab GPU, or any OpenAI-compatible endpoint.

FlashAgent★ 6

The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive tools.

agent-007★ 6

From web terminals for your coding agents to a self-running agent company: Claude Code and Codex in parallel git worktrees, a job board they pick work from, and one agent that runs the board from a goal.

aulthium-cli★ 6

Run Aulthium AI Agent instantly in Termux, Linux, or any terminal with a single command.

talos★ 6

An agentic multiplatform coding workspace that remembers what matters,spawns sub agents, controls your device and runs models — private by design.

medha-agent★ 6

A verification-first AI agent harness - one Rust binary, any model. Deny-first policy, OS sandbox, and a tamper-evident event log you can rewind.

swarms-code★ 6

Swarms Code is the fastest and lightest coding agent harness

sudal★ 6

Sudal is a chat-first macOS and Windows app for Claude Code and Codex. Let agents delegate tasks to each other and bring results back to your chat.

agentic-dev-setup★ 6

Multi-agent dev environment: Claude Code thinks, cheaper models type. herdr + OpenCode + OmniRoute + Ollama + Engram.

fusion-cli★ 6

Local multi-model coding control plane. Models propose; Fusion verifies and delivers — nothing reaches your repo until you approve its exact bytes.

shiki★ 6

A simple cockpit for any AI coding agent, extensible with plugins.

opencode-courier★ 6

Multi-session orchestration for OpenCode V2: spawn child sessions, be woken by them.

lemieux★ 6

An open-source coding agent you can take apart: a terminal app (lmx), and the Elixir runtime underneath it (Lemieux). Works with any ReqLLM provider or a local Ollama model, and keeps every session as a transcript you can resume, fork and replay.

lensa-dev-1c★ 6

Нейросеть как оператор Конфигуратора 1С: читает и правит код модулей, проверяет его платформой. Бесплатная программа для Windows в Releases.

Kvist★ 6

🌿 Describe it. Kvist builds it. Your code, your machine, your rules: a sandboxed coding agent that plans, edits, tests and remembers, and asks before anything risky. Powered by AnyModel, with 40+ providers one switch away. Terminal, VS Code, JetBrains, Zed.

wakil★ 6

A multi-model, terminal-native AI agent.

loop★ 6

Loop engineering for AI agents.

jarvis★ 6

A desktop workspace for running coding agents by voice

squad-devkit★ 6

One manager agent, on-demand workers, fewer tokens: Claude Code plans, Codex/Claude/ccr workers build in isolated git worktrees, the manager verifies and merges.

argonauts-code★ 6

Orchestrate any mix of coding agents and models, from Claude Code and Codex to open-weight models on your own machine.

swrm★ 6

Distributed heterogeneous agent task dispatcher — claim under lease, return with evidence. Quota-aware routing across Claude, Codex, OpenCode Go and DeepSeek, in isolated git worktrees with hard budgets.

kagan★ 5

Open-source desktop app for AI coding agents. Run Claude Code, Codex, and more in terminals, review changes, and work in isolated Git worktrees.

swarmux★ 5

Agent-first tmux async task orchestration CLI

write-a-better-codeAgent★ 5

A secure, iterative code generation agent using LangGraph, Docker, and human-in-the-loop validation.

free-coding-agent★ 5

AgentQT / Agent Qt: free local desktop coding agent with a Codex-like UI for web AI providers.

build-your-own-coding-agent★ 5

A minimal CLI coding agent built from scratch with Bun, Ink, and AI SDK v6. Educational project demystifying how AI coding agents work.

Rcode★ 5

OpenCode.ai implementation in Rust - High-performance AI coding agent with streaming LLM, tool execution, TUI, Web UI, MCP, LSP integrations

agent-valley★ 5

AI coding agent orchestration platform — dispatches Linear issues to Claude, Codex, and Gemini agents in isolated git worktrees

WHITE-BOX-CODER★ 5

This tool pioneers transparent AI development. It doesn't just write code; it shows the rigorous process. Core Innovation: Generate Draft code. Review: AI self-critiques for bugs. Fix & Refine: Outputs the final, professional, and compliant code. The result is highly reliable code and a fascinating look into the LLM's self-correction process.

Sia★ 5

:star2: Your AI dev assistant who works on your behalf while you are offline. It gets your tasks from Slack, works on it asynchronously through your favourite vibe coding platform and gets the PRs ready for you.

sharkbait★ 5

AI-powered coding assistant for the command line. Uses OpenAI Responses API (not Chat). Autonomous agents, parallel code reviews, 33+ tools, multi-model support. Built with Bun & TypeScript.

FireClaw★ 5

FireClaw — open-source AI coding agent forged in Mojo. Clean-room rewrite of Claw Code with 184+ tools, full MCP integration, and 3-tier permissions. Mojo delivers C-level speed with full Python library compatibility via native interop. Runtimes in Mojo, Rust & Python.

ralph-methodology★ 5

Ship working code while you sleep - The Ralph Wiggum Loop autonomous AI coding methodology

nyrve★ 5

Code editor with Claude baked in. Every change is verified before you see it.

Omni-IDE★ 5

Omni-IDE v3.0: An AI-native workspace that autonomously fixes terminal errors. Powered by a Gemini + Ollama Agentic Core inside a Hardened Sandbox. 🚀15,795+ clones in 14 days!

PANDA★ 5

PANDA is an autonomous coding orchestrator for Jira and GitHub. It picks up tickets, implements changes, opens pull requests, and handles review follow-ups.

clawcode★ 5

Open-source, terminal-native AI coding agent with multi-provider support, structured diffs, and persistent memory

spool★ 5

Local-first task backend for agent-driven development

sortie★ 5

AI harness that you actually pilot

agented★ 5

A text editor for LLMs, not humans.

autodev★ 5

autodev 是一个自动化开发流程编排工具。它通过 plan -> dev -> review -> arbitrator -> merge 的闭环循环,驱动多代理协作,直到任务通过质量门禁并完成合并。

agent-karen★ 5

I want to speak to the manager

Claude3-5-Agent-Python★ 5

self made agent what have bunch of tools can create files, folders, can analyze, pylint, autopep8, Difff, Edit and Apply , SummerizeWebage, TavilyWebserach uvm.

SiliceProtocol★ 5

A 9-step development workflow that treats JSON as the single source of truth, minimizing AI token usage while ensuring quality.

code-agent★ 5

Code Agent is a minimal, terminal-first coding agent that brings agentic code editing, file system access, and command execution into a lightweight CLI experience.

phi-code★ 5

𝜑 -code: An Agentic Python Competitive Programmer Fueled by (tiny) LLMs

alors★ 5

no-bullshit terminal ai coding agent for professionals. CLI + library

scotpy★ 5

Smart coding template for Python

CodeDAWN★ 5

A discreet, powerful, and context-aware AI code assistant for Visual Studio Code. Get intelligent code suggestions and terminal commands without breaking your flow.

fellow★ 5

Fellow is a command-line interface (CLI) tool that acts as an autonomous software engineering assistant. It uses the OpenAI API to perform various structured tasks by reasoning step-by-step, executing commands, and maintaining a log of its activities.

More in Coding agents & developer tools