Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 8 of 44

paneflow★ 98

Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI.

OpenClaudia★ 98

Open Source Agentic Coding Harness

pi.nix★ 98

Nix flake for earendil's pi, a terminal coding agent.

agention-marshall★ 98

Coding agent

100x-orchestrator★ 97

An orchestration system for managing AI coding agents. The system uses Aider (an AI coding assistant) to handle coding tasks and provides real-time monitoring of agent outputs through a user-friendly interface.

toh-framework★ 97

Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is verified done. Works in Claude Code, Cursor, Antigravity, Codex and ZCode.

ness★ 97

An IDE for coding with agents

ai-project-copilot★ 97

🚀 Turn ideas and repositories into showcase-ready AI projects with agents, RAG, multimodal AI, local models, evals, safety checks, and polished demos.

pi-web★ 97

Drive your pi coding agent from any browser on your network — laptop, phone, or tablet.

tortie★ 97

A calm agent multiplexer with familiar IDE features, for macOS, with an iPhone app.

pi-web★ 97

Web UI for Pi Coding Agent that keeps sessions alive in real workspaces.

Pywen★ 96

Full-stack Python Code Agent platform

harness-engineering-playbook★ 96

A practical framework to ship quality software with AI agents in team environments

simple-long-horizon-agent★ 96

Simple Long Horizon Agent - A simple yet effective AI agent for learning, experimentation, and long horizon work.

intentic★ 96

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

my-code★ 96

A modular, glass-box coding agent—inspect exactly what your agent sends to the model.

MiMo-CodeHarness★ 96

A Xiaomi MiMo-powered multi-agent evaluation harness for real-world code repositories.

Mountains★ 96

A coding agent engine and CLI with cache-aware context management.

koder★ 95

Koder - An intuitive AI coding assistant and interactive CLI tool that boosts developer productivity with intelligent automation and context-aware support.

AI_Teammates_in_SE3★ 95

Replication package for "The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping SE"

opencode-safechange★ 95

A risk-aware multi-agent runtime for safe code migrations in OpenCode.

Monstrare★ 95

Monstrare — a gate-based workflow layer for AI coding agents. Every non-trivial change is spec'd, planned, verified, and reviewed before it ships — nothing is called done without evidence.

EasyMint★ 95

Open-source desktop AI coding platform with built-in Pi Agent (pi-coding-agent) — a graphical AI programming assistant that lets non-technical users drive AI through the full software development flow (Electron)

damon-ade★ 94

ADE — an agentic development environment for macOS. A roster of persistent coding agents, each with its own repo, runtime CLI, and memory.

EmbodiedSWE★ 94

Sim data generation with coding agent

multriix-x★ 94

Local AI Developer Platform with Integrated Code Editor, Mixture-of-Agents Collaborative Ensemble.

OrbitDock★ 93

Run, review, and orchestrate AI coding agents from anywhere

fine★ 93

Ready-to-use Fine AI agents for automating development workflows

tenet★ 93

Cross-platform AI agent harness for 12+ hour autonomous development cycles. Spec-driven, DAG-orchestrated, with a 3-critic evaluation pipeline. Works with Claude Code, OpenCode, and Codex.

y★ 93

Malleable coding agent app. Use Claude Code and Codex to code and reshape the app itself live.

SemaPLC★ 93

SemaPLC is an open-source agentic IDE for generation, verification, and simulation of PLC Programs from natural language.

mo-code★ 93

mo-code 是 mortis 从零实现 Claude Code 核心功能的实验项目,目标是实现一个可运行、可解释,并重点研究安全边界的终端 Coding Agent。

jemma★ 92

jemma & her ai agents that build software

forge★ 92

The Vibe Coding++™ platform - orchestrate multiple AI agents, experiment with isolated attempts, ship code you understand. Multi-agent kanban with MCP integration.

claude-code-go★ 92

本仓库通过 npm 发布包(@anthropic-ai/claude-code)内附带的 source map(cli.js.map)还原的 TypeScript 源码,版本为 2.1.88。本从仓库翻译为go版本

OpenClaudia★ 92

Open Source Agentic Coding Harness

keen-code★ 92

A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.

PurrCode★ 92

A judgment-first coding agent runtime

connector_sdk_tools★ 92

AI coding agent tools to build connectors using Fivetran Connector SDK

aizen★ 92

Aizen is an AI coding agent that lives on your PC or VPS. Control it from your phone while it autonomously fixes code, runs tests, and reports the results back to you.

DeepTask★ 92

open source agent in vscodium

toolmaker-agent★ 92

Toolmaker Agent is an Agentic AI SDLC platform — humans and agents collaborate on the same structured data model.

xmatrix★ 92

Group chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your own subscription and keeps the team's pages current.

graphone★ 91

A visual workbench for coding agent orchestration for Windows, Linux & macOS. Chat interface for local & remote LLMs. Built with Tauri 2.x and Svelte 5.

baro★ 91

CLI that turns a goal into a pull request. Parallel AI coding agents on a Mozaik event bus.

kobe★ 91

The agent multiplexer in your shell. Multiplex your agents like you multiplex your terminals — run Claude Code, Codex, and Copilot in parallel, each session on its own git worktree and branch. Attach, detach, reattach; they keep working after you disconnect.

evolve-agent★ 91

自主迭代进化的 Code Agent 工具

openseek★ 91

DeepSeek-backed MoonBit coding agent.

PiDeck★ 91

A desktop interface for Pi Coding Agent, with visual workflows for conversations, tool calls, sessions, models, and packages.

adaptive-repository-agent★ 91

A LangGraph-powered repository agent that uses LangChain, Q-learning, and human approval to plan, patch, test, and adapt code changes safely.

SI2CA★ 91

Official Repo for (Self-Improving)^2 Coding Agent: Curating High-Quality Trajectories via Recursive Self-Improvement

claudius★ 90

Agentic Development Environment

ralph★ 90

Ralph is a small runner around GitHub Copilot CLI (standalone) inspired by the“Ralph Wiggum” technique: run a coding agent from a clean slate, over and over, until a stop condition is met

ThoughtCoding★ 90

支持命令行的 AI Agent 编程工具

bash-agent★ 90

A minimal AI coding agent runtime. Pure bash + awk, zero runtime dependencies.

pi★ 90

A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop, and pi-coding-agent, native in Go with no Node.js runtime. Anthropic/OpenAI/Google, 999-model catalog.

spex★ 90

The essential spec layer AI agents need to build software reliably.

neurosquad-cli★ 90

nsq — run several AI coding agents in your terminal and stop babysitting them. Open-source CLI by NeuroSquad.

upcomputer★ 90

The self-orchestrating control plane for coding agents. Free, open source, any provider.

anvil★ 89

IDE for parallel agent work. Create worktrees in one click. Share plans between agents. Execute with parallelism + isolation.

kent★ 89

Agentic Coding platform for Professional SWE work focusing on output quality. Self-review, supervision, dynamic workflows, dynamic agent loops.

Claxedo★ 89

Open-source coding-agent workspace: desktop app + composable TypeScript framework for building coding-agent products

zeno★ 89

Desktop shell for the pi coding agent

codej★ 89

Java-powered open source coding agent CLI with an explicit agent runtime and unified tool pipeline.

fx-ui★ 89

A desktop app for the fx coding agent, built on libfx and GPUIX.

Dossier★ 88

Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships from one interface.

HolyCode★ 88

AI coding workstation: OpenCode + Claude subscription support + 30+ tools + headless browser + multi-agent orchestration

sekrun★ 88

A coding agent CLI powered by DeepSeek V4 Flash

avlcode★ 88

AVL Code 是安天(Antiy)澜砥团队推出的国产 AI 智能编程与安全分析桌面助手,Windows / macOS / Linux 全平台原生分发。它把对话式 AI 与工程师真实工作台合二为一:读写代码、执行命令、研判恶意样本。

OpenWork★ 88

Simple editor supports agentic AI.

3code★ 88

The Economical Coding Agent

mini-coding-agent-go★ 88

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

koko-pi-agent★ 88

终端里的 AI 编程助手。基于 Python + Textual 构建,提供交互式 TUI、非交互式单次执行、浏览器远程模式三种前端,并内置多 Agent 团队协作能力。架构上参考 Pi 的分层设计,取向是稳定核心 + 可扩展 Runtime。

coder★ 87

🚀 Next-generation AI code assistant with Multi Agent methodology

daintree★ 87

A review-first desktop habitat for running AI coding agents in parallel.

discobot★ 87

Coding Agent Session Manager

open-cladude-code★ 87

A pure open-source coding agent developed solely by DeepSeek.

shadxn★ 86

Experimenting with AI our way into the unknown — monorepo: agentx (agentic code generation engine) + shadxn (component registry & transforms)

LibreCode★ 86

LibreCode - A Ollama cursor like coding / Reversing Interface

deepseekcode★ 86

Archived coding agent for DeepSeek models. See deepseek-ai/deepseek-harness.

AgentCodeGUI★ 86

Claude Code와 Codex CLI를 위한 올인원 에이전트 앱

SWE-agent-LM-32B★ 86

transformers safetensors qwen2 text-generation agent software engineering

iceCoder★ 86

Self-hosted AI coding agent with desktop & mobile UI

viden★ 86

Rust-first reimplementation of a local agent CLI inspired by Claude Code.

coppice★ 86

Local desktop app for multi-agent coding with Claude Code, Codex, Cursor, and more.

pi-dispatch★ 85

Run the pi coding agent as a service — triggered on demand, on a cron schedule, or by a GitHub or GitLab issue, comment or pull/merge request — in a container you control, with a durable queue, a spend cap, and a live admin panel.

waybill★ 85

Continue unfinished work across coding agents with portable handoff bundles.

mo-code★ 85

mo-code 是 mortis 从零实现 Claude Code 核心功能的实验项目,目标是实现一个可运行、可解释,并重点研究安全边界的终端 Coding Agent。

2M-Code★ 84

2M Code (Multi-Mind) — A terminal-native AI coding platform where teams of specialized, multi-provider LLM agents (Anthropic, Google, OpenAI, Mistral) collaborate to plan, implement, and review code together via a shared SQLite event bus.

sagent★ 84

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

aicode★ 84

在 Android 上运行的 AI 代码编辑器,内置 Linux 终端、AI Agent 与 MCP 协议。

BanyanCode★ 84

A terminal-native multi-agent coding agent with parallel subagents, persistent memory, Tree-sitter code intelligence, repository-aware reasoning, web research, and built-in verification.

kyde★ 84

A native home for coding agents — many Claude Code agents in their own git worktrees with live status, plus a light IDE and Git client to review and land their work. GPU-rendered, Rust, macOS + Linux.

Jan-code-4b★ 83

transformers safetensors qwen3 text-generation agent conversational

illusion-agent★ 83

Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.

pi-desktop★ 83

pi-desktop Minimalist desktop GUI for the Pi coding agent — the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals, and custom themes.

oh-my-kimi★ 82

Verified agent runtime for Kimi Code. Stable daily-use core with alpha orchestration surfaces; release-gated and evidence-gated workflows. | Kimi Code向け検証済みエージェント実行基盤。日常利用コアは安定、オーケストレーション面はalpha。

damocles★ 82

An agentic development environment (ADE) for Windows, macOS and Linux, and a VS Code extension. Chat with Claude, GPT and other models, approve diffs, rewind checkpoints, plan and design before you build, work over SSH, WSL and dev containers, and use persistent memory, subagents, teams and MCP, powered by the Pi agent runtime.

FABULA-LLM-5★ 82

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.

acgo★ 81

acgo is a agent coding tool for golang.

More in Coding agents & developer tools