Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 11 of 44
Local-first desktop app that orchestrates AI coding agents in parallel — work items, git worktrees, dependency tracking, and review workflow in one window.
auto-rust is an experimental project that automatically generate Rust code with LLM (Large Language Models) during compilation, utilizing procedural macros.
The AI assistant that seamlessly integrates with VSCode to autonomously create, edit, and run terminal commands; redefining how you code.
A Pi-Agent extension that supervises the coding agent and steers it toward a defined outcome.
Agentless Lite: RAG-based SWE-Bench software engineering scaffold
AI coding agent with more freedom.
A desktop coding agent built with Mastracode and Electron.
Opinionated Rails AI agent system
a TypeScript-based CLI coding agent built with OpenAI SDK and Ink
AI Agent驱动的Claude code 软件开发工作流框架 — 让AI Agent协作完成软件全流程开发。自动生成PRD、架构设计、源码、教程,实现"描述即交付"。
Code paid die,which means 'Kill The Paid AI Coding Agent'. Turn ChatGPT, Gemini, Kimi, or any AI into a free local coding environment. Read, write, code on your machine — no Codex, no MCP, no ban risk. Works with any platform that supports custom tool calling.
transformers safetensors qwen2 text-generation code chat
TUI for agentic code orchestration
The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel, darwin, and redblue behind a promotion gate that never merges.
A lightweight coding agent 🧑💻 built from scratch, with tool calling, session persistence, workspace context, memory, and multi-provider LLM support 🛠️.
AiNxt CLI is an open-source AI coding agent that brings AI-powered software development directly to the terminal. It can understand code, build features, fix issues, automate tasks and execute commands using the AI models and providers chosen by the developer.
Agentic development environment for pi
Disk-backed pipeline that takes AI coding agents from raw idea to shipped code — gated phases, orchestrated subagent builds, and crash-proof state, from a single milestone to a full multi-milestone program.
An agent process for building software meant to last
A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors and automation.
A meta-harness for coding agents to follow proper Software Development Lifecycle practices. Can also write code from specs. Based on literate programming ideas from Donald Knuth
A Claude-Code-like CLI coding agent scaffold (TypeScript + oclif)
Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do.
Multi Agent Worktrees: run your agent automatically in a separate worktree that's merged at the end.
[Experimental] A coding agent for RStudio
Ouro is an open-source AI agent — run it as a Coding agent CLI or deploy it as a bot just like JARVIS.
Desktop IDE for working with multiple AI coding agents. Supports Claude, Codex, OpenCode, Cursor and Grok.
Tool-agnostic 13-phase AI development pipeline — turns a task description into reviewed, committed code through automated design, adversarial review, security, test, and code-review gates. One bash engine, balanced Opus/Sonnet routing, self-healing commit review.
Angles Code CLI — Terminal-based agentic coding assistant
NeoCode is a terminal based AI coding agent IDE
Open-source AI agent and cross-platform client for local and remote development workflows.
Tree-first orchestration TUI for pi coding agents: run many pi sessions in parallel, keep them alive in the background 🌲
A CLI-based coding agent similar to Claude Code.
An editor to remember everything with human-brain like memory system powered by a built-in coding agent.
Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.
One unified CLI for headless coding agent execution 🤖
基于PiAgent的一个本地优先、轻量流畅的多 Agent 可远程操控的桌面工作台。
The multi-agent ADE: all your agents working at once, each on its own branch. Claude Code, Codex, opencode or the agent you already use, each in its own worktree, all in one window.
A privacy-first local coding agent that consults frontier AI models without exposing your source code.
moon agent rewritten in async
A platform evolution of OpenAI Symphony (openai/symphony) for running Codex, Claude Code, CodeBuddy Code, and OpenCode from real project tasks.
AI-powered terminal coding agent in Rust — TUI, BAML agent loop, fuzzy search, tmux background tasks, skills, MCP support
A pair of OpenCode agents that turn Matt Pocock's skill-driven workflow into a grill/plan/dispatch pipeline with parallel TDD workers on git worktrees.
An Orchestrate multiple coding agent desktop app
Lightweight, non-intrusive, yet versatile ADE. Run Claude Code, Codex and Antigravity side by side in one native Mac app, with no hooks, no wrappers and nothing written into their settings.
transformers safetensors llama text-generation arxiv:2403.04652 license:apache-2.0
minimalist/toy terminal agent harness written in bash
Open-source AI coding agent CLI with multi-provider support, local models, MCP, and specialized AI agents.
An Emacs Lisp AI coding agent with multi-agent architecture, permission-based tool access, and LLM integration via gptel.
small coding agent in go
Plan, run, and track AI coding work feature by feature—with local Markdown cards, diagrams and Git worktrees.
Dure — every coding agent, one workspace across desktop and mobile.
Recursive Language Model extension for Pi coding agent
一个面向本地代码项目的桌面 Agent 工作台,把 Claude Code、OpenCode 和 Codex 放进同一套桌宠式界面里。
Agent Smith — the open source agentic software factory: ticket in, spec, verified pull request out. Self-hosted; Azure DevOps, GitHub, GitLab, Jira.
coding agent
The next easy code and work AI agents harness system: auto, asynchronous, concurrency, efficiently and High accuracy
Small, modular coding-agent harness for Node.js
Privacy-First AI IDE - Autonomous Agentic AI, Local LLMs, and Encrypted Real-Time Collaboration
Run AI coding agents like Cursor, Windsurf, and Claude Code via code and let them implement features all the way to a pull request
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
D.U.H. — D.U.H is a Universal Harness. Provider-agnostic AI coding agent.
Manim Coding Agent
Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your own Claude, GPT or Gemini keys. No account, no subscription. 🇮🇳
Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right where the code lives. It increases productivity, reduces implementation errors, and helps keep changes aligned with the project’s intended design.
Gaster Code: public local AI coding assistant with CLI, desktop app, MCP, Skills, Agents, and signed installers
transformers safetensors qwen3_next text-generation qwen3 moe
transformers safetensors qwen3_next text-generation unsloth qwen
transformers pytorch codegen text-generation custom_code arxiv:2305.02309
gradio region:us
mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next
Unofficial lab for the OpenCode AI agent: recipes, benchmarks, experiments, and tricks.
A minimal local coding agent built on the CloudWeGo eino framework — the framework-variant sibling of mini-coding-agent-go.
Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯
Privacy-First AI IDE - Autonomous Agentic AI, Local LLMs, and Encrypted Real-Time Collaboration
AiNxt Code is an open-source AI coding agent for VS Code and JetBrains IDEs that brings AI-powered development directly into the developer’s workflow. It helps developers understand, write, modify and improve code through an agent-based experience powered by the Agent Client Protocol (ACP).
Autonomous AI Dev Team On Coder
A live 3D office for your coding agents. Every agent gets a character and a desk; every team gets an office. Works with Claude Code, Codex, Cursor and anything that speaks HTTP.
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.
Privacy-First AI IDE - Autonomous Agentic AI, Local LLMs, and Encrypted Real-Time Collaboration
Lightweight coding agent that runs in your terminal
CarryCode is a terminal-native AI coding agent that helps you write, refactor, debug, and understand code — all through natural conversation. It connects to 17+ LLM providers, supports the MCP protocol for extensibility, and delivers a beautiful terminal UI with themes, syntax highlighting, and code diff previews.
A terminal coding agent for real project work.
A local-first, CLI-driven multi-agent AI software engineering workflow orchestrator with feed specs, PRDs, and guidelines to auto-generate implementation plans and code.
A fully automated coding agent powered by GitHub Copilot CLI and GitLab CI/CD.
AI-native development environment for orchestrating agents
Local semantic copilot and governed agent engineering runtime for AI-assisted software delivery.
CarryCode is a terminal-native AI coding agent that helps you write, refactor, debug, and understand code — all through natural conversation. It connects to 17+ LLM providers, supports the MCP protocol for extensibility, and delivers a beautiful terminal UI with themes, syntax highlighting, and code diff previews.
CyCode is a lightweight AI coding agent that runs in your terminal. It uses an OpenAI-compatible Chat Completions API and provides built-in tools for reading files, applying precise edits, searching code, running shell commands, and delegating work to sub-agents.
OneCode 是一个参考Claude Code实现的Code Agent。它用可控的工程框架约束大模型完成编码任务。它的主循环采用 Hooks 机制实现扩展,通过上下文工程与工具调用支撑任务;运行状态可中断、可恢复,并提供结构化的 trace 与 error log 用于观测与回放。可用于学习与二次开发。
OpenBrowser is free local AI coding agent — use your ChatGPT, Claude, or Gemini browser subscription. No API keys. CLI + Chrome extension bridge.
Dual-AI-agent collaborative coding orchestrator
OhMyPi (OMP) Agent Framework Spec-Driven Development infrastructure for Oh My Pi. Skills transform artifacts through a deterministic engineering workflow.
NOW you can let AI agents make code changes without losing engineering control.
Spec-driven DDD framework for AI coding assistants
Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.
A multi-model CLI coding agent for terminal-first teams
No long blocks of time? Run an AI team from your phone. Open-source, local: Git worktree sessions, task contracts and verification gates for Claude Code, Codex, Gemini CLI, Copilot, OpenCode, Antigravity and Command Code.
Navide is an open-source Agentic Development Environment (ADE) that orchestrates AI software teams across the software development lifecycle. Coordinate AI agents, workflows, context, and human collaboration from idea to deployment.