Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 22 of 44
Practical AI agent swarm: 6–15+ parallel coding agents in Docker with isolated git branches. 500–800 commits/day, massive test coverage gains. Clean, safe, no worktrees. Battle-tested on 100k+ LOC codebases.
Streamlined Development with AI An all-in-one platform integrating LLMs for code generation, reviews, documentation, testing, profiling, and security scanning. Features a Streamlit interface with vector-based indexing using Hugging Face and LlamaIndex for efficient, context-aware operations.
An terminal based (IRC-style) LLM-powered coding tool
A Docker-based Ralph Wiggum loop featuring a 3-tier review system, multi-provider support, automatic provider fallback, role escalation, task mode with dependency tracking, and steering guidance.
Autonomous AI development pipeline powered by Claude -- ships reviewed PRs from your backlog or generates cross-repo specs.
✊ Let your agent grind on your projects 24x7 fully autonomously
automated issue to code diff generator
Your CLI coding agent shouldn't need a babysitter. cliclaw is a tool-agnostic meta-agent that runs Claude Code, Codex, or any TUI agent in parallel through tmux — clearing confirmations, remembering across sessions, scaling out.
north-starr is your AI development partner
Telegram bot that uses AI to generate full codebases from user prompts, providing structured, ready-to-deploy software projects, differentiating from simple code generation by offering entire architectural solutions.
An AI coding assistant - agentic loop, tool calls, guardrails, reminders, terminal TUI.
A basic, hackable AI code editor inspired by Cursor. Monaco + Claude + ~600 lines of JS, no build step.
AI coding agents should work in attempts, not your working tree
A modular, open-source AI Developer Assistant designed to automate, accelerate, and improve the software development lifecycle. This command-line tool helps developers review, understand, document, refactor, test, and secure code using AI models while maintaining privacy, extensibility, and open access.
🧬 RAGIX: Local-first development assistant making LLMs behave like disciplined engineers – Unix-RAG retrieval, sandboxed execution, MCP-compatible, fully auditable
An unofficial fork of OpenAI Codex with multi-account ChatGPT and one-command local models via LM Studio. Save every plan, hop between them mid-task, fall back to a model on your own machine when you want to.
Local, privacy-first agentic coding workspace in Go. CodeDone breaks large dev tasks into atomic serialized tickets, dispatches AI implementers one step at a time, and uses a Contre-Maître system to plan, supervise, review, and finalize work with lower token waste and higher reliability. Built to excel at very long tasks spanning multiple days.
Native macOS workspace for AI-driven development. Graph, code, and terminal in one window.
Local coding agent for Ollama that saves your Claude Code / Codex tokens: your paid agent writes a short brief, Nedster runs the read-edit-test loop on your GPU and returns a JSON outcome backed by real test runs. Offline, no account, Windows/macOS/Linux.
Fast, lightweight, cross-platform IDE built with C++17 and Qt 6. AI assistant, LSP intelligence, integrated terminal, Git — native performance, no Electron.
Autonomous coding-agent task runner — queue work and Lea runs it headlessly with Claude Code or Codex the moment your limit resets. Menu-bar app on macOS, a real windowed app on Windows/Linux. MIT.
Sleek, fast, token-efficient AI coding agent. Multi-provider (Cortex, OpenAI, Anthropic, Ollama) with a polished terminal UI. Fork of vix.
CLI coding agent สไตล์ Claude Code — Claude API / Cloud / Ollama / llama.cpp, 42 skills, single-file
Xcoder — 超越人类与 AI 边界的 AI 编程 CLI | AI coding assistant that pushes beyond the boundary between human and AI
Open-source, local-first AI coding agent for developers who want control. Use any model, inspect every action, review diffs, run commands safely, and keep your code under your rules.
MOVED to github.com/professorpalmer/marionette -- this repo is archived. Marionette: a desktop AI coding harness over Puppetmaster durable state.
5 AI agents that turn GitHub Issues into mergeable PRs — from architecture to passing tests, fully autonomous.
AI-Powered Software Development tool — Multi-Methodology, CLI based
Run your AI coding tool through a 18-stage dev pipeline. Multi-host across Claude Code, Codex, Gemini CLI and OpenAI API compatible endpoints. Artifacts and gates on disk, not a chat log.
CoderChat is an alternative to tools such as Void, Cursor, Qoder, Trae, and CodeBuddy.The core goal of this project is to benchmark the most user-friendly agent technology, reject token premium, and experience the charm of AI programming with the lowest token cost.
Agentic coding CLI for a-Shell
Codex Orchestrator for Codex App: Loop Engineering with worktree sessions, heartbeat monitoring, persistent ledger, review routines, and evidence-label gates.
Open-source agentic substrate for AECO. Apps are text. AI is the runtime.
opinionated agent neutral scaffold for new projects
面向复杂软件工作的闭环协调层 ,把专家路由 · 计划 · 执行 · 迭代 · Beta · Release · Feedback 收拢成一个可持续迭代的闭环工作流
transformers safetensors qwen3 text-generation code jupyter
transformers safetensors qwen2 text-generation code codeqwen
transformers safetensors deepseek_v2 text-generation fp8 vllm
transformers safetensors qwen2 text-generation unsloth code
transformers gguf code granite text-generation dataset:bigcode/commitpackft
transformers gguf code codeqwen chat qwen
gguf conversational chat code agent text-generation
Let the Orcha play. — AI-driven Feishu coding agent: one @-mention → autonomous plan/code/test/review/push to a new git branch.
Open-source coding agent that produces tamper-evident, CI-verifiable proof for every code change
Where intent meets code — a local AI coding agent
Turn your ChatGPT account into a local software factory. Four browser tabs plan, write, review and audit real projects, then install, run and screenshot them. No API key.
The open source agent.
A fast, model-agnostic coding agent for your terminal — built in Rust with a rich TUI, MCP, lossless context, safe tools, and built-in verification.
A super-fast, ram-efficient, and lightweight agentic code editor that's ready to ship your code to the next level!
Choreographic coding agents runtime
Sovereign, local-first terminal AI coding agent with approval gates, model-agnostic, and real GitHub workflows.
Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.
Orchestration kernel for autonomous software development — crash-only multi-agent coordination on git and plain text, fail-closed verification gates, self-learning guardrails.
Local-first agent IDE for steering Codex, Claude Code, OpenCode, and local models with visible review.
A virtual software company for Claude Code: 19 agents, 38 workflows, 16 quality gates. Takes an application project from idea to release.
Local-first, event-driven AI software factory for building, modernizing, debugging, securing, porting, validating, and optimizing applications through task-activated specialist agents, multi-provider model routing, isolated workspaces, runtime QC, and audit-ready evidence.
A lightweight native macOS desktop app / GUI for Pi Coding Agent, built with SwiftUI. Pi Coding Agent 原生桌面端,支持 AI 编程、技能扩展与定时任务。
A coding agent that jails model commands and uses editable state machines for long-running tasks
IssueClaw is a self-hosted AI coding assistant that lives entirely within your GitHub repository. By simply opening an Issue, you can chat with an AI, generate code, fix bugs, and automate tasks. It features persistent git-backed memory and runs entirely on GitHub Actions - meaning zero servers, zero databases, and zero monthly costs.
AI 桌面代码编辑器:支持多平台 LLM、Agent 工作流与可编辑的对话历史。AI-powered desktop code editor with multi-provider LLM support, agentic workflows, and editable chat history.
Demo project for agentic AI software engineering
Vinci Code CLI — a terminal coding agent you can run with your own provider key (OpenAI, Anthropic, OpenRouter, and more). A distribution of Pi. MIT.
A open sourced code editor(proposing to integrate with AI) using Qt/C++ and Rust, no trackers, no big companies, 100% pure IDE
Terminal-native multi-agent AI coding harness in Rust
From task to done. One open source workflow of 18 modules for AI coding agents that runs the AI-native SDLC: plan, design, build, test, deploy, maintain, with evidence in every handoff. Free, MIT.
Lean terminal coding agent in Python. Plan/build REPL, 15+ LLM providers, subagents, checkpoints, and headless CI runs.
A programmable AI agent harness built in Rust and configured with Lua. Create custom coding agents with a terminal UI, multi-provider LLM support, MCP tools, persistent sessions, and an extensible plugin system.
Multi-agent orchestration setup for OpenAI Codex: a root orchestrator with scout, builder, verifier, scholar and critic subagents. Pro, Plus and Lite plans.
🦖 Four AI coding CLIs (Claude, Codex, Kimi, Gemini) debate a task, reach consensus, and combine to build it — using your subscriptions, not API keys.
Fast local development workspace with AI built in.
Local-first terminal mission control for Claude Code, OpenAI Codex CLI, Gemini CLI and OpenCode. Run AI coding agents in parallel tmux sessions, manage direct SSH connections, monitor usage and continue securely from phone via Tailscale. No ComandOS cloud, hosted database, telemetry or SSH proxy.
A terminal AI coding agent with a streaming TUI — multi-agent fan-out, LSP-powered fast inner loop, pull-based repo context, approval guardrails. One-line install on macOS / Linux / Windows. Rust + MIT, built on the phi-agent framework.
From vibe coding to production code. A senior engineering team's process, ready-made: AI agents design, plan, build, review, fix and ship your features. Battle-tested over >1,000 commits. Works with Claude, Cursor, Codex, Antigravity and opencode.
One command from “I want X” to a merged PR.
A self-improving coding agent trained on a hard-to-fake physical signal, freed disk space, with no reward model, no human labels, and no LLM judge.
Desktop app to run Claude Code, Codex, Gemini CLI and OpenCode side by side, with a shared task board and memory over MCP, an orchestrator that runs workers in git worktrees, and Hangar Mobile to follow and steer them from your phone. Local, open source.
A self-hosted workspace where a small team and its AI agents build software together, on one Linux server you own. Claude Code sessions, shared projects, tasks, services and native apps.
docker region:us
SWE-Ladder: Learning to Localize, Reproduce, and Patch via Progressive Privileged Self-Distillation.
A local-first multi-agent coding harness that connects model providers and ACP agents, binds them to specialized roles, and coordinates them in a shared session.
A desktop ai coding harness for local models focused on research and coding.
Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from
An autonomous AI agent
CLI coding agent that runs in your terminal
Agent-agnostic unattended development orchestrator. Plan interactively, execute autonomously, review results.
auto-generate 业务代码脚手架
An advanced, local-first agentic CLI coding assistant. Features a multi-agent Tribunal review system and deep semantic indexing for safe, memory-efficient refactoring.
Sysclone: A purist, dependency-free Universal Interpreter and JIT compiler built entirely in JavaScript. Currently executing MS-DOS QBasic with absolute fidelity.
tmux for AI Agents — Orchestrate multiple AI coding agents (Codex, Gemini, Claude) in parallel with one command.
Command-line ADE tooling to run multiple Claude Code/AI agents in parallel - each in its own isolated git worktree. Spawn, manage, and orchestrate AI-powered development across concurrent tasks without stepping on your own changes.
Code sample repo to demo how Kiro can be used to migrate large codebases and working with such repos using Kiro spec-driven development approach.
The ultimate coding assistant you'll ever need, powered by OpenAI
Stuck While Coding? CoderClue Can Help You Out. CoderClue is Built Using OpenAI and It is very useful in day to day life of a programmer.
Autonomous coding agent — queue tasks, schedule jobs, and let Claude Code execute them in isolated git worktrees while you sleep
Zing plans, builds, tests, and ships clean code with AI. Zing keeps you in charge at each step. This is the Zen of Zing.
Local pre-write containment & structural scoring for AI coding agents: deterministic policy, Mamba-3 SSM coherence, and local Laya multi-file triage.
Autonomous coding agent orchestration. Give it a goal, walk away, come back to finished work. Eval loops, multi-agent pipelines, DAG dependencies, crash-proof persistence.
CodeNova an Ultimate Gen AI project with multiple features that helps developers to get their job ready and also ensure their to help in production level
GO-CODE is a terminal-based AI coding agent. It helps you automate coding tasks, execute shell commands, and manage files directly from your terminal. GO-CODE is designed for developers who want to interact with their codebase and operating system efficiently using natural language.
Spec, plan, and build with AI agents — with enforced guarantees.