Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 28 of 44
A native Android remote control for OpenCode. Run the agent on your development machine. Control it from your phone.
A Rust reimplementation of mini-swe-agent with CLI task execution, benchmark runners, trajectory inspection, and multi-environment support.
The autonomous local-first coding agent powered by a mutable DAG state-machine for highly reliable, macro-level architectural engineering.
Autonomous multi-agent software factory with parallel task dispatch, Kanban pipeline, isolated Git worktrees, and automated code review.
gguf qwen qwen3 coder text-generation GGUF
The AI software factory for your team: specs go in, reviewed and tested pull requests come out. An assembly line of agents (research → specify → plan → tasks → implement → review → verify → deliver) with human gates, on GitHub Spec Kit and the Pi Coding Agent SDK, following AIDLC. GitHub/Jira/Confluence/Linear/Slack integrations.
Ustam — one local hub for Codex, Claude Code, OpenCode and Antigravity. Project teams, protected installation and bounded work review. English / Türkçe.
Xynapse / clickncode — a Windows IDE built on Code - OSS with an AI coding assistant, Git, terminal and BVC planning.
Multi-provider coding agent harness built on Pi.
Windows operator workbench for running many AI coding agents across many projects with SAIPEN continuation, scheduling, workers, and routing.
Plan-native execution harness for AI coding agents: intent-to-contract synthesis, bounded delegation, durable handoff, and evidence-based acceptance.
✨Local coding agent powered by Ollama.
A minimalistic AI coding agent in 62 lines of bash, curl and jq. Step-by-step tutorial: LLM call → chat loop → tool-calling harness that writes and runs a Tetris game.
A TypeSafe-native (Jev) coding agent built on Recursive LLM Context Decomposition (RLCD), with a native macOS client
A TUI agent harness with multi-session support and Vim-style keybinds.
Harness-first fork of jcode with embedded skills, local memory, safety gates, ACP/API orchestration, and multi-agent workflows
Native Windows AI workbench for office work, research and code: an agent that edits files and runs commands, with an editor, Office and PDF previews, WSL and SSH remote development, and MCP.
在 MATLAB 中用 AI 生成、解释和修改代码,预览差异后应用。支持首次配置向导与多 Agent 后端。
Local-first (Private) AI coding tool, specifically for low VRAM (~6gb). Understands your codebase structurally, and edits with precision
Free Agentic coding tool on a free ChatGPT account. A VS Code extension + browser extension that lets ChatGPT read your GitHub repo, apply its edits, check them and iterate — no API keys no payment.
Cross-platform, secure AI coding agent. Bring your own model; every action is approval-gated and sandboxed.
Talk to your background coding agents from your phone - every long-running AI agent gets its own chat channel, with voice-first control and durable identity across restarts
ELENVA Web —— pi coding agent 的 Web 工作台(个人控制台,自用优先,非 IDE 前端)
Microsoft FrogNano 4B: The Tiny AI Coding Agent That Fixes Your Code Locally - An automated self-healing Python agent that detects Pygame crashes and fixes code locally.
Grok Build Desktop — a local-first AI coding agent for Ollama, built with Tauri, React, Rust, and TypeScript.
Unattended GitHub issue-to-PR worker running Claude, Codex & DeepSeek inside a strict containment boundary 🤙🏼
CUELO — open-source AI coding agent workspace and harness for omp (oh-my-pi). Multi-agent orchestration, model routing, sessions, skills and worktrees.
Orchestrated, parallel successor to Matt Pocock's /implement skill, for the pi coding agent: turns a spec + ticket graph into a reviewed, tested branch — parallel coders in isolated worktrees, per-ticket two-axis review, integration-test gate, final whole-branch review
Local AI system that turns ideas into working software projects using multi-agent pipelines running entirely on your own hardware.
A 3D control room for developers who run many AI coding agent sessions at once.
A personal experiment to learn: a coding agent in plain Java. No framework, no API key, runs on a local model.
Local coordination for parallel coding agents: scoped claims, isolated Git worktrees, shared resources and verified integration. MCP + VS Code/Cursor extensions. No hosted service.
gradio region:us
Local web workstation for the pi coding agent: resident sessions, live tool streams, PWA on your phone.
Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.
Terminal kanban board that orchestrates Claude Code and Codex agents: one agent per ticket, each in its own git worktree, and a card lights when one needs you
Multi-model AI agent stack: one model builds, another model lineage reviews. Runs Claude Code, Codex, Gemini, Grok, Kimi & more on your own CLI subscriptions. 60+ skills, task graphs, agent messaging, shared memory.
Shadow agents for autonomous code work - a local-first agentic work orchestrator
Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.
An issue-driven AI coding agent for reliable GitHub execution with plan-first orchestration and validator-gated completion.
A standalone desktop workspace for Ask, Plan, and Agent workflows, built on GitHub Models and the Copilot SDK.
O IDE onde a IA programa por ti. Chat-first, diffs ao vivo, pré-visualização em tempo real.
AI-powered agent that translates natural language into validated, benchmarked AVX2 intrinsics. Compiles and stress-tests generated C++ against a scalar reference, with an agentic retry loop on compiler errors and semantic mismatches. Built with Gemini, FastAPI, and deployed on Google Cloud Run.
Create high-grade software at speed with AI agent
Issue/PR-driven autonomous development system for GitHub, built with FastAPI, agent workers, and local/runtime automation.
AI Development Agent - Multi-Agent Software Development System A comprehensive multi-agent system that transforms project descriptions into complete, deployable applications using various AI technologies. Features configurable specialized agents working.
spec driven automatic development
Exploring AI-driven development with CodeSynthAI: An open-source project leveraging LLMs for automated coding through a collaborative multi-agent system
6 AI agents collaborate to build complete web applications in minutes. CrewAI-powered software development team that generates FastAPI backends, responsive frontends, tests, and deployment configs - demonstrating 95% automation with human oversight for the final 5%.
Provider-agnostic multi-agent coding orchestrator in Go. Unified router for any LLM provider (Ollama local+cloud, OpenAI, Anthropic, Google Gemini) with role-based model assignment, fallback chains, and cost tracking. Inspired by gastown and LiteLLM.
Bridge any chatbot to any AI coding agent via Linear — flip a ticket to "AI Implementation" and the executor runs your chosen CLI (claude / opencode / codex / gemini / forge) in a worktree; results post back as Linear comments.
CLI for AI coding agents: persistent tasks, memory, events, and deterministic resume across crashes and session resets.
🐣 TinyAgent that thinks in python and execute it in the cloud with extendable hooks
CLI that runs builder, validation, and independent reviewer agents in a bounded loop for local AI coding workflows.
An intelligent coding agent that understands your codebase, fixes bugs, refactors code, and explains architecture.
Sistema de desenvolvimento de software orientado por agentes de IA que automatiza e coordena todo o ciclo de vida do desenvolvimento.
CLI for managing tmux sessions running AI coding agents
Agentic AI Orchestrator and coding agent for business-as-code platforms, services, and data. Focused on streamlining development for startups and small business who want to own their own cloud.
Before there was CLUADE CODE - I wrote this similar tool. Leverage LLM-API to translate high level YAML requirements into function/unit-tested applicaiton
Archived: no longer maintained. 🤖 AI code assistant built for speed - zero-overhead tRPC communication with real-time streaming
CLI-based AI coding assistant using AWS Bedrock and Claude models. Features interactive mode, file context, git integration, web search, and image analysis.
AI-powered desktop coding assistant built with Tauri (Rust + React) and Gemini API. Features 50+ skills, 10 subagents, 23 MCP connectors, and multi-provider AI support.
⚡ High-performance AI coding agent for the terminal, built in modern C++23. Multi-provider LLM support (Anthropic, OpenAI, Ollama), 9 built-in tools, interactive REPL, and session persistence.
τέλεια — minimal TUI coding agent. Streams chat over Ollama / Anthropic / OpenAI, runs read/write/edit/bash, persists sessions to SQLite. (Rewritten in Rust btw)
Autonomous Software Development Orchestration - AI-powered development system using PRPs and autonomous agent coordination
🤖 AI-Powered Backend Builder Multi-agent + multi-tool system using AutoGen, Gemini & Groq to automate production-ready backend development. Features 4 specialized AI agents, MCP integration, and end-to-end automation. Perfect for rapid API development with built-in security & testing. 🔧 Tech: Python, AutoGen, Gemini, Groq, MCP, FastAPI, Docker
Sandbox-isolated multi-agent coding CLI. Run AI-generated code safely in Docker or true microVMs with built-in persona debate.
SynthCode — the open-source Claude Code alternative. Battle-tested agent framework, model-agnostic, TypeScript-first, MIT licensed.
AI agents that will oversee, manage and direct the main coding agent allowing you to code while you sleep
Small TUI coding agent in Go for any OpenAI-compatible endpoint. Built-in read/write/edit/bash/grep/web_fetch tools, sandboxed shell, SQLite session persistence.
AI Engineer: A multi-provider AI coding assistant with function calling, supporting DeepSeek and OpenRouter. Features include intelligent file operations, code analysis, and dynamic model switching for optimal development workflows.
Evidence-backed execution harness for AI coding agents: plans, gates, artifacts, codebase memory, learning loop, and verified claims.
Desktop AI loop orchestrator that drives open source coding CLIs (Claude Code, Codex, Cursor, Gemini, OpenCode) through PRDs and user stories until every story passes.
Multi-Agent Code Generation System — LangGraph + Groq + Tavily + LangSmith
AI-powered IDE featuring intelligent coding agents, auto-suggestions, quick edits, and modern developer tools for a faster and smarter coding experience.
An autonomous AI agent daemon — picks up tasks, executes them, validates the output, and commits results.
A coding agent that edits real repos with workspace tools (read/write/search/run), produces JSON traces with token accounting, and renders runs on a live dashboard.
A self-evolving scaffold for autonomous web projects. 9 workflows, hourly self-evolution, self-healing pipeline, feedback learning loop. The repo is the system.
digital employee that lives in your terminal. It autonomously plans, researches, codes, debugs, browses the web, manages DevOps, and remembers
Build Your Own AI Coding Army 2026 – Multi-Agent Dev Kit for Copilot, Cursor & Codex 🚀
Autonomous AI dev factory: sandboxed Claude Code agents design, build, review, and ship features across repos — supervised by a FastAPI PM dashboard. Experimental.
Build production-ready software from a description. A multi-agent engineering framework for any language, any stack.
Archived Grawkus NHE 3.0.0 base: Grawkus-branded fork of Agentic Harness Engineering
13 autonomous AI deities running a spec-driven development pipeline inside pi - from vague idea to shipped release.
the agentic coding harness
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.
Vibe Coding Revolution: Code 46x Faster & 98% Cheaper!
One person. Any project. Production-ready output.
ToCodex Community — a maintained open-source AI coding agent for VS Code, evolved from Roo Code.
Your AI agents write code; SPS makes sure it ships. An AI-driven dev pipeline orchestrator built on Claude Code - kanban-driven, persistent memory, per-project Wiki.
Local dashboard for running multiple AI coding agents in parallel. Claude Code + Codex, agent-agnostic, keyboard-first.
💖 Support Creator: https://pages.razorpay.com/pl_T1zknR655GpRoS/view — Turn a free NVIDIA NIM API key into a private, autonomous coding agent: plans, writes & runs code, and drives a real Chrome browser live in an on-screen Agent Computer. 100% local on macOS & Windows. One-command install. 💖 Please support the creator!
A hands-on tutorial for building a Claude Code-style coding agent with tools, memory, hooks, subagents, and plugins.
A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
gradio mcp-server-track agent-demo-track mcp-server region:us
docker region:us
gradio region:us