Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 19 of 44

Codestral-22B-v0.1-abliterated-v3-GGUF★ 11

transformers gguf code text-generation license:other endpoints_compatible

speechless-code-mistral-7B-v1.0-GGUF★ 11

transformers gguf mistral llama-2 code text-generation

fable-coder-35B-A3B★ 11

transformers safetensors qwen3_5_moe image-text-to-text code agentic

Qwen2.5-Coder-3B-GGUF★ 11

gguf code qwen qwen-coder codeqwen text-generation

Qwen3-Coder-30B-A3B-Instruct-8bit★ 11

mlx safetensors qwen3_moe text-generation conversational base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct

Code_LLM★ 11

docker region:us

PunamIDE★ 11

AI-powered native desktop code editor — Tauri 2, React 19, Monaco Editor. Multi-provider AI, agentic tool-calling, technical debt analysis, and full IDE features.

sigma★ 11

Open-source AI coding agent that survives interruptions, runs in a native sandbox, and proves its changes.

coderAI★ 11

A local-first agentic AI coding workspace with Ollama support, project memory, Git integration, streaming code generation, skills, and resumable sessions.

ZenCODE★ 11

Native-Swift coding agent for the terminal and ACP. One binary, no Node runtime — customizable tools, parallel agentic workflows with capability-based model bindings. macOS, Linux, and WSL, down to a Raspberry Pi.

vibecoding-orchestration★ 11

Vibecoding workflow to ship real software: gates G0-G5, contract freeze, multi-agent orchestration. Codex skill + opencode adapter.

ducklab★ 11

Multi-LLM development harness — local-first, test-gated, honest by construction. Requirements→spec→plan→build→review→release with real verification gates; operable by humans, CLI, desktop, or other agents via MCP.

avo★ 11

Open reproduction of NVIDIA's AVO paper (arXiv:2603.24517): evolutionary search where an autonomous coding agent IS the variation operator — Vary(P)=Agent(P,K,f). Runs on the Claude Code or Codex session you already have.

io★ 11

A tiny, self-contained LLM coding agent. One binary, 180+ providers, zero runtime dependencies.

ragent★ 11

Ai coding harness, written in rust with a large number of Model Providers and complex orchistration of LLM agents.

Mazu★ 11

A memory-augmented, checkpointable coding agent — persistent memory, branching checkpoints, and free local model support.

krill★ 11

A native Rust workspace for parallel AI coding agents, with persistent terminal sessions and Git worktrees.

codepilot★ 10

An LLM programming assistant engine built with Go

sofos-code★ 10

Terminal-based AI coding assistant with Claude/OpenAI support, secure local tools, web search, and MCP integrations.

hive★ 10

Hive: A Lightweight Multi-Agent Coding Orchestrator

aget★ 10

AGET Framework - Canonical specification for CLI-based human-AI collaborative coding agents

Spec4★ 10

Spec-driven development for developers. Spec4 AI works with you as a partner and advisor to guide you through a pipeline of six specialized AI agents that turn a rough idea — or an existing codebase — into a complete, phase-by-phase implementation spec, UI mock, and deployment plan ready for your agentic coding tool and infra.

DaveAgent★ 10

DaveAgent is an intelligent AI-powered coding assistant that works in your current directory. It uses AutoGen . Join the discord: https://discord.gg/qFwvrmQN

tinysdlc★ 10

Minimal agent orchestrator for AI coding — 8 SDLC roles, separation of duties, security hardening, multi-channel (MIT)

SIDEVKICK★ 10

SIDEVKICK is a tool designed to assist developers by integrating AI capabilities directly into their local development workflow. It helps with tasks like code editing, refactoring, generation, explanation, and more, using the GenAI models of your choice.

loop★ 10

The open source coding agent.

GenAI★ 10

GenAI harnesses the power of advanced models like GPT-4 and Gemini Pro to serve as versatile coding and writing assistants for users in both R and, soon, Python. This toolbox empowers users with a range of capabilities, including text generation, code optimization, natural language processing, chat assistance, and image interpretation.

EulerAI★ 10

Project Euler GPT Resolver

funcbygpt★ 10

tell the function what to do and gpt will write the code

musa★ 10

🧞‍♀️ Discover AI-generated programming project ideas

gpt-refactor-bot★ 10

Refactor your TypeScript codebase using OpenAI ChatGPT models

headless-agentic-codebase★ 10

Run a coding agent (Claude/Gemini/Codex) 24/7 on your project. Container-isolated, self-merging, GitHub-driven workflow. Bootstrap any project from your phone.

claude-intern★ 10

⚠️ Archived — now DevIntern. Development moved to github.com/getdevintern/devintern. Visit devintern.com

self_learning_ai_framework★ 10

The Self-Learning AI Framework is an autonomous system that analyzes, modifies, and optimizes its own code. It supports natural language interaction, framework creation, code suggestions, PDF-based learning, and package management. Ideal for automating code reviews, agent creation, and AI-driven development.

lauren★ 10

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.

arcane-agents★ 10

Local-first visual control room for terminal-backed AI coding agents. Manage Claude Code, OpenCode, or any CLI agent as characters on a 2D map with live terminal streaming.

symphony-go★ 10

Autonomous agent orchestrator — polls Linear issues, creates workspaces, runs Codex sessions.

Devika-Agentic-AI★ 10

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

opencode-plugin-opencoder★ 10

OpenCode plugin providing autonomous development agents for continuous codebase improvement

Claude-Code★ 10

Claude Code 的恢复源码工程。它包含 CLI 主入口、交互界面、工具系统、命令系统,以及围绕上下文压缩、技能加载、会 话恢复、后台任务和本地服务连接等能力的实现。这份源码当前已经可以完整构建,并能够启动 CLI 构建产物。与此同时,它仍然是一份恢复后的工程,不应被视为官方原始内部仓库;部分能力属于恢复态兼容实现,少数受 fe ature gate 或运行环境影响的路径仍需要按具体场景确认。

phone-a-friend★ 10

CLI relay for AI coding agents. Connect Claude Code, Codex, Gemini, Antigravity, OpenCode, pi, Grok, and Ollama with streaming, persistent sessions, reviews, and multi-model teams.

clio-coder★ 10

Open-source coding agent for scientific software and everyday engineering. Bring your own models, delegate bounded work, and inspect execution records.

forgegod★ 10

Autonomous coding agent with web research (Recon), adversarial plan debate, 5-tier cognitive memory, multi-model routing (Gemini + DeepSeek + Ollama), 24/7 loops, and $0 local mode. Apache 2.0.

kincode★ 10

AI coding assistant in Go. 9MB single binary, zero dependencies. MCP support, Soul files for custom AI personas. 10 built-in tools + sub-agents + web search + memory. The only Claude Code alternative with both MCP and Soul files.

mergecrew★ 10

Open-source agentic SDLC platform: an autonomous product team that ships PRs daily, with a human approval gate before production.

opencoded★ 10

Docker image for OpenCode AI — packaged with Docker Compose, web UI + CLI support, and GHCR publishing workflow. Infrastructure-only repo for running OpenCode in containers.

agentic-delivery-playbook★ 10

Spec first workflow for coding agents: choose the right model per task, use strong reasoning early, split work into smaller tickets, reduce drift, retries, and spend.

agent-workspace-fabric★ 10

Control plane that runs AI coding agents (Codex, Claude Code, Gemini, OpenCode, Grok, Cursor) as disciplined contributors: each task gets an isolated git worktree + Docker Compose stack, profile-driven validation, a created PR, and an autonomous PR-monitor loop (review, CI fixes, base sync, auto-merge). GitHub & BitBucket. Apache-2.0.

momapeer★ 10

适配中国移动MoMA的AI coding

agents★ 10

Minimal coding agents, easy to play with (opencode TUI) and easy to benchmark (ACP on BenchFlow) — built around mini-swe-agent

VibeHarness★ 10

A tiny, dependency-free Ralph-loop agent harness for small local models (VibeThinker-3B via Ollama).

covalo★ 10

Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.

jawcode★ 10

Jawcode (jwc) — coding-agent runner with IPABCD workflow. 46 providers, 3,600+ models, Bun-native.

forge★ 10

Fast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability.

LoopPlane★ 10

Durable local workflows for agent loops: plans, evidence, objective gates, checkpoints, and dashboards for coding agents.

vtx-coding-agent★ 10

Minimalist coding agent harness with a Textual TUI and headless CLI. <1k-token system prompt, 18+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.

Code_Assistant★ 10

streamlit region:us

Qwen3-Coder-30B-A3B-Instruct-MLX-5bit★ 10

transformers safetensors qwen3_moe text-generation mlx conversational

gemma-4-12B-coder-fable5-composer2.5-nvfp4★ 10

mlx safetensors gemma4_unified nvfp4 krill gemma4

VL-1-Coder-Heretic★ 10

transformers safetensors gguf qwen2 text-generation heretic

Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2★ 10

mlx safetensors qwen3_moe text-generation conversational base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct

Qwable-5-27B-Coder-NVFP4★ 10

safetensors qwen3_5 code agentic distillation demonstration

agentica-org_DeepSWE-Preview-GGUF★ 10

gguf text-generation en dataset:R2E-Gym/R2E-Gym-Subset base_model:agentica-org/DeepSWE-Preview base_model:quantized:agentica-org/DeepSWE-Preview

CodeQwen1.5-7B-Chat-GGUF★ 10

gguf chat text-generation en license:other endpoints_compatible

DeepSeek-Coder-V2-Lite-Instruct-IMat-GGUF★ 10

gguf quantized GGUF quantization imat imatrix

Yi-Coder-9B-Chat-GGUF★ 10

gguf mistral quantized 2-bit 3-bit 4-bit

North-Mini-Code-1.0-GGUF★ 10

gguf cohere moe code reasoning agent

OpenCodeAgent★ 10

Claude Code 增强版,支持本地私有化部署,无云端依赖,支持私有化部署;同时适配DeepSeek、通义千问等国产主流大模型,兼顾OpenAI模型兼容,支持中英双语交互,界面与提示中文适配,且会持续迭代更新,优化性能、适配更多模型,部署简单且功能稳定,在保留原版核心Agent能力的基础上进一步扩展实用功能,提升开发体验。

blitzdenk★ 10

The neovim of harnesses. Everything is Lua

Modesto★ 10

Plan, execute, and review coding-agent work in one desktop workspace.

klaussy-desktop★ 10

The agent-first IDE: run a fleet of coding agents (Claude Code, Codex, Gemini, Copilot, Antigravity) across isolated git worktrees, with a commit-time review gate. macOS · Windows · Linux.

xharness★ 10

🤝 装在你电脑上的 AI 编程搭档(macOS GUI + CLI):把项目文件夹丢给它,用聊天布置任务——自动读代码、改代码、跑命令验证,全程可见。支持 DeepSeek / Kimi / 任意 Anthropic 兼容模型;截图粘贴看图干活;技能系统;数据全本地。

atman★ 10

A flow-driven AI coding agent runtime. Write agent workflows in the .at DSL — Turing-complete, inspectable, deterministic. The LLM is one node; atman orchestrates the rest.

RxyCode★ 10

RxyCode is a local multi-agent for real work, not just code. 本地多智能体,能干的不只是写代码。

ai-generate-code★ 10

Evidence-driven AI software synthesis and verifiable artifact delivery platform with stateful orchestration, layered memory, hybrid retrieval, build validation, and reproducible deployment.

agent-harness-skills★ 10

Turn real software repos into agent-ready engineering environments with entrypoints, validation, evidence, and delivery records.

g023code★ 10

Pure-Python AI coding agent powered by DeepSeek V4 - Subagent-First architecture · Context is Currency · Terminal-native - Can connect Ollama models for Vision support - Uses the native web search built into DS v4 API and is built around the DeepSeek caching mechanism

sinclair★ 10

The terminal your agent team lives in — run coding agents in panes on a shared bus, on a fast GPU-rendered terminal for macOS and Linux.

euler★ 10

Euler is a research agent (coding agent included) and an open-ended runtime-extensible platform.

SapBuddy★ 10

sap abap ai agent cli

mini-pi★ 10

A minimal Coding Agent Harness inspired by Pi, built to study and validate Agent Runtime/Harness abstractions through executable demos and real LLM experiments.

openbot★ 10

Local-first multi-agent desktop workspace powered by Codex App Server.

pi-agent★ 10

A minimal terminal AI coding agent — LLM tool-use loop with sandboxed file/shell tools

heartwood★ 10

Compliance-first coding harness for working with sensitive biomedical research data.

otto-code★ 10

Agentic coding with personality, for every model, cloud or local

gptel-agent-harness★ 10

An execution harness for gptel-agent that adds reliable, autonomous coding-agent behavior.

vincent★ 10

Local-first orchestrator for AI coding-agent workloads

pdd★ 10

Product-Driven Development for coding agents

codegate-leader★ 10

Local-first technical leader workspace for reliable Coding Agent planning, handoff, evidence review, and FPGA competition workflows.

reve★ 10

The directory is the agent: durable Ruby coding agents in mandatory microsandbox microVMs

remote-agent-server★ 10

把 Claude Code、Codex 和 Hermes 接入工单、CI 与业务系统。自托管 Agent 执行服务,提供 Web 管理台、异步任务 API、独立工作区和结果回调。Self-hosted agent execution with a web console, async task API, isolated workspaces and signed webhooks.

BlackPearl-CodingAgent★ 10

BlackPearl — DeepSeek-powered AI agent harness and orchestration ecosystem with 286+ skills, 273+ specialist agents, plugins, security, QA and automation.

clidable★ 10

CLI coding agents for everyone — checkpoints, preview, plugin/skill/MCP management, AI teams.

spine★ 10

Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).

RunWhale★ 10

A coding agent that brings the full development loop to your phone — code, run, test, and iterate from anywhere.

Astera★ 10

Desktop app for running and orchestrating many Claude Code and Codex sessions — account rolling on usage limits, git worktree isolation, and Slack remote control.

Aether-Agent★ 10

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

forge-ai★ 10

Forge is a Multi-Agent AI Coding Orchestrator that unifies multiple AI coding assistants (Claude, Gemini, Antigravity, GitHub Copilot) into a single autonomous build system. It enables users to dispatch tasks to multiple AI agents simultaneously, orchestrate their collaboration through various patterns, and run full autonomous builds...

fable-jev★ 10

⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

agent-campus★ 10

A pixel-art mission control for your Claude Code agents — every project is an office, every agent is a character

More in Coding agents & developer tools