Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 18 of 44
Mobile remote control for AI coding agents on your own computer. Works with Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent CLI, GitHub Copilot CLI, Kimi Code, Qwen Code, Kiro CLI, Google Antigravity, CodeBuddy Code, Cline CLI, Trae Agent, CodeFuse Agent, DeepSeek Harness, Pi, OpenClaw and Hermes Agent.
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
🐯Autonomous dev orchestration that never stops. Failures still converge to completion.
A clean-room Go implementation of agentic coding harness patterns, derived from analyzing production AI agent architectures. Built for learning, extending, and teaching how to build coding agents like Claude Code, OpenCode, and Gemini CLI. Supports OpenRouter and Anthropic out of the box.
Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol
Antigravity Architect is the definitive Agent-First project engine. It is a modular, zero-dependency Python package that generates Living Repositories—complete development environments designed from the ground up to be self-describing, self-protecting, and self-evolving for AI coding agents like Gemini, Claude, and GPT-4.
The Agentic Development Environment You Need.
transformers safetensors qwen2 text-generation unsloth code
transformers safetensors mistral text-generation code license:other
gguf gemma4 coding code reasoning thinking
transformers gguf llama-cpp gguf-my-repo text-generation base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct
transformers safetensors qwen3_5_moe image-text-to-text text-generation-inference unsloth
gguf code codeqwen chat qwen qwen-coder
transformers safetensors qwen2 text-generation unsloth code
transformers safetensors qwen3_moe text-generation AWQ 量化修复
transformers safetensors qwen2 text-generation code codeqwen
Open-source autonomous AI dev team: Sensei orchestrates specialist agents from idea to shipped product. The engine behind KageOps.
Label a GitHub issue ai-agent and loope drives it to a PR with headless Claude Code. Stateless daemon, git worktrees, live dashboard.
Silico makes building maintainable firmware for embedded devices simple using AI.
A Claude Code loop that finds bugs in your repo, fixes them, and checks every fix before it commits.
A multi-agent AI coding workspace and orchestration environment for Pharo Smalltalk, featuring native and mobile-friendly Web UI
跨平台、本地优先的 Coding Agent 工作台:持久对话分支、Workspace 与 Session、多模型、Goal 与 Agent 编排、可自构建 Bots 和 Bot-to-Bot 协作。支持 macOS、Windows、Linux 桌面与无头 Web。
A minimal but complete Coding Agent Harness — learn how coding agents work by reading one. Built on Pi.
Lightweight terminal agent interface implemented in Golang
A Codex-like coding agent. Ask Amadeus to do anything
Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.
Your AI coding agents live on your computer. Relay puts them in your pocket.
Connecting coding agents across people and machines. Codex, Claude Code and Pi work together in one sandboxed workspace and, peer to peer, with your colleagues' agents. Each person directs their own agents and chooses what to share.
AI agents write tested code for your project, test-first; you approve the key steps. Dashboard, terminal app, Android app, MCP server, code review and a supervisor. Claude, Codex, Copilot, Vertex AI or local models (Ollama). One Docker image.
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
🚀 Open-source AI coding agent for your terminal, multi-model support, tool execution, code editing, approvals, failover routing, project context, and agentic workflows.
The 100 line AI agent for proving theorems and writing programs in Lean. Radically simple, no huge configs, no giant monorepo. Forked from mini-SWE-agent.
One terminal for Claude Code, Codex, Gemini CLI and 30+ coding agents. Run them side by side or as a team.
Agents that never hang up— One window for every agent, local and remote. Disconnect anytime, pick up where you left off.
OpenCode Plugin for supervised agentic software development on a Kanban board
Keep an eye on your AI coding agents: a live browser view of your agents, and CLI-based mail for them to collaborate on Tasks.
Async AI coding orchestrator: turns Yandex Tracker tasks into Claude Agent SDK workflows and GitHub PRs, with code review, deployment checks, and supervised auto-merge.
Command-line interface for performing software engineering tasks using large language models. It is based on Cline, but is simpler, uses fewer input tokens, has fewer capabilities, and does not depend on VSCode.
Agentic AI Software Engineer that can convert natural language to executable code
A LLM Agent capable of fixing bug by himself from a Javascript Error
Open-source AI coding team with multi-expert orchestration
🛡️ Orchestrate Claude Code sessions via API. Create, brief, monitor, refine, ship. The bridge between your orchestrator and your coding agent.
Structured wrapper for autonomous AI coding with Claude Code. PRD-driven task planning, atomic verification, and bash loop execution.
The first 100% file-based Local-First AgenticAI dev "construction yard", with its own memory & context, planning, writing and reviewing your code in safe sandboxes on your own machine.
An AI-powered desktop coding workspace for planning, coding, debugging, review, and testing through multi-agent orchestration and shared blackboards.
Multi-agent LLM system for autonomous code generation, testing, and debugging with Docker sandboxing
The composable agent development environment. Built in Zig. Modal. Extensible. Everything above the primitives is a plugin.
基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理,复杂任务智能拆解与多 Agent 并行执行。
You, multiplied. One place for every AI agent you run: Claude Code, Codex, and OpenCode side by side. See every session, approve what your agents do, and run them on a schedule. Self-hosted, MIT.
Open-source AI coding agent — 61 tools, 6 modes, 24 personas, 20+ models from 8 providers. Creative Studio for images, video, music, voice. 3M free tokens or BYOK.
Capable, auditable coding that runs fully offline on a 16 GB machine. A verification-first layer (hard test execution, symbolic checking, agentic repair) that takes a local 7B to parity with its 671B teacher on verifiable tasks. MIT, pre-registered, reproducible.
Your AI dev team in a box — parallel specialist agents, persistent memory, 820+ skills. Open-source, local-first.
The orchestration layer that turns Claude Code, OpenCode, and other AI coding CLIs into autonomous engineers — driving real work from task intake to merged pull request, with humans in the loop only where it counts. Swappable plugins for any trigger, chat, agent, or git host.
Local AI / LLM harness for professional programmers
M31 Autonomous — Rust-native autonomous software-engineering runtime with non-bypassable policy gates and verifiable execution
AI-powered coding agent for code generation, debugging, review, and deployment automation.
Model Optimizer safetensors qwen3 nvidia ModelOpt Kimi-K2.7-Code
transformers safetensors qwen3_next text-generation compression expert-merging
gguf qwen qwen3 moe mixture-of-experts deltanets
transformers safetensors qwen3 text-generation agents terminal
A modular coding-agent runtime for local or cloud models with a CLI, full-screen TUI, VS Code extension, desktop app, neovim plugin, and mobile app built on the same tools, safeguards, and workspace state.
Own the Outer Loop. Evidence → Verdict → Answerability. Governance layer for agentic engineering.
浏览器打开即用的 AI 编码工作台,着重优化了使用国产模型下的编程体验。 AI coding workbench that opens directly in the browser, with a focus on optimizing the programming experience when using Chinese models
A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).
Adeorq: nine agents working, one screen. A Windows and Linux desktop panel that runs AI coding agents in real terminals. Source visible, proprietary licence.
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
Terminal coding agent for local LLMs (llama.cpp, Ollama, vLLM) and any OpenAI-compatible API. OS-sandboxed autonomy, MCP, sessions. Go.
Local-first desktop workspace for ACP agents—DeepSeek Harness, Claude Code, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw—with projects, tools, files, browser, and sessions.
A local-first coding agent runtime, multi-provider LLM gateway, and terminal workspace — built from scratch in Go.
Autonomous multi-agent AI coding assistant as a JetBrains IDE plugin. Routes tasks through a Tolkien-themed fellowship (Gandalf→Aragorn→Celebrimbor→Samwise) with offline-first local Qwen inference, cloud fallback (Alibaba/Gemini/Amazon Q), and tools for code editing, terminal, git, web search, and project scanning.
A small Claude Code plugin: plain explanations, confidence % on options, verify before done, a cross-check by a different model, and a read-only audit.
gguf quantized quantization apex apex-quant custom-quantization
Experimental local AI workspace for multi-repository conversations, persistent tasks and reviewable pull requests. Built by FourBis. MIT.
码农场物语 · A team of coding agents you direct by voice or chat, drawn as a pixel farm. Runs on your own machine.
The agent harness you can embed anywhere: a 5.5 MB Zig agent core and coding CLI with a C ABI, graph memory and a kernel no plugin can bypass.
Self-hosted web console for running AI coding agents (Claude Code, Codex, Copilot, Antigravity, Cursor, Kiro, OpenCode) as a managed fleet: isolated per-user workspaces, git/SVN working copies, scheduling and usage accounting.
A native AI harness for Android.
Personal IDE: self-improving agentic dev environment with The God Factory, autonomous agent fleets, NANO model training, multi-LLM fallback, Monaco editor, and devtag-based forensic code analysis
AI coding assistant task and workflow manager
Skill-first AI coding agent in Rust — injects only the context your task needs. No prompt bloat. Single binary, no runtime.
Autonomous AI coding agent triggered by Linear tickets — spins up full dev environments on EC2, writes code, runs tests, and opens PRs with live preview URLs.
AI developer that generates LangChain Expression Language code
LLM-driven software development helper.
A LangChain, CLI based AI coding assistant and library aimed at fixing common issues that exist in other AI agents
ADD — Agent Driven Development. Coordinated AI agent teams that ship verified software. Spec-driven TDD, trust-but-verify orchestration, maturity lifecycle. Runs on Claude Code + Codex CLI.
agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.
Automatically create applications with a self task managing GPT
Resonant IDE — AI-native code editor built on VS Code OSS. Agentic loop, 59 local tools, 11 AI providers + BYOK + Ollama, AST Code Visualizer, Hash Sphere memory, DSID blockchain identity.
An agentic system that builds a full repo from a product requirements document (PRD)
🦀 Production-grade Rust rewrite of Claude Code. 42 native tools, multi-provider, 100% parity.
AI coding agent orchestrator — run parallel Claude Code tasks in sandboxed Docker containers, monitor from a Kanban board or chat bot.
TiyCode is an AI-first desktop coding agent. “钛可”是一款践行 AI First 理念的桌面版 Coding Agent
Minimal local-Qwen coding agent in a single Python file. ReAct loop, tool dispatch, atomic tools, no framework. Educational.
Modular Python coding and agent platform — LLM agents, graph RAG, static analysis, git ops, cloud and container deployment, all exposed as Model Context Protocol tools. uv-managed, with a zero-mock test suite.
Open-source AI coding agent for your terminal that you can undo, even its shell commands. 250+ models, /taste for AI-slop UI, model racing and parallel swarms. MIT.
Browser-based AI coding assistant — zero install, zero deploy, zero config. Agentic loop with 10 tools, 18 skills, and a force-directed Cosmos visualization. Runs entirely client-side.
🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.
Open-source, multi-provider AI coding-agent TUI in Rust.
Browser-native AI coding agent
transformers safetensors llama text-generation base_model:deepseek-ai/deepseek-coder-6.7b-base base_model:quantized:deepseek-ai/deepseek-coder-6.7b-base