Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 29 of 44
safetensors qwen3_next fp8 quantized llm-compressor compressed-tensors
gguf code qwen qwen-coder codeqwen text-generation
transformers safetensors qwen2 text-generation code codeqwen
transformers gguf code codeqwen chat qwen
gguf mistral quantized 2-bit 3-bit 4-bit
mlx safetensors qwen2 code codeqwen chat
AI Dev Squad turns AI coding into a controlled workflow. It helps teams plan, write, and test code faster with clear human approval before changes happen. Built for safer AI-assisted development with Python, LangGraph, LangChain, Codex CLI, Streamlit, and local model-ready routing.
The terminal for the agent era — AI coding agent cockpit & multiplexer. Run a wall of Claude/Aider/Cursor agents from one TUI with live status, peer messaging, and an AI conductor.
Compact Rust coding agent for local OpenAI-compatible models: one static binary, kernel folder lock (Landlock), sessions, skills, MCP, plan mode, detached sub-agents. Ships NO0B, a wgpu GPU front end.
Cross-harness orchestration for wakeable coding agents using Agent Intercom
A DeepSeek-native AI coding agent framework in Rust — 22 crates, CLI/TUI/HTTP API, agentic tool loop + graph retrieval + 4-layer memory + MCP.
Bring agents into your codebase, courtesy of Ollama and a little bird.
An Agentic Python Library and CLI Tool to automate Coding tutorial generation.
yet another coding agent to learn how it works
Coding agents that ship to a real repository on their own: one agent writes, a different agent reviews the exact diff, and the tests actually run.
From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.
CLI-based AI coding assistant using AWS Bedrock and Claude models. Features interactive mode, file context, git integration, web search, and image analysis.
An AI agent that writes, tests, and debugs code on its own — built with LangGraph and Groq, and it's actually opened a real GitHub PR.
Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.
AgentLoop — harness-agnostic, self-verifying autonomy wrapper for coding agents. Drives OpenCode/Kilo/Claude/Aider/Codex in a verify-gated loop with a held-out oracle, so the agent actually finishes and proves it is correct.
Run a software team from your chat: backlog, AI workers, adversarial review, human merges. Vibecoding, for teams. Built on Hermes Agent.
Vega Multiagent — open-source multi-agent AI coding assistant for VS Code, JetBrains IDEs & CLI. Derived from Cline (Apache-2.0). Local LLMs, security testing, MCP. Creator: Ajay Jatav
A Python AI coding agent with tool calling, safe file operations, and multi-step agent loops.
🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.
The open-source agentic execution layer.
Agent Harness
Apply LLM code edits via SEARCH/REPLACE blocks. Exact match or refuse — never guesses. Zero dependencies.
Work goes in -> webs come out. Task optimizer for Codex.
Empathetic AI engineering partner with cognitive memory, multi-agent orchestration (10 agents), 132-signal skill routing, and self-improving reflection loops. Built on Model Context Protocol. By Aldo Karendra.
Persistent, goal-driven UltraWork mode for pi.dev — auto-continues across turns and fans sub-tasks out to child pi processes.
A high-performance AI coding agent.
Spec-driven agentic workflow for AI coding agents, with specialized subagents (research, plan, critique, execute, verify, debug) via markdown specs
[ASE 2026] MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs
天机(Tianji):多 CLI 编程助手编排框架——六角色机械流水线(总控/分配器/监控器/架构师/实施者/审核者),账本单一真源,机制化不靠自觉
Your AI coding crew in one Windows terminal - run Claude Code, Codex, opencode & Antigravity as a real team (lead + workers) in a native psmux cockpit. Event-sourced, no WSL, no API keys.
Lightweight terminal coding agent - drives a small local model or a frontier model with minimal context usage
LLM Agent based VisualBasic.NET IDE
Daedalus - Agentic platform for collaborative defect resolution
Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.
Open-source VS Code extension — AI coding agent with local LLM support, multi-provider auto-discovery, and autonomous workflows
Open-source AI coding agent and agent harness in Rust. Terminal CLI (TUI) for DeepSeek, Claude, OpenAI, Gemini and 10+ providers, with MCP, Skills, permissions, remote agents and cost tracking.
A beautiful code agent GUI with graceful agent design.
Zero-dependency autonomous AI software engineer in pure Python stdlib. Native Windows PowerShell REPL (<5ms), AST causal healing, MCP standard, Swarm speculation & Byzantine consensus.
Codex plugin for durable agentic software-factory orchestration with SQLite-backed ledgers.
Lightweight AI coding assistant inspired by Claude Code, Codex & OpenCode — 100% Python, LangGraph state machine, Textual TUI, WebSocket server. Self-hosted & extensible.
MC-GPT: say the outcome in English or German. Task, Meeting and Multi-Coder for Claude, Codex, Gemini, Grok and Ollama. Docs + AI index: https://iotaitech.github.io/MC-GPT/ · llms.txt
An AI-powered coding assistant fine tuned for local light-weight LLMS with enhanced features for file management, terminal integration, testing, code refactoring, and project management.
Slow and steady wins the (AI) race! 🐢🏁 turtle is a locally hosted CLI LLM coding assistant because F%#@ data-centers!
JMP — Joint Model Participation. A local coding workspace where Jev routes actions and OpenAI, DeepSeek, or local models generate arguments.
Recursive Language Models for pi: persistent Python REPL with rlm() sub-agent recursion, namespace snapshots and a continual harness (/refine) — as a single extension
Open source runtime to migrate DRF to FastAPI (and more to come) 🚚
Reliability Harness v2 for OpenCode CLI — task contracts, least-privilege sub-agents, clean-checkout verification, and a deterministic done-gate. Orthogonal agents (scout/spec-critic/test-designer/lead/verifier/adversary) instead of 3 identical thinking clones. Compatible with Oh My OpenAgent. Not a model swap or 1:1 emulation.
One desktop app for every coding agent. Pick the harness per session and any model it can reach.
Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency
A light coding harness with agent-controlled context. Full machine control, zero permission prompts. 200+ LLM providers, ACP/A2A, plugins, SQLite sessions, TUI + headless.
Desktop AI coding agent for Linux/Windows/macOS: an Avalonia .NET app with git-worktree isolation per session, plan review, subagents, a real XTerm grid and an encrypted secret vault that masks credentials before they reach a model.
A coding agent with guardrails — an Ink TUI for your terminal and an Electron app for the desktop: streaming tools, approvals, compaction, repeat guards.
A minimal, dependency-free coding agent written in C
Spec-driven software-engineering team of three AI roles (Morfeo, Supervisor, Implementers) on Hermes Agent: Objective Contracts, isolated worktrees, independent review. v1.0.
VALI - verification-gated coding platform: Z3-proved refactors, ThoughtGraph reasoning DAG, temporal time-travel over agent edits
Pi's coding agent ported to Rust
gguf text-generation arxiv:2401.06066 base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Base base_model:quantized:deepseek-ai/DeepSeek-Coder-V2-Lite-Base license:ot
Best blend of spec-driven and superpowers - YMMV
Modular .NET 10 platform for agentic software delivery. Orchestrator + specialist agents (Requirements → Code → Tests → QA) on a provider-agnostic LLM gateway (Claude · Azure OpenAI · OpenAI · Gemini · xAI · local models · paired dev machine), multi-tenant with Postgres row-level security, Blazor AgentOS desktop UI.
Self-evolving coding agent for long-running autonomous tasks
EURUS is a provider-agnostic autonomous AI coding agent for terminal workflows, with shell execution, file editing, patch generation, testing, persistent memory, skills, and MCP integrations.
Tongxi · Agent Hub — a Windows desktop app that seats Codex, Claude Code, Hermes, DSH and OpenCode at one table: 1:1 chat, group chat, and a lead agent that splits repo work across members (Tauri 2 + TypeScript + Rust)
Run a team of Claude Code agents side by side: real terminal panes, a task board, a lead agent, git worktrees, review and merge. macOS app, local only.
gradio region:us
GAN-inspired multi-agent system that autonomously builds full-stack web apps from a single prompt using Claude AI agents
Minimal AI agent in your terminal
自托管 HTTP 编程 Agent 工作台:支持流式对话、持久会话、文件交付、后台任务和 Docker Chrome 真实浏览器访问。
Background coding agents that execute, review, and land work unattended.
A demonstration of using the CrewAI framework to automatically plan, write, execute, and collect output from Python coding assignments using an LLM-based “Coder” agent.
POC R&D : Une équipe d'agents IA autonomes pour construire vos logiciels. Orchestrés par un superviseur, des agents Analyste et Développeur utilisent une architecture RAG et des LLMs (Mistral) pour gérer la conception, le code, les tests et la documentation de manière 100% autonome.
A self-hosted control plane for AI engineering workflows.
SAGE — Self-improving Autonomous Generation Engine. Prompt → production software using coordinated AI agents. Local-first multi-agent coding pipeline with planning, coding, execution, and self-healing debugging.
The Autonomous Development Platform represents a paradigm shift in software development - a fully autonomous, multi-agent research and development system that transcends traditional no-code tools.
🌟 open source alternative for cursor, claude code , codex etc.
Opinionated autonomous software engineering runtime with operator messaging, scheduling, and multi-provider agents
Terminal AI coding CLI for any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates.
Anvil-code — autonomous coding agent that runs entirely on your machine. 32B local models + structural-anchor edits, no cloud.
AI Agent for PMSM FOC development with LangGraph + RAG + 37 tools — supports DeepSeek / MiMo / GPT-4o
PersistenceAI by Leo Louvar - Terminal AI IDE and Agentic Coding Multiplexer. Enterprise-grade terminal IDE with multi-agent AI integration, AI agentic coding, vibe coding, terminal-first design, and full IDE features.
One prompt, one app. Multi-agent AI engine that builds software projects autonomously.
Assign a GitHub issue, wake up to a PR. Autonomous agent in ~630 lines of bash — cron, flock, and git worktrees on a $10/month VPS.
A self-improving coding agent with episodic failure memory. Runs locally. No cloud. No API. Just gets better.
A small code snippet as a part of "How to Write an Agent" Blog Post
Using natural language to write in any programming language.
Local-first agentic coding CLI — 862 expert beliefs, hybrid vector retrieval (embeddings + knowledge graph + TF-IDF), error database that learns from mistakes, self-directed web learning, and evolving identity. A 31B model with persistent memory that accumulates wisdom across sessions. Zero cloud. Zero API keys. Powered by llama.cpp + Gemma 4.
A modern, full-stack AI coding and task assistant leveraging local LLMs, a robust React, TypeScript, PostgreSQL stack, and a highly extensible component system.
model-agnostic, local-first ai coding assistant
An AI Agency that code entire projects for you. Runs on the latest OpenAI Assistants API.
Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency
The hybrid CLI/Web coding agent that works your way.
Coding Agent written in rust
Autonomous coding loop for OpenAI Codex and Google Gemini CLIs. Drop planning docs into a folder, set an iteration count, and loop-agent generates a backlog and runs plan → implement → review cycles to write your code. Independent-process reviews, atomic backlog updates, auto git rollback on failure, and safe rate-limit handling.
High-performance, Rust-based terminal coding agent that integrates with multiple LLM providers (cloud and local) to deliver a fully autonomous, agentic development workflow.
Local-first coding agent for small language models, with workspace indexing, structured edits, and reliable tool calls.
Stop non-deterministic edits: A strict "Read-Match-Hash-Write" pipeline for safe and reproducible code modifications. AnchorScope is a reference implementation of a deterministic code editing protocol for LLM agents.