Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 21 of 44
Task queue and orchestrator for AI coding agents. Manage Claude Code agents from Discord — auto-recovers from rate limits, runs overnight, queues work across projects.
The complete coding agent for your terminal. Autopilot, decision system for screening and reranking, built-in token savings, background subagents/shell calls, learner + memory system, nudges that keep models on track (small and flagship), code mode, and everything else a modern coding agent should have, designed together in one native binary.
Your coding agents, working in a live pixel-art office: Claude Code, Codex, Command Code and more, local or in sandboxes. npx theagentoffice
Tell your AI coding agent: plz do it, then prove it
Stop burning your Claude or Codex limits on boilerplate. Delegate multi-file implementation to Cursor's Composer 2.5 over MCP — your frontier model writes the brief and reviews the diff; Composer does the typing, fast, on a separate quota.
Go REST API scaffold: spec-first OpenAPI, chi, pgx/sqlc, OpenTelemetry, JWKS auth, embedded migrations, one-command resource generation.
A coding agent that refuses to over-engineer, built from scratch and measured honestly in one course notebook
Escreva uma issue, receba um PR testado: Claude Code e Codex programando no seu repositório em salas Docker isoladas, com verificação independente. Self-hosted, zero dependências npm.
Auto-pilot for agents
Product Wiki is an open-source harness for building software with coding agents, especially useful for non-technical builders who want to build complex products without the codebase turning messy.
share a live agent session with a link
Codebase for Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution paper
Zyvo AI - AI coding CLI for Android Termux . Native Android, 50 free AI models via random apo zero config. Banglish e kotha bole.the devoloper name is (9MPROFESSOR)
Simple code generator, choose your language and generate code, unit cases and documentation. Built with LangChain and React. OpenAI key required. This is a portfolio project showpiece and will not be updated in the future.
Extremely Tiny Coding Agent
ArchiFlow is an event-driven AI agent framework designed for software architecture, development, and code review tasks. Built on a lightweight message queue system, combined with an autonomous agent framework.
deepseek code agent for web client
Using AI Agents to solve hallucination problem in LLM and trying to make them reason and discuss just like a real team
Autonomous software delivery with AI agents — your BACKLOG runs itself, guided by encoded engineering discipline. No sprints, no hand-holding.
Your 24/7 team of senior engineers — a desktop AI multi-agent harness built for long-horizon software tasks.
A fully extensible AI coding agent harness built in Rust — designed to be embedded, extended, and composed into larger autonomous systems. Built using the Regula Framework.
The terminal workspace for AI coding agents. Run dozens of Claude Code sessions on a 2D canvas. macOS.
This project use the power of LLM Agents to Refactor Legacy code.
Your repo's engineering department. 7 AI agents ship PRs autonomously — from coverage gaps to features. Zero dependencies. Just Claude Code.
TUI for managing a fleet of opencode agents in git worktrees
RepoBird CLI is a powerful command-line interface and terminal UI for RepoBird.ai - the One-shot agentic coding platform
Self bootstrapped general purpose coder AGI (the "G" is joke?).
An AI assistant powered by Google Gemini to help you manage, create, and debug your programming projects.
A multi-provider desktop agent IDE for tool-using local and cloud models.
Multi-agent control plane for coding CLIs (Codex, OpenCode, CommandCode, Hermes) with one tmux session, one .logs/ source of truth, terminal + web frontends.
Refio – open source, local-first coding companion for IntelliJ
AI-powered coding assistant that sits on top of your IDE. Screenshot any coding problem, get instant AI solutions via Google Gemini.
A finish-first agent loop for Claude Opus 4.7 — plans, executes, verifies, and ships.
A coding agent built based on the LangChain / LangGraph ecosystem
Slack bot that exposes pi as a conversational coding agent
A customized Claude Code fork for routed models, multi-agent orchestration, and dense terminal control.
Agents change weekly. Your workflows shouldn't. One CLI for Claude, Codex, Gemini, Copilot, and Ollama.
Terminal-based agent runner that turns any LLM into a disciplined software engineer. FSM control, circuit breakers, model-agnostic. Bring Your Own Auth.
Autonomous multi-agent codebase modernization & tech debt hunter — 7 specialized agents, 4-pass long-chain reasoning, powered by Xiaomi MiMo V2.5
Run PAI (Personal AI Infrastructure) without an Anthropic subscription. Adapter layer for OpenCode — use any LLM provider.
Local-first Rust agent cockpit — route, run, replay, rewind.
Extremely Tiny Coding Agent
Stateful AI agent pipeline that turns task descriptions into review-ready branches
Local-first web command center for Claude Code, Codex, OpenCode and other CLI coding agents. Run agents in tmux across local, SSH and WSL, with notifications and file view.
The missing toolchain for CLI coding agents. Run any agent on your subscription. Parallel teams, browser driving, Touch ID secrets, routines.
macOS workbench for multi-agent coding — run and monitor multiple AI coding CLIs (Claude Code, Codex, Gemini, Kiro, and more) side by side, with project terminals, an embedded browser, Git at a glance, a Markdown task protocol, and remote control from Telegram.
An experimental AI system that can autonomously fix and improve code
Ripple — Autonomous agent runs for your development tasks. A local-first task manager where humans shape the backlog and agents handle the full cycle: branch → code → PR → review → merge. Built for developers who want to direct agents instead of micromanage them.
Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.
Runs CLI coding agents (Claude Code, Codex, Copilot, Cursor, Gemini, opencode) against a task queue. Each works in an isolated VM; output is checked by configurable auditors, then merged via git. Pools multiple provider subscriptions with quota-aware routing and fallback. C#/.NET 10, MIT-licensed.
Autonomous agentic coding environment — an OpenCode-driven 12-agent crew that ships hands-off. AGPL-3.0 · use at your own risk.
Autonomous multi-agent software development harness, powered by local LLMs
An advanced, sandboxed AI coding assistant CLI & TUI in Rust, featuring parallel tool execution, multi-provider LLM support
Free, self-hosted AI coding assistant for VS Code — local Ollama models, Anthropic Claude, or any OpenAI-compatible server. Full agent loop with tool use, inline completions, and MCP support.
A zero-dependency operating system for reliable multi-agent software delivery
transformers pytorch llama text-generation Python assistant
gguf llama.cpp gemma4 gemma abliterated uncensored
gguf qwen3 moe coding-agent tool-calling llama.cpp
transformers safetensors qwen3_moe text-generation GPTQ Int8
transformers gguf agent cohere byteshape text-generation
transformers gguf llama text-generation base_model:deepseek-ai/deepseek-coder-6.7b-instruct base_model:quantized:deepseek-ai/deepseek-coder-6.7b-instruct
transformers safetensors qwen2 text-generation agent software engineering
transformers safetensors qwen2 text-generation unsloth code
gguf llama-cpp lm-studio qwen3_5 fable5 reasoning
transformers safetensors qwen2 text-generation unsloth code
Agent-first CLI that runs Codex, Claude Code, and Grok as detached coding workers, while a stronger model keeps orchestration, steering, and review.
One coding session. Two AI agents. Zero lost context. Run Claude Code and Codex CLI as a single paired session.
Open-source, self-hosted browser workspace for running and supervising Codex, Claude Code, OpenCode, Pi, and other AI coding agents.
Open-source AI engineering team. Prompt in. PR out. Specialized agents plan, build, review, test, and ship code — with human approval at every gate.
Set the goal. A local agent team carries it to done. Coordinate models, continue sessions and inspect changes in one desktop workspace. Follow the work from your phone when you step away.
Local-first Windows desktop Agent for coding and Office, with specialist agents, a 2.5D office, Skills/MCP and an integrated workbench. Stable: 1.0.1.
Claude Code agents on a graph, each in its own git worktree. Chain a task to another and it inherits its output.
DeepSeek Harness 核心的便携引擎 + Termux 友好的终端编程 Agent CLI(pi 壳 + DSH 引擎,零运行时依赖,359MB→7.6MB 单文件)
Managed delegation for AI development. Delegate research, code review, and implementation through a local CLI and MCP server.
面向 Coding Agent 的终端工作台:以项目为单位维护 Session 与分屏终端,为 Agent 自动注入 Hook 和 MCP,并内置 SSH、SFTP 与浏览器自动化。
Retired. Superseded by Excalibur (xcb), the local workspace for coding agents. Historical OOMPA source and release contracts are preserved here.
Captain Code: one terminal for every coding agent you already pay for. Local director routing across Claude Code, Codex, Cursor, and remote models via opencode.
A terminal CLI that runs multiple AI coding agents from different LLM providers concurrently on one project. Install now!
An experimental terminal coding agent with configurable models, Witch orchestration, and multiple context compaction methods.
Safe, Speedy, Self-evolving coding agent.
Patched AGY binary — uncensored, unrestricted, rebuilt. Fork of google-antigravity/antigravity-cli.
Autonomous AI agent in pure Go: one static binary, zero dependencies, 9 platforms. A deterministic check, not the model, decides when a task is done. Runs on your ChatGPT, Copilot, Claude or Qwen subscription or any API, with parallel background agents on git worktrees, a TUI, a web UI and an HTTP API.
/ship takes one sentence to verified code. Terminal coding agent for DeepSeek and any compatible endpoint.
OpenCode and Claude Code coding agents in Telegram: run on your own machine or VPS, drive by voice or text from your phone. One topic per project, like terminal tabs. Self-hosted, no open ports.
Cross-device live sessions for AI coding agents (Claude / Codex / Pi). Master + join code. Website: https://skepagent.com
Retired. Orchestrated parallel AI coding into reviewable PRs.
A coding-agent harness that isn't tied to one model or provider: it picks a model per task, switches when one fails, and checks the work with your own tests.
OpenAI-first C++23 terminal coding agent with an ncursesw TUI
PTA (pintia.cn) 编程题辅助工具 —— 题目提取、答案读写、AI 代码生成
Turn a GitHub issue into a verified pull request: reproduces the bug with a test that must fail first, proves the fix in a Docker sandbox and opens the PR. Local-only (LangGraph + Ollama).
ReinAgent 是一个桌面 AI 编程客户端:把多个大模型接入你的本地工作区,用自然语言驱动它读写代码、执行命令、操作浏览器,并支持从手机远程查看与控制。
An autonomous SDK integration guardrail. Prevents AI hallucinations by forcing agents to ingest official `llms.txt` documentation and clone verified boilerplates before writing custom code.
GenPark AI Agent Skill: opencode-automator (Autonomous Code Engineering)
gradio region:us
Desktop AI coding agent built on Pi — Electron + React + TypeScript
Don't pay, just vibes. A desktop coding agent that runs on the accounts you already have: ChatGPT, Claude, and free provider tiers. No Anticode account, no API bill. Rotate usage across dozens of accounts and providers, and watch quota live.
Native desktop AI coding assistant. wxWidgets + C++20. No Electron.
A tiny terminal AI coding agent for Termux (Android). Like opencode/codex/claude-code, but Python. Free OpenCode Zen models, no auth needed.
An open-source autonomous AI agent implementation inspired by Cursor Agent, built with the Swarms framework. This production-grade agent can autonomously plan, execute, and complete complex tasks using a combination of Large Language Model reasoning and tool execution.
AI agent swarm orchestration toolkit — spawn, monitor, and manage coding agents (Codex, Claude Code, Gemini) with automated PR review and CI fix handling