Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 25 of 44
The cognitive operating system that gives AI coding agents memory, structure, and discipline — knowledge graph, Scrumban board, and an enforced engineering loop.
An orchestrator that runs coding agents unattended — and never believes them. Event-sourced, independently gate-verified, resumable from any crash.
Spec-driven AI development workflow for the terminal — from idea to reviewed merge.
Artemis: a local-first visual canvas for running Claude Code, Codex, Gemini, and OpenCode coding agents in parallel git worktrees, with human approval gates before anything merges — no telemetry.
A long-running agent harness for building software from ideas.
A self-evolving project builder. Given a vision and spec, it autonomously builds and improves a project session after session. Just drop it into your existing project and go.
Multiplayer AI coding — invite Claude agents, split tasks, and ship together in real time
Run Cursor Cloud coding agents from Hermes, on hosted VMs or isolated workers on your own machine.
Run a fleet of agent coding agents from Neovim
Native AI terminal for working with a fleet of coding agents. Run any agent (Claude Code, Codex, opencode…) with your own subscription — plan, sandbox, ship. macOS & Windows.
AI-powered coding interview assistant. Captures screenshots and analyzes them using OpenAI, Google Gemini, Claude, or Ollama. Features real-time streaming, multi-language support, and cross-platform compatibility (macOS, Windows, Linux).
Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a CLI or MCP server.
Terminal coding agent that executes tools (real think>tool>result loop with confirm + undo, MCP tools in-loop) and rewrites its own system prompt from feedback with metrics + auto-rollback. Free by default via the FCM model router.
Spawn silent-boot codex/omx coder teams — a maw plugin + charter. Each coder on its own account & worktree, zero trust prompts.
Local AI assistant proxy — connect ChatGPT/Claude/Gemini/Qwen to your local filesystem & browser via a Chrome extension + sandboxed Go server.
Native multi-provider AI coding agent in Rust — Avalonia desktop app for Linux/macOS with a native Android companion, WhatsApp bridge, Tor/Arti multi-device mesh, on-device skills, persistent memory and Web Search.
An open-source coding agent built with Rust.
Self-hosted, browser-based orchestrator for AI coding agents — real terminals, a kanban board that routes attention, review with real diffs. Access from anywhere. AGPL, no telemetry.
Arnesto — the agent harness that got out of hand
EMRG — a self-evolving AI agent architecture
Claude Code reimplemented in pure C — the lowest level it's ever been done
Canopy IDE
A local-first operator that turns plain-language ideas into tracked, verified Codex work—planned by Hermes, executed by Codex, and explained back to you.
Taurus - a Windows desktop launcher that runs multiple Claude Code agents as embedded terminal tabs, each started in the right process folder. Built around the Interpreted Context Methodology (ICM).
Collomia is a provider-neutral agentic coding agent for the terminal. Every model-proposed action passes through layered permissions, command analysis, OS sandboxing, network controls, an audit ledger, and evidence-based completion gates
A fast, model-agnostic coding agent for your terminal — built in Rust with a rich TUI, MCP, lossless context, safe tools, and built-in verification.
Agent-driven SDLC workflow that turns feature ideas into planned, built, verified, shipped, and maintained software.
A lightweight, DSL-driven AI agent for file operations, code modification, and command execution — designed for web and client-side AI assistants.
Clean, Simple Claude-Code Web-based Clone: Amber (amberagent.dev)
A FastAPI backend template for services that are built and maintained by coding agents
Autonomous COBOL to Python migration using AI agent swarms. 226 tests. pip install cobol-moderniser
Minimal Rust terminal harness for coding. Small, extremely fast, and self-extensible.
A Python CLI coding agent powered by remote Ollama, with workspace inspection and command-execution tools over Tailscale.
Local-first desktop command center for running and supervising teams of AI coding agents — embedded Claude Code terminals, a live agent constellation, kanban work board, cron schedules, and spend budgets. All state in local SQLite. Tauri 2 + React + FastAPI.
The MandoCode AI coding agent as a native Windows app — WinUI 3 over the same open-weight-model engine as the CLI (Ollama + Agent Framework). Review diffs before they land, run plans step-by-step. Local or hosted, no API keys, never locked to one vendor's model.
The official open-source repository for community-built prototypes and tools powered by the Oxlo API
The reachpad CLI: workspaces where Claude, Codex and other coding agents build full-stack apps and share them by link, from your terminal.
Governed software development for AI coding agents.
An agent for coding and everyday tasks, powered by your own ChatGPT or DeepSeek account. No API key, no per-token billing.
Pi coding agent 的桌面工作台:Web UI + Electron 壳,内置右侧浏览器控制、Univer 表格/文档/PPT 深度集成、会话可视化与团队协作
Work anywhere. Orchestrate coding agents and real terminal workflows from one Web command panel.
Terminal-based AI coding agent — provider-agnostic, MCP-ready, with live reasoning streams, prompt caching, plans mode and a skills system. Pure ES modules, zero build step.
Watch your Herdr coding agents as an 8-bit town. Read and answer them without leaving it.
An open-source terminal coding agent built on a bounded, observable Rust runtime.
Pin, blitz, merge. Autonomous coding pipeline: GitHub issue → EC2 spot instance → OpenCode agent → pull request. From issue to PR. With a trail.
Desktop app that runs agent CLIs in project-scoped rooms and presents their history in one shared view.
A command center for coding agents you run on your own VPS — Claude Code, Codex, Antigravity & OpenCode in one cockpit, self-hosted, no Docker required
Mission control for your coding agents — every Claude Code and Codex session on your Mac in one window: live terminals, activity status (which agent needs you), restore after reboot.
Autonomous context-engineered development system. 5 agents, 17 commands, SQLite brain. 70-90% fewer tokens. Works with Claude Code, Cursor, Codex, Gemini, Windsurf + 9 more.
Forge Studio - Agentic SWE factory builder
Lean coding harness written in Rust, focused on fast local workflows, deterministic tooling, and efficient code retrieval.
🤖 MahoAI: Full-stack AI coding assistant and automated backup/refactoring environment with Flask & modern web interface.
Free, open-source cross-platform desktop app for the Pi coding agent on Windows, macOS, and Linux. Projects, conversations, streamed tool activity, diffs, model controls, and graphical extensions in one native workspace.
Pi harness as a modern app, with UI, web search, subagents, /goal, and more, all installed in one command
Provider-agnostic coding-agent runtime and CLI for Elixir and the BEAM
Drop a card on the board, pick Claude Code, Codex CLI, OpenCode or the Hermes agent, and watch it work in its own git branch and worktree — then review, test and merge from one screen.
Run parallel AI coding agents in isolated Git worktrees with one lightweight, agent-agnostic CLI.
Open-source orchestrator for Compound Engineering across AI coding agents. Turn ideas into verified work, preserve engineering context, and make each change improve the next.
Agentic LLM shell aimed at low cost GPUs
Native macOS terminal for running many coding agents in parallel. Swift 6 + AppKit, SwiftTerm engine, agent state from Claude Code hooks instead of output parsing. Workspaces, split panes, triage dashboard. ~90 MB resident, 2.4us added input latency. brew install --cask essedev/relay/relay
Spec-driven development kit that orchestrates a team of AI agents (Copilot, OpenCode, Claude Code) through the full change lifecycle.
Local mission control for AI coding work: durable missions, evidence gates, and guarded completion.
Astra plans and reviews; Luna implements. Native Codex skill/plugin plus a standalone CLI with test gates and token receipts.
An autonomous AI coding assistant for developers. Write code, manage files, run terminal commands, and search the web directly from your terminal. Built with TypeScript and Bun as a modern, fast monorepo toolchain.
Orchestration platform for autonomous AI coding agents — turns issues into reviewed merge requests across GitLab and GitHub, with a conductor/worker hierarchy, durable messaging, and persistent memory.
Agent Relay: a local-first CLI for multi-agent coding workflows. Run Claude Code, Codex, Gemini, and OpenCode, hand off between them, and resume any session where it left off. This repo holds the README, issues, and releases.
A native macOS workspace for local and remote coding agents. Conversations, tools, approvals and tasks — with Kimi, Codex and more.
coding tasks with independent review
VD Agent: desktop AI coding agent that works with free API keys (Groq, Gemini, Ollama)
Minimal coding agent.
A locally runnable AI coding agent with desktop, web, IDE integrations, browser automation, MCP, and SDKs.
Public fork of openai/codex with honcho-backed memory, expanded hook parity, hashline, compaction, code_mode and multi_agent_v2 tweaks/fixes and fork-focused runtime/docs cleanup.
Moa — My Own Agent. A coding agent in Go.
FixIt - fuzzy-patch agentic C++ repair loop: compiler diagnostics -> code location -> LLM patch -> tolerant apply -> re-verify.
Coding should feel like thinking. Sayknow-CLI는 터미널에서 돌아가는 코딩 에이전트다. 요구를 인터뷰로 정리하고, 검토된 계획으로 실행을 검증하며, tmux 워커와 여러 모델 제공자를 넘나든다.
A desktop workspace for your dev day: Jira, GitHub PRs, notes and AI coding agents (Claude, Cursor, Codex via Paseo) in one place. Mac, Windows, Linux.
Spend the subscription quota you didn't use and achieve your goals: finished, reviewable PRs in your own private repo.
Run coding-agent CLIs on your machine and reach them from a browser as a terminal.
The only AI coding app you'll need. Run agents in parallel. Hand off tasks that come back as pull requests. Draw on screenshots to show exactly what's wrong. Native macOS.
A programming language designed for AI agents. 76% fewer tokens than Python.
Progress-aware execution for durable, grounded, token-efficient coding agents.
Stacking Agent Development Environment (ADE) for the busy dev
Agent OS for Claude Code: a desktop app to plan tasks, hand them to Claude Code agents and follow their runs across all your projects. macOS, early alpha.
Go library for driving AI coding CLIs in headless mode.
Lightweight terminal agent written in Go
Agent-native evolutionary optimization. Say the goal in english, evolve code toward a measured target with a population of coding agents.
Self Improving RLM based coding agent
A terminal AI agent written from scratch in Rust (multi-provider, file and shell tools). Learning project.
The open-source, local-first coding assistant and multi-agent IDE for macOS, Windows & Linux.
OpenCode Jesk - the OpenCode AI coding agent, natively inside Visual Studio.
A local multi-task terminal workspace for Coding Agent workflows.
From implementation plan to merged, tested pull requests: AI agents write the code, developers review, guardrails and tests protect quality. Browser wizard or CLI. A Ruby gem for Rails teams.
Yapay Zeka Ajanları için Mimari Koruma, Token Verimliliği ve Kod Üretim Altyapısı
Local-first workspace for CLI coding agents: plan projects in Origin, engineer prompts in Compose, run tasks on Kanban and reuse agentic AI resources in Base.
Let AI agents manage your whole codebase by editing small grids. Spec-driven, deterministic code generation for Next.js, TypeScript, React, Prisma, CSS and JSON.
Local-first chat workspace where you and the agent CLIs you already use (Claude Code, Codex, Grok, Kimi, Antigravity, OpenCode) work together. MIT.
A fast, hackable coding agent for your terminal, editor and browser.
Open-source, self-hosted AI coding agents: label a GitHub issue and sandboxed agents analyse, build and open the pull request. No network, no credentials.
Terminal coding agent that drives chat.deepseek.com or chat.qwen.ai through Playwright — no API key required. Reads/edits files, runs commands, commits to git.
Long-running coding-agent orchestrator for GitHub Projects