Turn Claude Code into a coordinated team of 40+ specialized AI agents that work together like a world-class engineering organization.

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.

Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.

Open-source CLI coding agent, a free alternative to Claude Code. Generate, debug, and manage code seamlessly.

Lightweight coding agent written in Rust, optimized for memory footprint and performance

An ML engineering plugin for your coding agents.

Automated quality checks that nudge AI coding agents toward better habits

Next.js Development for Coding Agent

An open-source AI coding agent that lives in your terminal.

An eBPF skill for coding agents

The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

General-purpose Playwright automation for coding agents

⌥ Coding agent with the IDE wired in

C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins

Production-grade engineering skills for AI coding agents.

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

a coding Agent, rpc plugin, sub-agents, hashline edits, and mcp

Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.

Token-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.

Chrome DevTools for coding agents

Security testing that runs inside the coding agent you already use. Source-available, not open source.

Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents