GitHub Agentic Workflows

A dev environment for AI agents.

An open-source code repository and version control system for people and AI agents. Functions, types, recorded relationships and change history are repository data you commit, branch and merge. Look up what a change might affect before you make it. Public alpha.

Production-grade engineering skills for AI coding agents.

An agentic skills framework & software development methodology that works.

Lint rules for your AI agent's discipline, not its code

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Give any AI agent the ability to code

AI-agent skills for distributed-systems testing

Security scanner for AI agents, MCP servers and agent skills.

Git. Ship. Done - Core

Toolkit for Coding Agents to work reliably with repo of any size.

Simple workflow for agent coding with skills

Workflow orchestration for AI coding agent swarms, from task to merged PR.

Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifies and merges

A Lisp with first-class LLM primitives, implemented in Rust

Curated collection of agent skills for AI coding assistants.

One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 20 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.

A framework-agnostic, git-native standard for defining AI agents

Spring Boot skills for AI coding agents

Your AI-Powered Coding Tools Best Practices

Give your AI Agent a whole IDE, not just the files

🥷 Engineering habits you already know, turned into skills Claude can run.

Forcing-function skills for AI agents — validated to improve behavior, not just change it.