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

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.

Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)

Building blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Authorized security testing workspace. v2 TypeScript terminal product on release; v1 Python on pypi-release; Go branch is demo only.

A collection of production-ready slash commands for Claude Code

LSP plugins for Claude Code — Bash/Shell, C/C++/Objective-C, C#, Clojure, Dart/Flutter, Elixir, Gleam, Go, Java, Kotlin, Lua, Nix, OCaml, PHP, Python, Ruby, Rust, Swift, Terraform, TypeScript/JavaScript, YAML & Zig

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

AI Agent Orchestrator for Claude Code

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

Agent skill for modern Android development with Jetpack Compose — best practices for code generation and review

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

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

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

lnwjud — local AI-agent runtime & MCP gateway

Bring Claude Code, Codex, and your favorite CLI agents into one visual workspace. Run agents in parallel and build executable workflows in isolated Git worktrees. Build your own AI coding team, and turn builds, tests, and dev servers into reusable canvas workflows.

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.