AI-powered development tools. 19 agents, 22 commands, 32 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

Gerillass is a Sass mixin library containing a set of Sass mixins and functions to help front-end developers generate scalable CSS outputs.

Agent Skills Evaluation Framework

A native desktop application for developing, testing, and debugging Model Context Protocol servers.

A comprehensive MCP server for Gradle.

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

Open source software factory infrastructure for advanced AI coding workflows

A structural code search engine for Al agents.

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

CLI tool for controlling Unity Editor via command line - Play Mode, console logs, tests, scenes, GameObjects and more

Reusable agent skills for end-to-end software delivery, from requirements and implementation to review, testing, and release.

Orchestrate multiple coding agents from desktop and mobile

Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.

Research that compiles.

The graph based agentic IDE

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

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

Agent coordination protocol — declare intents, lock symbols, detect conflicts before code is written

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

Repo dependency analyzer with **blast-radius impact scoring** for AI-assisted development.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode.