The official Rust SDK for the Model Context Protocol

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Claude Code role-based Rails agent kit with orchestrator and specialist slash commands.

⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.

Claude Code skill for building interactive node-based UIs with React Flow (@xyflow/react v12+)

Advanced MCP Server ROS 2 bridging AI agents straight into robotics

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

RikkaHub is an Android APP that supports for multiple LLM providers.

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Give your AI coding agent a Roblox brain. Skill collection for Roblox Studio game development.

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

A collection of MATLAB coding rules and guidelines optimized for use with AI coding assistants like Cursor, Windsurf, Claude Code, and GitHub Copilot

A community driven registry service for Model Context Protocol (MCP) servers.

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based

Your coding agent starts every session blank. Rekal is the memory your team is missing

The official Ruby SDK for the Model Context Protocol servers and clients.

MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik

PDF RAG server for cursor.

TUI framework and developer productivity apps in Rust 🦀

An Agent Skill for the DL experiment lifecycle: RUN (a GPU you own or rent) → VERIFY the number is real → DELIVER reproducible, single-source figures and tables.

Typed pythonic RSS/Atom parser: RSS 2.0/0.9x, Atom 1.0, RSS 1.0 (RDF) and podcasts into pydantic v2 models, plus a CLI

TUI for reviewing diffs, files, and documents with inline annotations

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.