local-first analytics for AI agent skills
A fast codebase indexer and knowledge wiki for AI agents.
Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.
A metasearch library that aggregates results from diverse web search services
Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.
Persistent Intelligence Infrastructure for AI Agents
A Model Context Protocol (MCP) server enabling AI assistants to interact with Outline documentation services.
Model Context Protocol (MCP) server for the Webflow Data API.
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
An MCP server that provides LLMs access to other LLMs
MCP Server para 70 APIs públicas brasileiras
Next.js Development for Coding Agent
The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.
An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.
The capability harness for AI agents. Skills over SDKs.

🧑🏻💻 MCP Server for @antvis visualization development, which provides documentation context and examples for visualization developers.
SpecStory's official collection of agent skills. Summarize, organize and create with `.specstory/history`

Comet: agent skill harness for turning ideas into evaluated workflows
Agent Skill that silently refines prompts for the currently running model
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Persistent memory for Claude Code. Your AI never starts from scratch again.
MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read