Vector Search

Graph-based memory system for LLMs with knowledge graphs and semantic search.

Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.

Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.

Local semantic search — embedding-powered grep for files, zero external services.

Local-first RAG engine with MCP server for AI agent integration.

AST-based semantic code search; results ship with their call graph (calls + callers).

Governed support MCP: answers only KB-grounded questions with citations, escalates the rest.

Local-only MCP server for source-attributed Markdown memory and documentation retrieval.

Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.

Graph-vector memory for AI assistants using FalkorDB and Qdrant

Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.

magic-8-ball MCP — wraps StupidAPIs (keyless — no credential needed)

mercury-number MCP — wraps StupidAPIs (keyless — no credential needed)

excuse MCP — wraps StupidAPIs (keyless — no credential needed)

iss-number MCP — wraps StupidAPIs (keyless — no credential needed)