Vector Search

Query a verified document collection: passages that answer a question, with their source.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

Recall locally stored agent memories through an MCP-compatible host.

Full-text Asian financial reports (China, Korea, Japan) as clean Markdown — 6 tools for RAG agents.

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

bioRxiv/medRxiv/arXiv preprint full text as structured sections for AI agents + search.

Tamper-evident record of what your AI agent did, plus local-first verifiable memory.

31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.

MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.

Self-maintaining knowledge vault: figure-level search, auto-wikilinks, and memory compression.

Production-grade PostgreSQL MCP server — 254 tools for query, tuning & ops, read-only by default.

Convert PDFs and other documents to structured formats via Docling, for AI applications.

The data control plane for AI agents — acquire, validate, land, and query data over MCP.

Hybrid search for Cowork history: FTS, Spotlight, and semantic vectors

Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.

Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types

Local-first bookmark management with semantic search and AI-powered organization