Vector Search

Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

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

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

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

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

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

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

Convert a document once, then get back only the passages that answer a question.

Local-first, source-grounded memory that survives AI agent sessions.

Index your codebase. AI searches instead of re-reading files. 94% token savings.

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.

Deterministic ebook-to-markdown pipeline with MCP tools to browse, search, and read your books.

Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.

Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.

Governed memory for AI agents (Paramind AI): conflict-checked writes, time-travel reads, ACL, audit.

Open-source MCP memory server. Persistent, searchable, tiered memory across sessions.