#vector-search

LanceDB MCP Server nodejs

MCP persistent memory service that gives AI assistants long-term memory across sessions and projects. Powered by Qdrant vector search + Ollama/Gemini embedding with hybrid retrieval (vector + BM25). Features include: semantic memory save/search/forget, content deduplication via SHA-256, automatic sensitive data redaction, dual-shell architecture (MCP stdio + HTTP REST), Web Admin Panel with analytics, multi-user auth & API key management, and audit logging.

AI-Ready Data & Context Engineering API. Connect any data source — PostgreSQL, CRMs, APIs — and get clean, structured, AI-ready data in seconds. Natural language queries, semantic vector search, automated PII redaction, deduplication, and AI-powered context building for RAG pipelines. 25 free credits on signup.

Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware. Key features: . Semantic search (find memories by meaning, not keywords) . Per-agent API keys with granular permissions . 3D constellation viewer with live agent activity . File vault (attach real documents to memories) . CSV audit log (full transparency on every agent action) . Pre-Strata history import (your memory doesn't start at install day) . Global MCP kill switch (emergency brake, only a human can undo) . Automatic deduplication . 10 structured thought types . Backend using PostgreSQL . Runs on a Raspberry Pi Always on, always local, always yours.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories locally in SQLite, ranks by 6-factor scoring, returns results in TOON compact format (79% smaller than JSON). 17 MCP tools, 20 HTTP endpoints, 25 CLI commands. 4 tiers from keyword to autonomous with local LLMs via Ollama. 97.8% recall accuracy on ICLR 2025 LongMemEval benchmark. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, Continue.dev, OpenClaw, Llama, and any MCP client. Open source, MIT licensed, written in Rust.

Transform your AI agents into Apple development experts! Apple RAG MCP gives you instant access to official Swift docs, design guidelines, and comprehensive Apple platform knowledge through cutting-edge RAG technology. With professional AI reranking and hybrid search across iOS, macOS, watchOS, tvOS, and visionOS documentation plus Apple Developer YouTube content, you'll get precise, contextual answers every time. Compatible with Cursor, Claude Desktop, and all MCP tools - start building smarter Apple apps today!

Model–Context–Protocol (MCP) Server A modular, extensible Rust-based server providing short-term, long-term, and latent memory services, a chat endpoint backed by a BaseAgent + Sentience DSL, and seamless integration with ChromaDB and LLM services.

Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.

One-line MCP config gives your AI agent persistent memory with automatic workflow rules. Unlike passive memory stores, Awareness teaches your agent WHEN to remember and recall — works across Claude Code, Cursor, Windsurf, Cline, Copilot and 7 more IDEs.

Memory with integrity for AI coding agents. SAME tracks provenance, flags stale knowledge, and surfaces contradictions; so your AI trusts what's current, not what's outdated. 17 MCP tools: semantic search, cross-vault federation, session handoffs, decision logging, knowledge graph, trust-aware retrieval, consolidation, health analysis. Provenance on every write. Stale notes rank lower automatically. SQLite + vector search. Ollama, OpenAI, LM Studio, or keyword-only. One 12MB Go binary. No cloud, no API keys, no telemetry. Your notes never leave your machine. Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, and any MCP client.