Vector Search

Adaptive error memory and code intelligence system with Hebbian synapse network, hybrid search, and REST API

A local-first Model Context Protocol (MCP) server that provides semantic search capabilities for codebases

Model Context Protocol stdio server for @jeffs-brain/memory, exposing eleven memory tools with zero-config local and hosted modes.

MCP server for ThinkHive Explainer API v3 - Run-centric architecture with facts vs inferences, deterministic linking, calibrated predictions, and AI agent observability

Local RAG setup with ChromaDB + MCP server (Jina/BGE hybrid support).

GeneTech 14站知识引擎 — 数据引擎 MCP Server：让外部 AI Agent 实时查询、检索、引用前沿科技知识库（基因/量子/脑科学/AI Agent 等 14 个垂直领域）。

Ask huge PDFs, Word documents and spreadsheets specific questions: your AI gets only the passages that answer, with citations. A local MCP server for Claude Code, Cursor and Codex, plus a browser version.

Local-first, project-scoped MCP memory server for AI coding assistants.

n8n nodes for LightRAG workflows, AI Agent retrieval, and live n8n Chat responses

Search a curated English and Chinese web index through one read-only MCP tool.

Private, local-first memory subsystem for the pi coding agent. Long-term memory across sessions, stored on your own machine in SQLite, with optional on-device semantic search. No server, no cloud, nothing leaves your machine.

YouTube Client — free MCP server & Node library: transcripts with timestamps, RAG citation packs, chapters, captions, search. Native Go engine, no yt-dlp, no Python. For Cursor, Claude, and agents.

Agent-native Markdown workspace for raw capture, linked wikis, knowledge graphs, and semantic search

Local-first persistent memory MCP server for AI agents — with consolidation loop and git sync

Persistent memory for AI agents — pgvector + BM25 keyword search with RRF fusion, credential scrubbing, auto-consolidation.

Local-first Cognitive Memory Operating System and MCP server for autonomous AI coding agents. Tri-hybrid retrieval: ONNX semantic embeddings + SQLite FTS5/BM25 + hierarchical knowledge graph, fused with Reciprocal Rank Fusion. Zero cloud.

Full local browser engine for AI agents. Includes Playwright for complete page rendering, MCP server, and learning capabilities.

Local-first MCP code analyst: index your repo privately (embeddings + ripgrep-style search), then ask 'where does X break if I change Y' — zero cloud, zero config.

Semantic code search and cited answers over your codebase, for coding agents. Runs entirely locally.

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with token-efficient Skeletonization.