Explore

Node.js·MIT·★ 78·No key

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Python·Apache-2.0·★ 13k·No key

Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and ot

Python·MIT·★ 24·No key

Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.

Python·MIT·★ 47·No key

Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB.

Python·MIT·★ 68·No key

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

Python·Apache-2.0·★ 282·No key

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

Skill·MIT·★ 40·No key

✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation

Node.js·MIT·★ 13·No key

Blueprint for spinning up read-only SQL data agents from any SQLAlchemy-compatible database. Indexes schema and column content into LanceDB and exposes MCP + REST tools so LLMs and UIs can safely expl

Skill·Apache-2.0·★ 4·Few stars·No key

Local-first archive, semantic search, and continuation for AI conversations across ChatGPT, Claude, Gemini, Grok, OpenRouter, LM Studio and Google/Gemini Ai Studio

Node.js·MIT·★ 12·No key

Memory layer MCP for AI coding agents — durable save/recall/update on Gemini embeddings + embedded LanceDB hybrid retrieval

Node.js·MIT·★ 5·Needs a key

Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.

Skill·MIT·★ 110·No key

AIDEFEND MCP is a local-first AI Security Defensive Assistant that brings the full AIDEFEND countermeasure library into your environment and turns static knowledge into actionable protection for LLMs

Python·MIT·★ 18·No key

ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector

Node.js·MIT·★ 29·No key

A rag + rag-graph native code intelligence layer for Java microservice estates, exposed to LLM agents via CLI

Python·MIT·★ 9·No key

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agen

Skill·MIT·★ 112·No key

Dig through any documentation with AI - MCP server for Claude, Cursor, and other AI assistants

Node.js·MIT·★ 18·No key

Python·AGPL-3.0·★ 29·No key

MCP tool to enable semantic code search in your project.

Node.js·MIT·★ 4·Few stars·No key

One private memory across Claude, ChatGPT, Cursor, and every MCP client — on-device, zero-knowledge. Plaintext never leaves your machine.

Node.js·Apache-2.0·★ 7·No key

Multi-layer agent memory MCP server — working, episodic, semantic, procedural & affective — for Claude Code and any MCP client.

Node.js·MIT·★ 3·Few stars·No key

On-device AI agent engine for mobile apps — embedded Node.js worker with Claude LLM, file tools, code execution, git, and extensible MCP device tools

Skill·MIT·★ 12·No key