Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.
MCP server for semantic search and write actions across Apple Mail, Messages, Calendar, and Contacts. Speaks stdio (local) or bearer-token-authenticated Streamable HTTP (LAN / Tailscale).
Local-first long-term memory for AI coding agents. Stored on your own machine.
Literature knowledge base for DSH and MCP clients. Index PDFs or a Zotero library into one SQLite file; search and RAG tools return passages with section, page and DOI. Embedding and reranking run loc
Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.
A paid public-domain knowledge base for AI agents: full-text search, book metadata, chapters.
Local RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.
Curated Islamic knowledge MCP server: Quranic verses, a curated du'a corpus, and the 99 Names of Allah. New and changed content is reviewed through AskSakina's structured specialist-AI review chain ac
Persistent memory for coding agents: an MCP server for Claude Code, Claude Desktop, Cursor and VS Code Copilot. Layered project memory, Claude Code hooks, JSON Schema validation, token ledger and shif
CogmemAi is the safe, persistent memory that keeps Ai in line. It remembers what matters across every session, stops any action that breaks the rules you set before it happens, and reviews what your A
Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.
Manage HelpCrunch chats, customers, agents and knowledge-base articles.
The Runpod plugin's skills, reference docs, golden paths and concept graph as one JSON bundle, for programs such as the Runpod MCP server
LensMCP container/memory mutation tracking (Map/Set/Array instrumentation).
Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embedd
A lightweight, structured, token-efficient local-first MCP memory server
Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.
OpenCode plugin + MCP server that saves 98% of your context window. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.
Transcribes audio and video files to text, SRT, VTT and timestamped chunks for RAG.
PLUR MCP server — persistent memory tools for any AI agent
Shared task board and knowledge base for AI coding agents
Team-shared memory MCP: 15 tools, search, links, collections, bulk ops, Teams workspaces.
Typed AI framework for TypeScript: provider routing and failover, durable agent graphs and workflows, retrieval over any vector store, MCP, evals, guardrails, and cost control
Simple agent memory MCP: keep, recall, update, forget; shared team graph on Maindex.
Pay-per-request GPT chat, embeddings, agents and prepaid keys with local x402 USDC signing
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
MCP server that gives Claude, ChatGPT and other MCP clients access to a Zotero library: search, citations, adding items, safe writes, semantic search, PDF passages and page images.
Versioned documentation registry and semantic search for AI tools and coding assistants.
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
E2E-encrypted markdown notes as shared memory for you and your agents, with local semantic search.
Local knowledge graph memory for agents. SHACL rules refuse bad facts; SPARQL and time travel.
Local codebase search for agents: hybrid keyword/semantic search, locate, expand, related code.
ディレクトリ全体
RAG、グラフ、エージェントの長期メモリ。 2,637 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。