Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43…
Runs locally- Open source
- Knowledge and memory
Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43…
Runs locallyLocal-first durable AI memory with policy-bound recall and a typed project graph.
Runs locallyLocal semantic search over Obsidian vaults via Smart Connections embeddings…
Runs locallyMemory your agent can trust — every answer carries its source; when it doesn't know, it…
Runs locallyAI-powered vector knowledge graph MCP server for agents. Supports add node, add edge…
Runs locallyOn-device, self-organizing memory for AI coding agents — recalls the right facts into…
Runs locallyPersistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit…
Runs locallyLocal-first, governable long-term memory for AI coding agents
Runs locallyLocal-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
Runs locallyPersistent code memory for AI agents: notes pinned to files and symbols that survive…
Runs locallyLocal Zotero, MinerU, Obsidian literature workflow with transactional Analysis notes.
Runs locallySearch IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported.
Runs locallyRAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by…
Runs locallyLocal-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 +…
Runs locallyIdentity, memory, trust, and swarm primitives for AI agents. MIRC base always free.
Runs locallyNarrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.
Runs locallyOpen, source-cited knowledge base of Belgian insurance products: search, compare…
Runs locallyLocal-first persistent memory for coding agents and MCP clients.
Runs locallyLocal-first RAG engine with MCP server for AI agent integration.
Runs locallyEmbedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
Runs locallyShared, git-tracked working memory for AI agents on the same codebase.
Runs locallyLocal MCP server for Obsidian Desktop via the official Obsidian CLI.
Runs locallyMCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector…
Not checked yetOffline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Runs locallyLocal-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT…
Runs locallyPersistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB.
Runs locallyx402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid…
Runs locallyCloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by…
Runs locallyPersistent memory for AI thinking partnerships: hybrid search and a temporal knowledge…
Runs locallyEmbedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no…
Runs locallySee every kind of AI for knowledge and memory: tools, agents, MCP servers and skills.Ranked: the best AI for knowledge and memory.