Memory & Knowledge MCP Servers

97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.

Review-gated declarative long-term memory with bounded read-only MCP access.

An MCP server that gives AI agents persistent, intent-based memory with vector embeddings and semantic indexing.

Knowledge-graph based memory server with storage in the current working directory.

Evidence-first entity and knowledge graph MCP server for AI agents to verify claims.

Append-only event log for cross-agent context/memory sharing via 3 MCP tools.

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

Universal AI memory layer - cross-client, cross-repo context management with RAG

Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).

Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.

Authority-weighted memory graph for AI agents with conflict detection and semantic search.

Local SQLite MCP memory: evidence-based recall, advisory conflict notices, authorized governance.

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest

Personal knowledge vault MCP server for Claude Desktop

Semantic search for Obsidian vaults via MCP

Knowledge graph + MCP tool server for LLM agents — 3rd-gen retrieval, graph-aware multi-turn exploration, structured data tools

Detect stale source context and retain traceable code-chain understanding for AI coding agents.

MCP server for vector search with Qdrant and Ollama embeddings

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

Persistent memory for Claude via weighted, interconnected knowledge nodes.

An MCP server that provides persistent memory and context management across sessions