Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.
2,023 MCP servers
One searchable history across every AI coding tool, with secret scanning and a shared task board.
Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting.
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.
Recognition-first cross-agent memory federation. One shared memory across all your agents.
MCP server that gives coding agents persistent project understanding via a knowledge graph
Universal memory system for AI agents - CLI + MCP server + library API
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
Persistent project context for Claude. IANA-registered .faf format.
Licensed, rights-cleared content for AI agents — verifiable license keys, on-chain proof, and EU AI Act attestation. The MCP alternative to
Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.
Seven-layer agent memory: episodic, semantic, procedural and core. Local SQLite, no account.
LanceDB long-term memory MCP server with SiliconFlow/OpenAI-compatible embeddings.
MCP server for reading Simplenote notes across macOS, Linux, and Windows
The self-correcting memory layer for AI agents: when a fact is corrected, mnemo serves the new value and resists the old one resurfacing
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
Headless semantic MCP server for Obsidian, Logseq, Dendron and any markdown-based knowledge base
PayBito infrastructure knowledge helper for AI agents — injects PayBito API expertise (Resources + Prompts + read-only knowledge tools, no
Verifiable, portable AI memory. Optional vault: encrypted on your machine, 12 words only you hold.