Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
2,064 MCP servers
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.
Enhanced MCP memory server with timestamps, tags, importance, search, and export (JSON/CSV/GraphML)
Recall locally stored agent memories through an MCP-compatible host.
An MCP memory server. One memory your agents share — across models, devices and apps.
Local-first memory for MCP assistants: remember, recall, forget and expand. Everything stays on your own computer. Needs the free ModelBrain desktop app.
Persistent memory for long conversations - MCP server for knowledge graph with atomic facts, cross-chat memory sharing, and multi-agent
A lightweight, Git-backed permanent memory for AI agents.
Lightweight MCP server that records and reuses Prompt Gaps
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
MCP Server for Claude Code project memory - multi-block Core Memory (project/learnings/decisions) via Letta Cloud
A Model Context Protocol (MCP) server for managing structured project context.
Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest
Project-local knowledge-graph memory MCP server from N2NS Lab for AI coding agents.
Manually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB.
Local read-only semantic search for Markdown vaults through MCP.
MCP server + LLM-wiki skill for Trilium/TriliumNext Notes (Karpathy LLM-wiki methodology).