Memory MCP Servers — Page 6

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP — with a 3D viewer that renders up to a million nodes.

Persistent AI memory: store, search, and recall knowledge across sessions

Access control, conflict resolution, and audit for shared agent memory.

Local-first second brain for Claude. Saves notes as Markdown and recalls them across sessions with offline semantic search, no cloud and no API keys.

Your portable AI memory vault — memories, skills & configs, shared across every AI tool.

Local-first, auditable memory for AI agents, with durable SQLite, MCP recall, and opt-in governed writeback.

Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph

Pay-per-call people + life-in-days knowledge API for AI agents (x402 on Base)

Local-first persistent memory for Claude Code and Codex. Hooks capture sessions automatically, an LLM distills them into SQLite (optional SQLCipher encryption), and recall stays auditable via MCP, REST, and CLI. Single Rust binary.

Hosted shared memory for coding agents: what one connected agent learns, other connected agents can recall.

Your portable, growing memory for AI: an EU-hosted personal knowledge layer that serves your AI-self files and learned patterns to any MCP client, read-only by default.

Self-hosted MCP server + dashboard that gives agents shared memory over a git-backed folder of markdown.

Perseus Vault is a single Rust binary that gives AI agents durable memory across sessions. One binary. One file. No Docker. No Postgres. No cloud. Just persistent memory that works with any MCP host.

The knowledge OS every AI can read from — persistent memory MCP server over your saved YouTube, articles, PDFs, and notes.

Waymark — shared route network for AI agents. Query verified step sequences + documented failure modes for API tasks over MCP. Reads free & keyless. 7,400+ routes, 2,100+ domains.

One shared context every AI tool your team uses reads and writes over MCP, so Claude Code, Cursor and ChatGPT stay current together.

NVIDIA AI Developer Stack as Compressed Knowledge Graph (CKG) - 20 domains, 998 notes, agents traverse typed dependency edges instead of scanning docs.

Persistent coding memory for AI assistants — MCP stdio + remote URL, hybrid search, knowledge graph, token-efficient context. Self-host on Cloudflare D1 or Postgres.

Connect AI agents to Granoflow for tasks, reviews, and spaced-review memory cards.

Local-first encrypted memory for AI agents with cryptographic forgetting

Local-first long-term memory for coding agents — in-process embeddings (MLX/CPU), hybrid vector+BM25 search, markdown as source of truth. No cloud, no keys.

A markdown knowledge base your AI reads, writes, and organizes — a memory in plain files you can actually open and correct (not an opaque vector store), with every agent edit signed and yours to approve.

Local-first MCP memory server with no external dependency, source citations and OKF/Markdown KB.

MCP server for Statewave, an open-source memory runtime for AI agents. Provides persistent memory, context retrieval, and memory compilation through the Model Context Protocol.

Remember everything. Stored on your device, not theirs.

A living memory that decays, learns, and evolves with your AI.

Provides local repo-intelligence by indexing source, symbols, call graphs, Git/GitHub history, and source-bound repo memories into a local database for coding agents.

Self-hosted long-term memory for AI agents: MCP server with hierarchical recall over pgvector.

The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI, zero dependencies.

Save your AI chat's working state and load it in any other model, client or provider. Verified on save, secrets stripped.