Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.
Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.
Your agents rent their intelligence from a lab; their memory should be yours. Mnema is a single, durable store of what your agents have learned — consult it before you act, learn a durable fact, walk the related graph, list what's recent. Data lives in ~/.mnema on your machine and nothing leaves it unless you point it somewhere.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
| Variable | Description | Required |
|---|---|---|
| MNEMA_URL | Endpoint or connection string the server talks to. | Yes |
| MNEMA_TOKEN | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Pick the surface that matches how you work — every option talks to the same handlers, the same auth, the same data:
Turns Obsidian vaults into AI-queryable knowledge graphs with 12 tools
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
A remote MCP server at mcp.reply.io that lets MCP-compatible AI clients — Claude, ChatGPT, Cursor, Codex, and more — work with your Reply.io CRM and AI SDR. One connection gives an agent a catalog…