Ori Mnemos is an open-source persistent memory infrastructure for AI agents that implements human cognition models on a knowledge graph, enabling efficient retrieval and learning across sessions and clients.
From the registry: Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.
$ npm install -g ori-memory && ori init my-agentPlease install the `ori-memory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install ori-memory CLI** — Install globally via npm and initialize a vault Run: `npm install -g ori-memory && ori init my-agent` (https://www.npmjs.com/package/ori-memory)
Canonical MCP server config (stdio transport):
- command: `ori`
- args: ["serve","--mcp","--vault","/path/to/brain"]
- optional environment variables:
- `ORI_VAULT`: Path to the Ori vault directory (example: `/path/to/brain`)
Note: Persistent memory infrastructure for AI agents. Requires npm install -g ori-memory and initializing a vault. Use 'ori bridge claude-code --vault ~/brain' for full Claude Code integration with hooks. Local embeddings via all-MiniLM-L6-v2. Optional LLM for classification.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.ORI_VAULTrequiredPath to the directory where the agent's memory is stored.AI Agents Framework with Self Reflection and MCP support