Ori Memory

{
  "mcpServers": {
    "ori-memory": {
      "command": "npx",
      "args": [
        "-y",
        "ori-memory"
      ]
    }
  }
}

claude mcp add --transport stdio ori-memory -- npx -y ori-memory

{
  "mcpServers": {
    "ori-memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ori-memory"
      ]
    }
  }
}

{
  "servers": {
    "ori-memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ori-memory"
      ]
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

• ori_wake

  Session boot: bounded briefing, plus onboarding on a fresh vault

• ori_update

  Write to identity, goals, methodology, daily, or reminders

• ori_update_decision

  Record the user's answer to an update notice

• ori_whats_new

  Release notes for the installed version, or any version

• memory_sql

  Read-only SQL over the index — anything the ranking tools cannot express

• ori_health

  Full diagnostics

• ori_add

  Capture to inbox

• ori_promote

  Promote with classification, linking, and area assignment

• ori_validate

  Schema validation

• ori_query_ranked

  Full retrieval with Q-value reranking, co-occurrence PPR, and stage meta-learning

• ori_query_similar

  Semantic search (vector only, faster)

• ori_warmth

  Inspect the associative warmth field

• ori_explore

  Recursive graph traversal — PPR, sub-question decomposition, convergence detection

• ori_prune

  Activation topology analysis and archive candidates

• ori_index_build

  Build/update embedding index and bootstrap co-occurrence edges

• ori_status

  SELECT COUNT() FROM vnote

• ori_query_important

  SELECT title, pagerank FROM vnote ORDER BY pagerank DESC

• ori_query_fading

  oriprune, which its own description already deferred to

Open-source persistent memory infrastructure for AI agents. Ori implements human cognition as mathematical models on a knowledge graph. Activation decay from ACT-R. Spreading activation along wiki-link edges. Hebbian co-occurrence from retrieval patterns. Reinforcement learning on retrieval itself. Recursive graph traversal with sub-question decomposition. The system learns what matters, forgets what doesn't, and optimizes its own retrieval pipeline.

• agent-memory
• ai-agent
• ai-memory
• knowledge-graph
• llm
• markdown
• mcp
• mcp-server
• model-context-protocol
• persistent-memory