---

name: openmemory description: Persistent long-term agent memory for storing and querying past work, patterns, and learnings. agents: [blaze, rex, nova, tap, spark, grizz, bolt, cleo, cipher, tess, morgan, atlas, stitch] triggers: [memory, remember, store, recall, past work, similar, previous]

OpenMemory (Persistent Agent Memory)

You have access to OpenMemory for persistent long-term memory across sessions.

Memory Tools

Memory Sectors

Memories are classified into sectors:

Usage Patterns

Before starting a task:

Copyopenmemory_query({ query: "similar implementations", sector: "episodic" })

After completing a task:

Copyopenmemory_store({ 
  content: "Implemented OAuth2 with PKCE for React app using Effect",
  sector: "episodic",
  tags: ["auth", "react", "effect"]
})

For important learnings:

Copyopenmemory_reinforce({ memory_id: "mem_xyz", boost: 1.5 })

Best Practices

1. Query before implementing - Check for similar past work
2. Store after completing - Save successful patterns and solutions
3. Reinforce important memories - Boost salience of critical learnings
4. Tag memories well - Include relevant technologies and patterns