🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
BytesAgain β€Ί Skills β€Ί Openclaw Memories
πŸ¦€ ClawHub

Openclaw Memories

by @arosstale

Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer w...

Versionv2.0.1
Downloads807
Installs1
#clawhub
TERMINAL
clawhub install openclaw-memory-2

πŸ“– About This Skill

name: openclaw-memories description: Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer work offline.

OpenClaw Memory System

Three components for agent memory:

1. ALMA β€” Evolves memory designs through mutation + evaluation (offline) 2. Observer β€” Extracts structured facts from conversations via LLM API (requires API key) 3. Indexer β€” Full-text search over workspace Markdown files (offline)

Environment Variables

Observer requires one of:

  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • Or pass apiKey in config

    • ALMA and Indexer require no keys or network access.

    How It Works

    ALMA (Algorithm Learning via Meta-learning Agents)

    Proposes memory system designs, evaluates them, keeps the best. Uses gaussian mutation and simulated annealing to explore the design space.

    alma.propose() β†’ design
alma.evaluate(design.id, metrics) β†’ score  
alma.best() β†’ top design
alma.top(5) β†’ leaderboard

    Observer

    Sends conversation history to an LLM, gets back structured facts:
  • Kind: world fact / biographical / opinion / observation
  • Priority: high / medium / low
  • Entities: mentioned people/places
  • Confidence: 0.0–1.0 for opinions

    • Fails gracefully β€” returns empty array if LLM is unavailable.

    Indexer

    Chunks workspace Markdown files and indexes them for search:
  • MEMORY.md β€” core facts
  • memory/YYYY-MM-DD.md β€” daily logs
  • bank/entities/*.md β€” entity summaries
  • bank/opinions.md β€” beliefs with confidence

    • indexer.index() β†’ count of chunks indexed
indexer.search('query') β†’ ranked results
indexer.rebuild() β†’ re-index from scratch

    Install

    npm install @artale/openclaw-memory

    Limitations

  • Indexer uses an in-memory mock database, not real SQLite FTS5. Search works but ranking is simplified.
  • Observer calls remote APIs β€” not offline. Only ALMA and Indexer work without network.
  • No dashboard β€” removed in v2 for simplicity.

    • Source

    5 files, 578 lines, 0 runtime dependencies.

    https://github.com/arosstale/openclaw-memory