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

Memory Oracle

by @oleglegegg

Persistent structured memory system for OpenClaw agents with SQLite storage, hybrid search (FTS5 + decay scoring), rule-based capture, LLM-powered daily refl...

Versionv1.0.2
βš™οΈ Configuration

All thresholds live in config/settings.json. Key tunables:

  • recall_budget_tokens: Total injection budget (default: 2000)
  • decay_rate: Daily score decay multiplier (default: 0.05)
  • archive_threshold: Score below which facts move to cold (default: 0.2)
  • delete_threshold: Score below which cold facts are purged (default: 0.05)
  • delete_min_age_days: Minimum age before deletion (default: 90)
  • reflect_deep_day: Day of week for deep reflection, 0=Mon (default: 0)
  • api_model: Model for HEAVY process (default: claude-sonnet-4-20250514)
  • api_max_tokens: Max response tokens for LLM calls (default: 1000)
  • View on ClawHub
    TERMINAL
    clawhub install memory-oracle

    πŸ§ͺ Use this skill with your agent

    Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

    πŸ” Can't find the right skill?

    Search 60,000+ AI agent skills β€” free, no login needed.

    Search Skills β†’