Lily Memory#

Persistent memory plugin for OpenClaw agents. Gives your agent long-term memory that survives session resets, compaction, and restarts.

What It Does#

• Auto-recall: Injects relevant memories as context before each LLM turn
• Auto-capture: Extracts facts from conversations and stores them automatically
• Hybrid search: SQLite FTS5 keyword search + Ollama vector cosine similarity
• Stuck detection: Detects topic repetition and nudges the agent to break loops
• Memory consolidation: Deduplicates entries on startup
• Dynamic entities: Config-driven allowlist + runtime tool to add entities
• Graceful degradation: Works without Ollama (keyword-only mode)
• Zero npm dependencies: Uses sqlite3 CLI + native fetch

Requirements#

• Node.js 18+ (for native fetch)
• SQLite 3.33+ with FTS5 (ships with macOS; apt install sqlite3 on Linux)
• Optional: Ollama with nomic-embed-text model for semantic search

Quick Start#

1. Install the plugin to your extensions directory
2. Add to your openclaw.json:

json

{
  "plugins": {
    "slots": { "memory": "lily-memory" },
    "entries": {
      "lily-memory": {
        "enabled": true,
        "config": {
          "dbPath": "~/.openclaw/memory/decisions.db",
          "entities": ["config", "system"]
        }
      }
    }
  }
}

1. Restart the gateway: openclaw gateway restart

Tools#

ToolDescriptionmemory_searchFTS5 keyword search across all factsmemory_entityLook up all facts for a specific entitymemory_storeSave a fact to persistent memorymemory_semantic_searchVector similarity search via Ollamamemory_add_entityRegister a new entity at runtime

Configuration#

OptionTypeDefaultDescriptiondbPathstring~/.openclaw/memory/decisions.dbSQLite database pathautoRecallbooleantrueInject memories before each turnautoCapturebooleantrueExtract facts from responsesmaxRecallResultsnumber10Max memories per turnmaxCapturePerTurnnumber5Max facts per responsestuckDetectionbooleantrueTopic repetition detectionvectorSearchbooleantrueOllama semantic searchollamaUrlstringhttp://localhost:11434Ollama endpointembeddingModelstringnomic-embed-textEmbedding modelconsolidationbooleantrueDedup on startupvectorSimilarityThresholdnumber0.5Min cosine similarityentitiesarray[]Additional entity names

Architecture#

Recall flow: Extract keywords from message -> FTS5 + vector search -> merge and deduplicate -> inject as context

Capture flow: Regex scan for entity: key = value patterns -> validate entity against allowlist -> store to SQLite -> async embed via Ollama

Stuck detection: Track top 5 content words per response -> Jaccard similarity -> if 3+ consecutive >60% overlap, inject Reflexion nudge

License#

MIT