Back to directory

memory-lancedb-pro

A LanceDB-backed long-term memory plugin for OpenClaw agents that auto-captures preferences, decisions, and project context, then recalls them with hybrid vector and keyword search.

memory-lancedb-pro

memory-lancedb-pro is a LanceDB-backed memory plugin for OpenClaw that stores preferences, decisions, and project context, then automatically recalls them in future sessions without manual tagging. It captures what matters from every conversation automatically, using LLM-powered classification into six categories, profiles, preferences, entities, events, cases, and patterns, and lets older, less relevant memories fade through a decay model while important ones are kept.

Retrieval combines vector search with BM25 full-text search, fused and reordered with a cross-encoder reranker, and relevant memories are injected into context automatically rather than through a manual store call. It supports multiple isolated memory scopes across agents and sessions, and ships a management command-line interface alongside the plugin itself. The current release adapts the plugin to OpenClaw's newer plugin architecture, replacing a deprecated hook with a new one triggered before a prompt is built.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.