# cortexreach/memory-lancedb-pro **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/cortexreach-memory-lancedb-pro).** _How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._ 4,449 stars · 725 forks · JavaScript ## Links - GitHub: https://github.com/CortexReach/memory-lancedb-pro - Homepage: https://www.bilibili.com/video/BV1iWwtztEQf/ - awesome-repositories: https://awesome-repositories.com/repository/cortexreach-memory-lancedb-pro.md ## Topics `lancedb` `memory` `openclaw` `openclaw-agent` `openclaw-plugin` `rag` ## Description memory-lancedb-pro is a plugin that gives AI agents persistent long-term memory stored in LanceDB. It saves and recalls facts, preferences, decisions, and entities across conversations, capturing new memories after each turn and injecting relevant ones into the agent's context before each reply, with no manual save command needed. What sets it apart is how memories are extracted and retrieved. A language model classifies conversation content into profile, preference, entity, event, case, and pattern categories, then deduplicates and merges results before storage. Recall blends vector similarity with BM25 keyword matching and can reorder results with a cross-encoder reranker. Memories are also separated into global, agent, user, project, and custom scopes, with per-agent rules that block reads or writes to scopes an agent is not permitted to use. Beyond that core, the plugin scores memories by recency, access frequency, and importance, so stale entries fade while frequently recalled ones move between core, working, and peripheral tiers. It filters out low-quality content such as refusals and greetings, saves a session summary when a new chat starts, and can index memory files and transcripts so search returns file paths, line spans, and citations. Embeddings can come from any OpenAI-compatible provider, and concurrent writers are coordinated with a file lock, optionally upgraded to a Redis lock when several machines share a store. A command-line tool lists, searches, exports, imports, re-embeds, upgrades, and migrates stored memories, and a setup script handles installing, upgrading, and repairing the plugin in one command. ## Tags ### Artificial Intelligence & ML - [Agent Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-stores.md) — Gives AI agents persistent long-term memory in LanceDB, saving and recalling facts, preferences, and decisions across conversations without manual save commands. - [Automatic Memory Extractors](https://awesome-repositories.com/f/artificial-intelligence-ml/automatic-memory-extractors.md) — Extract preferences, facts, decisions, and entities from conversations after each turn, remove duplicates, and store them without requiring any manual save command from the user. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) - [Memory Structuring](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing-analysis/memory-structuring.md) — Classify conversation content into profile, preference, entity, event, case, and pattern categories using a language model, then store layered summaries with duplicate detection and merge rules. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) - [Memory Decay Scoring](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-decay-scoring.md) — Score each memory by recency, access frequency, and importance so rarely used or low-value items decay while frequently recalled ones persist and move between core, working, and peripheral tiers. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) - [Cross-Encoder Rerankers](https://awesome-repositories.com/f/artificial-intelligence-ml/result-reranking/cross-encoder-rerankers.md) — Reorder retrieved memories using a cross-encoder reranking provider, then blend that relevance score with the original ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) ### Part of an Awesome List - [Automated Memory Pipelines](https://awesome-repositories.com/f/awesome-lists/ai/continual-learning/automated-memory-pipelines.md) — Uses a language model to classify conversation content into typed memory categories, then deduplicates and merges results before storing them as long-term memory. ### Data & Databases - [Hybrid Vector-Keyword Indexing](https://awesome-repositories.com/f/data-databases/hybrid-vector-keyword-indexing.md) — Blends embedding similarity search with BM25 keyword matching so stored memories are found by both meaning and exact terms. - [Contextual Memory Recall](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/contextual-memory-recall.md) — Search stored memories with combined vector and keyword matching, then inject the most relevant entries into the agent's context before each reply so past knowledge informs the answer. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) - [LLM-to-Structured Data Converters](https://awesome-repositories.com/f/data-databases/structured-data-extraction/llm-to-structured-data-converters.md) — Sends conversation text to a language model that classifies it into typed categories, then deduplicates and merges results before storage. - [Salience-Based Decay Engines](https://awesome-repositories.com/f/data-databases/tiered-caching-systems/multi-tier-memory-systems/salience-based-decay-engines.md) — Ranks memories by recency, access frequency, and importance so stale entries fade while frequently recalled ones are promoted across core, working, and peripheral tiers. - [Vector Memory Stores](https://awesome-repositories.com/f/data-databases/vector-memory-stores.md) — Persists memories and their vectors in a local columnar database that runs inside the host process without a separate server. ### Development Tools & Productivity - [Memory Management CLIs](https://awesome-repositories.com/f/development-tools-productivity/memory-management-clis.md) — List, search, delete, export, import, re-embed, upgrade, and migrate stored memories with terminal commands, and sign in through OAuth for the extraction model. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme)) ### Security & Cryptography - [Scope-Based Isolation](https://awesome-repositories.com/f/security-cryptography/policy-based-access-control/scope-based-isolation.md) — Tags every memory with a namespace such as global, agent, user, or project and enforces per-agent read and write rules on each query. ### User Interface & Experience - [Memory Scoping](https://awesome-repositories.com/f/user-interface-experience/context-scoping/memory-scoping.md) — Separates stored memories into global, agent, user, project, and custom scopes, with per-agent rules blocking reads or writes to scopes an agent may not use. ([source](https://github.com/cortexreach/memory-lancedb-pro#readme))