{"id":"cortexreach-memory-lancedb-pro","name":"memory-lancedb-pro","homepage":"https://youtu.be/bhuGrjuCM_g","repo_url":"https://github.com/CortexReach/memory-lancedb-pro","category":"ai-ml","subcategories":[],"tags":["openclaw","openclaw-plugin","lancedb","memory","hybrid-retrieval","bm25","vector-search","cross-encoder-rerank","reranking","mmr","multi-scope","cli","typescript","rag"],"what_it_does":"memory-lancedb-pro is an OpenClaw plugin that provides long-term “memory” storage and hybrid retrieval on top of LanceDB. It combines vector (ANN) search with BM25 full-text search, fuses results, applies cross-encoder reranking, and runs a multi-stage scoring pipeline including recency/importance/length normalization/time decay plus diversity (MMR). It also supports multi-scope isolation, auto-capture/auto-recall hooks in the OpenClaw lifecycle, optional Markdown mirroring, long-context embedding chunking, and a management CLI for memory CRUD/migration/reindexing.","use_cases":["RAG systems needing long-term memory with both semantic and keyword recall","Agentic assistants that must retrieve relevant prior facts/preferences across sessions","Projects that want hybrid retrieval with reranking and recency/decay weighting","Multi-tenant or multi-agent environments requiring scoped memory isolation","Teams that need memory management operations (import/export, migrate, reembed) via CLI"],"not_for":["Production deployments that require a network-accessible REST/GraphQL service API from this package alone","Use cases needing fine-grained, per-record user authorization enforced externally (the plugin appears to implement logical scoping inside OpenClaw, not cryptographic enforcement)","Organizations that cannot store any memory content locally/offline (LanceDB storage plus optional Markdown mirror)"],"best_when":"Used as an OpenClaw plugin in a TypeScript/Node environment where agents can call the plugin’s tools/hooks and where LanceDB + an embedding provider (OpenAI-compatible) are acceptable.","avoid_when":"Avoid if you cannot run the plugin inside OpenClaw’s plugin lifecycle or if you require a standardized external API (REST/GraphQL/GRPC) with OpenAPI/SDK contracts; also avoid if you need strict compliance guarantees that are not documented (e.g., data residency/compliance).","alternatives":["OpenClaw built-in memory-lancedb (basic vector search)","Other RAG memory stores that provide hybrid search (vector + BM25) via a single managed service or self-hosted stack","Local search libraries with OpenAI-compatible embeddings plus a separate BM25 engine (e.g., Elasticsearch/OpenSearch hybrid)"],"af_score":69.8,"security_score":59.0,"reliability_score":36.2,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-29T15:05:24.415801+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":["TypeScript","JavaScript"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["OpenAI-compatible embedding provider API key / auth configuration (implied by OpenAI dependency and OpenAI-compatible wording)"],"oauth":false,"scopes":false,"notes":"Authentication is primarily to external embedding/reranker endpoints (OpenAI-compatible and “compatible endpoint” mentions). The README focuses on configuration behavior rather than a formal auth method list (e.g., API key vs bearer token) or per-scope authorization with the external endpoints."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing for the plugin itself is not described; costs depend on the embedding/reranking providers used (not specified here)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":69.8,"security_score":59.0,"reliability_score":36.2,"mcp_server_quality":0.0,"documentation_accuracy":70.0,"error_message_quality":80.0,"error_message_notes":"README explicitly claims “actionable error messages” for common embedding failures (401/403, network errors, 429, 404, context length exceeded with automatic chunking). However, the provided snippet is descriptive and does not show concrete error formats/codes.","auth_complexity":70.0,"rate_limit_clarity":55.0,"tls_enforcement":60.0,"auth_strength":55.0,"scope_granularity":70.0,"dependency_hygiene":55.0,"secret_handling":55.0,"security_notes":"Strengths: multi-scope isolation is explicitly described (global, agent:<id>, custom, project, user). Security posture around transport and secrets is not fully evidenced in the provided content; embedding provider calls likely use HTTPS but TLS enforcement is not documented here. Secret handling practices (e.g., logging/never logging) are not verifiable from the snippet. Dependency hygiene cannot be assessed from the provided manifest beyond presence of common libs.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":30.0,"error_recovery":75.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":true,"known_agent_gotchas":["This is a plugin integrated into OpenClaw lifecycle hooks; an external agent expecting a standalone HTTP API will not find one.","Cross-encoder reranking depends on an external compatible endpoint; behavior includes fallback on API failure, so results may vary.","Hybrid scoring and diversity thresholds (minScore, MMR demotion threshold, age half-lives) can materially change recall; agents should be configured/tuned rather than assuming stable ranking.","Memory management CLI exists, but whether tool calls are strictly idempotent for repeated operations is not documented in the provided content."]}}