{"id":"robotmem-robotmem","name":"robotmem","af_score":53.8,"security_score":27.2,"reliability_score":22.5,"what_it_does":"robotmem is a persistent memory system for robotic/agent experiences. It records episodic robot experience (parameters/strategies/trajectories/outcomes), stores perception data, and retrieves relevant past memories using hybrid search (BM25 + vector) with structured JSON filtering and optional spatial nearest-neighbor sorting. It can also run as an MCP server (7 tools) or be used directly via Python imports, with an embedded local SQLite database.","best_when":"You have robotics/agent experiments where you can run a local persistent SQLite-backed memory store and want structured + spatially informed retrieval to guide future decisions.","avoid_when":"You need a hosted service with enterprise-grade security, centralized access control, and documented SLAs, or you cannot store data locally.","last_evaluated":"2026-03-30T15:35:28.306913+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["No documented rate limiting behavior (local usage likely, but MCP/UI could differ).","Structured filtering expects specific JSON field paths and operators (e.g., $lt); incorrect schema/paths may lead to empty/incorrect recall without clear guidance.","Spatial sorting depends on consistent coordinate field naming and the expected 'spatial.*' structure; mismatches may reduce retrieval quality."],"error_quality":0.0}