{"id":"agentic-box-memora","name":"memora","af_score":56.0,"security_score":50.5,"reliability_score":26.2,"what_it_does":"Memora is a lightweight MCP-compatible memory server that provides persistent semantic memory storage (SQLite with optional cloud sync), knowledge-graph linking, and a graph UI. It supports embeddings-based semantic search, RAG chat with tool calling, and LLM-assisted deduplication/merge workflows.","best_when":"You want an MCP server-based memory layer that an agent can call locally (stdio MCP) or via a streaming HTTP transport, with optional cloud backing and a visualization UI.","avoid_when":"You need strict, standardized API contracts (OpenAPI/SDK), or you cannot tolerate operational complexity around LLM providers, embeddings models, or cloud database credentials.","last_evaluated":"2026-03-30T13:33:00.060741+00:00","has_mcp":true,"has_api":false,"auth_methods":["Cloudflare D1 access via CLOUDFLARE_API_TOKEN (for d1:// storage URI)","AWS/R2/S3 access via AWS_PROFILE / AWS credentials (for s3:// storage URI)","OpenAI-compatible API key via OPENAI_API_KEY (for embeddings and LLM dedup/chat if enabled)"],"has_free_tier":false,"known_gotchas":["Embedding model changes require rebuilding embeddings and cross-references (manual operational step).","LLM deduplication/chat may fail if the configured OpenAI-compatible endpoint/model does not support required tool/function calling behavior.","Cloud DB modes rely on correct environment variables/credentials; misconfiguration can prevent storage access."],"error_quality":0.0}