Vibe Coding Discovermentedb
View on GitHubA cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.
MenteDB is a Rust database engine for AI agent memory, combining vector and BM25 search, knowledge graphs, and cognitive extraction and consolidation. It provides SDKs, REST, and MCP integrations for persistent memory and context retrieval.
Use Cases
Give AI agents persistent conversational memoryExtract and organize facts from conversationsRetrieve relevant memories within a token budgetTrack changing or contradictory facts over timeShare isolated memory spaces across agents
Built With
- Language
- Rust
- Frameworks
- LangChain · CrewAI · MCP
Tags
agent memory · vector database · knowledge graph · hybrid search · embeddings · context assembly · memory extraction · contradiction detection · Rust · MCP