Vibe Coding Discoveryantrikdb-server
View on GitHubCognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.
YantrikDB is a Rust cognitive memory engine for AI agents: a vector/knowledge store that consolidates duplicates, detects contradictions, and decays stale memories. Ship it as an embeddable library, HTTP/HA cluster, or MCP server with 15 memory tools.
Use Cases
Give coding agents like Claude Code, Cursor and Windsurf persistent memory over MCPConsolidate duplicate agent memories into canonical entriesDetect and resolve contradictory facts across agent sessionsFade stale memories with configurable temporal decayStore and query entities/relations as a knowledge graphCut context tokens vs dumping CLAUDE.md memory filesShare one memory store across machines or teammates via HA clusterRecord and reinforce procedural strategies for agentsDerive user personality/preference traits from memory patternsSurface proactive triggers for conflicts, deadlines and decaying factsEmbed a semantic memory engine directly in Python or Rust appsRun a multi-tenant memory service over HTTP with quotas and metrics
Built With
- Language
- Rust
- Frameworks
- FastAPI · sentence-transformers · PyO3 · maturin · uvicorn · LangChain · CrewAI · OpenAI · Docker · Prometheus · SQLite · PyTorch
Tags
agent-memory · cognitive-memory · vector-database · embeddings · mcp-server · knowledge-graph · semantic-memory · temporal-decay · memory-consolidation · contradiction-detection · hnsw · rust · self-hosted · persistent-memory · clustering · llm