YantrikDB is a cognitive memory database designed for AI agents. It models memory processes such as temporal decay, semantic consolidation, contradiction detection, and proactive triggers. The system functions as an embeddable library for Rust and Python, operates as an MCP server for AI tool integration, and supports multi-node deployment via Raft consensus. Data is stored in a single SQLite file utilizing unified indexes for vector, graph, temporal, and key-value operations.
- Website
- https://yantrikdb.com[01]
- Source Code
- https://github.com/yantrikos/yantrikdb[02]
- Developer
- Country of Origin
- IN
- Start Year
- 2026
- Project Types
- Hobby, Open Source
- Embeds / Uses
- SQLite
- License
- AGPL v3
YantrikDB is a cognitive memory database designed for AI agents. It models memory processes such as temporal decay, semantic consolidation, contradiction detection, and proactive triggers. The system functions as an embeddable library for Rust and Python, operates as an MCP server for AI tool integration, and supports multi-node deployment via Raft consensus. Data is stored in a single SQLite file utilizing unified indexes for vector, graph, temporal, and key-value operations.
Citations
3 sources- YantrikDB — Cognitive Memory Database for AI Agents | YantrikDB yantrikdb.com
- GitHub - yantrikos/yantrikdb: Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP github.com
- https://github.com/yantrikos/yantrikdb/commit/da3caabbfed93a0a9c016e8691a6495ae9e5bf26 github.com