by yantrikos · MCP Server · ★ 37
YantrikDB — A Cognitive Memory Engine for Persistent AI Systems The memory engine for AI that actually knows you. Get Started in 60 Seconds For AI agents (MCP — works with Claude, Cursor, Windsurf, Copilot) Add to your MCP client config: That's it. The agent auto-recalls context, auto-remembers decisions, and auto-detects contradictions — no prompting needed. See yantrikdb-mcp for full docs. As a Python library The engine ships a default embedder (, 7 MB, distilled from BGE-base-en-v1.5) — / work out of the box. No install. No first-run model download. No ONNX runtime. Just one .
| Stars | 37 |
| Forks | 8 |
| Language | Rust |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 61.9533528700089/100 |
| Open Issues | 10 |
| Last Updated | 2026-06-29 |
| Created | 2026-02-23 |
| Platforms | claude-code, mcp, rust |
| Est. Tokens | ~27k |
These tools work well together with yantrikdb for enhanced workflows:
Explore other popular mcp server tools:
yantrikdb is 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 ya. It is categorized as a MCP Server with 37 GitHub stars.
yantrikdb is primarily written in Rust. It covers topics such as agent-memory, ai-agents, anthropic.
You can find installation instructions and usage details in the yantrikdb GitHub repository at github.com/yantrikos/yantrikdb. The project has 37 stars and 8 forks, indicating an active community.
yantrikdb is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.