YantrikDB Server
What it is
YantrikDB is a cognitive memory database for AI agents written in Rust that manages memory through consolidation, contradiction detection, and temporal decay. It is distributed as a library, an MCP server, and an HTTP cluster to provide a persistent, self-organizing memory layer for autonomous agents.
The problem it solves
Standard vector databases store memories but do not manage them, leading to degraded recall quality and excessive token usage as memory counts grow without consolidation or forgetting mechanisms.
What you could use it for
- Providing long-term memory for AI agents in IDEs like Claude Code and Cursor via MCP
- Resolving conflicting facts in agent knowledge bases
- Reducing token usage by consolidating duplicate memories
- Implementing temporal decay for stale information in agent contexts
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.