YantrikDB – persistent memory for AI agents
Bundled 7MB embedder means zero network calls or model downloads for agent memory.
Biological decay model for memory is a clever twist on standard vector stores.
AI engineers building long-context autonomous agents
Zep · Mem0 · LangChain Memory
Created a CLI command to infer knowledge from the context stored in memory system without any token utilization or llm call.
It comes with a memory dashboard to monitor and manage your memories it can be extended as audit trail for agents as well !
Bundled 7MB embedder means zero network calls or model downloads for agent memory.
Claims brain-like cognition with zero LLM calls, but zero evidence of actual learning.
Bi-temporal versioning with LLM-driven auto-supersede solves agent memory rot elegantly.
Ebbinghaus decay prunes memory automatically, unlike standard RAG hoarding.
Predict-calibrate extraction reduces noise, but Zep and Mem0 already dominate the agent memory space.
SQLite-backed agent memory with graph viz when Mem0 and Zep already dominate.