vstorm-co/memv
Structured, temporal memory for AI agents.
Extracts facts only when the model fails to predict them, reducing noise through prediction error rather than upfront scoring. Implements bi-temporal validity tracking (event time vs. transaction time) with hybrid retrieval combining vector similarity, BM25 text search, and reciprocal rank fusion. Supports SQLite for local development and PostgreSQL with pgvector for production, integrating with PydanticAI, LangGraph, LlamaIndex, CrewAI, and AutoGen.
Stars
51
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/vstorm-co/memv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Higher-rated alternatives
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent,...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents