nemori-ai/nemori
A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.
Segments multi-turn conversations into semantically coherent episodes via LLM-powered boundary detection and predictive learning loops, then surfaces queryable knowledge through a dual-backend architecture (PostgreSQL for metadata/text search, Qdrant for vector similarity). Includes async Python bindings, pluggable LLM/embedding clients (OpenAI/OpenRouter), multimodal image support, and production-grade concurrency with Docker Compose infrastructure for PostgreSQL and Qdrant.
174 stars.
Stars
174
Forks
13
Language
Python
License
MIT
Category
Last pushed
Dec 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/nemori-ai/nemori"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
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