remete618/widemem-ai

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

50
/ 100
Established

Implements a three-tier hierarchical storage (facts → summaries → themes) with automatic LLM-powered conflict resolution that batches contradictions into single API calls, reducing costs and maintaining consistency. Built on SQLite + FAISS locally with pluggable LLM providers (OpenAI, Anthropic, Ollama) and vector stores (Qdrant), plus confidence-aware retrieval modes (fast/balanced/deep) that detect and flag low-confidence answers instead of hallucinating.

Available on PyPI.

Maintenance 13 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 12 / 25

How are scores calculated?

Stars

2

Forks

1

Language

Python

License

Last pushed

Mar 12, 2026

Monthly downloads

137

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/remete618/widemem-ai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.