Maverick0351a/Oscillink
Oscillink — Self‑Optimizing Coherent Memory for Embedding Workflows
Implements physics-inspired convex energy minimization over mutual-kNN graphs to refine embedding coherence, solving via preconditioned conjugate gradients with deterministic SHA-256 audit receipts. Agnostic to embedding source (OpenAI, Sentence-Transformers, custom models) and requires no retraining. Targets RAG pipelines and retrieval systems with <40ms latency on commodity CPUs while providing per-decision diagnostics and hallucination mitigation.
Available on PyPI.
Stars
16
Forks
2
Language
Python
License
—
Category
Last pushed
Nov 24, 2025
Monthly downloads
28
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Maverick0351a/Oscillink"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
mem0ai/mem0
Universal memory layer for AI Agents
memodb-io/memobase
User Profile-Based Long-Term Memory for AI Chatbot Applications.