vigmarcarlo/OntoPrune

Neuro-Symbolic Context Pruning Middleware for Local SLMs & Coding Agents (85% token reduction, 6.7x faster TTFT on CPU, 0% hallucinations)

1 best points · 0 comments · 1 Hacker News post · 3 GitHub stars · View on GitHub

Hacker News discussions

• OntoPrune – Pruning 85% LLM context tokens and 6.7x TTFT on CPU (1 points, 0 comments, by vigmarcarlo, 2026-10-05)