onestardao/WFGY

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

11 best points · 40 comments · 15 Hacker News posts · 1,804 GitHub stars · View on GitHub

Hacker News discussions

Show HN: WFGY – A reasoning engine that repairs LLM logic without retraining (11 points, 6 comments, by WFGY, 2025-06-18)
Show HN: TXT OS – Open-Source AI Reasoning, One Plain-Text File at a Time (10 points, 6 comments, by TXTOS, 2025-07-13)
Show HN: I open-sourced a $1M engine for closing loops in embedding space (8 points, 10 comments, by WFGY, 2025-06-28)
Show HN: WFGY – Endorsed by Tesseract.js dev, 2k+ downloads/month live (7 points, 3 comments, by TXTOS, 2025-07-23)
Show HN: Achieves Perfect 100 Score Across 6 Leading AI Model Evaluations (6 points, 8 comments, by TXTOS, 2025-07-16)
Show HN: Subtle Failure Modes I Keep Seeing in Production‑Grade AI Systems (6 points, 2 comments, by TXTOS, 2025-07-30)
Show HN: A tiny reasoning layer that steadies LLM outputs (MIT; +22.4% accuracy) (6 points, 0 comments, by TXTOS, 2025-08-04)
Show HN: 70 Days → 800 GitHub Stars (Cold Start) – My Secret Was a Problem Map (5 points, 1 comments, by tgrrr9111, 2025-08-26)
Show HN: Txtos for LLMs – 60 SEC setup, long memory, boundary guard, MIT (5 points, 1 comments, by tgrrr9111, 2025-08-28)
Show HN: 70 days, 800 stars. If AI bugs are not random but math inevitable? (5 points, 1 comments, by tgrrr9111, 2025-08-31)
We open-sourced a 'Semantic Clinic' for LLM bugs – 16 root causes (4 points, 1 comments, by TXTOS, 2025-08-07)
Show HN: I made a semantic OS for language reasoning (not kidding) (3 points, 0 comments, by TXTOS, 2025-08-01)
Show HN: AGI Lite for Free,Semantic AI boost with WFGY(stability ×3.6, open SDK (2 points, 1 comments, by PSBigBig, 2025-06-15)
Show HN: "hard questions" as a shared language for cross-domain reasoning (2 points, 0 comments, by wfgy-github, 2026-02-11)
Show HN: A text-only reasoning core for LLMs (MIT, system prompt and self-test) (1 points, 0 comments, by wfgy-github, 2026-02-14)