adrida/tracer

Distill your LLM traces into a fast hybrid System 1 models. Open-source ML + LLM inference with calibrated deferral.

2 best points · 1 comments · 2 Hacker News posts · 1,036 GitHub stars · View on GitHub

Hacker News discussions

• Trace-Based Adaptive Cost-Efficient Routing (2 points, 1 comments, by nlpnerd, 2026-06-09)
• (OSS) >90% of LLM calls don't need an LLM and could be replaced by classic ML (1 points, 0 comments, by adam_rida, 2026-03-31)