shakewingo/Tadpole

Build an LLM agent from scratch and continuously evolve it.

3 best points · 0 comments · 1 Hacker News post · 47 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Tadpole – an LLM agent built from scratch then post-trained on 4B model (3 points, 0 comments, by shakewingo, 2026-10-31)