Infini-AI-Lab open-sources Hermit: continual learning via reusable adapters, no model changes
udmrzn · x · 2026-10-28
Infini-AI-Lab has open-sourced Hermit, a harness evolution framework for continual learning and RSI (recursive self improvement). The core idea: an agent's experience should improve the agent that takes on the next task.
Hermit trains reusable adapters without changing your model or harness, unifying multiple continual-learning methods in one framework. Available at github.com/Infini-AI-Lab/hermit.
Related event: Infini-AI-Lab Open-Sources Hermit for Evolving Agent Harnesses(2 posts)→
More from coding & agent
- Supercharging LLM classification with logprobs: soft classifiers you can threshold-tune — JnBrymn · 2026-10-28
- Codex daily build series day 23: skipping iCloud plugins for a reset — dotey · 2026-10-28
- Cloudflare Access adds fully customizable pages with HTML + Liquid templates — dinasaur_404 · 2026-10-28
- Opus retried every session 20.6 million times during a memory leak hunt — johnlindquist · 2026-10-28
- Open-Source Skill Teaches AI Agents to Design and Produce Videos — songguoxiansen · 2026-10-28
- Not Everything Needs an Agent: Fixed Steps Are Recipes, Save Agents for Judgment — adamse · 2026-10-28