Show HN: Mini-AGI — a dynamic continual learning model trained on 8GB VRAM
petrusenko_max · x · 2026-09-22
A Show HN post presents Mini-AGI, a dynamic continual learning model that its author says can be trained on just 8GB of VRAM, making continual-learning experiments accessible on consumer hardware.
Related event: Developer Trains 530M-Parameter Continual Learning Model on 8GB Laptop(2 posts)→
More from coding & agent
- Building an image rating tool with GPT Vision and Jev: what worked and what didn't — huangyun_122 · 2026-09-22
- Dev ditches throttled GitHub Actions, open-sources dsr for local releases via act — doodlestein · 2026-09-22
- Nous ships official plugin to run Hermes Agent on Claude Pro/Max subscriptions, no API key — Teknium · 2026-09-22
- Kos raises $12M from 8VC to build AI finance agents for data center invoices — ahelkky · 2026-09-22
- Harrison Chase on decision models: agentic systems are just good engineering around models — Hacubu · 2026-09-22
- LangSmith Integrates Jev for Cheap Large-Scale Trace Mining That Feeds Directly Into Evals — hwchase17 · 2026-09-22