# volotat/mini-AGI > A byte-level continual-learning language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. An experiment showing continual learning without catastrophic forgetting is possible on modest hardware. - Magnitude: 0.7 out of 10 — Steady - Stars: 1,255 total · +0 stars measured 2026-10-19, 00:13–03:00 UTC, ≈ 2 by evening - Star trust: star growth looks organic - Category: Language models · Language: Python · License: MIT · Created: 2026-09-19 · Last push: 2026-10-17 - GitHub: https://github.com/volotat/mini-AGI · Page: https://gitnova.dev/en/r/volotat/mini-AGI ## Useful for - Train your own language model from scratch on an 8 GB VRAM laptop - Continue training the model on your own text corpus without forgetting - Study adaptive depth and expert routing in a toy model ## Why it’s here - Star-counter measurements on 2026-10-19 (UTC), 00:13–03:00: 1255 → 1255 stars (+0). This is the change over that interval. - Estimated end-of-day forecast: about +2 stars, using observed gains and the previous day. - The repository is 30 days old and already has 1,255 stars. - Hacker News: “Mini-AGI – dynamic continual learning model trained from scratch on 8GB VRAM” — 277 points, 27 days ago. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 203 - Issues and pull requests: 28 - Watchers: 25 - Average over the last week: 3 per day - Usual pace: 29 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: 3, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 10-06 2.0, 10-07 1.7, 10-08 1.3, 10-09 1.4, 10-10 1.4, 10-11 1.3, 10-12 1.1, 10-13 0.8, 10-14 0.1, 10-15 0.6, 10-16 0.9, 10-17 1.1, 10-18 1.2, 10-19 0.8 ## Hacker News - Mini-AGI – dynamic continual learning model trained from scratch on 8GB VRAM — 277 points, 80 comments: https://news.ycombinator.com/item?id=49783133 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-19 03:02 UTC, updated every 30 minutes.