volotat/mini-AGI
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.
About the project
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.
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
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 43 stars so far today, about 79 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 59 stars.
- Hacker News: “Mini-AGI – dynamic continual learning model trained from scratch on 8GB VRAM” — 42 points, 3 h ago.
- About 48 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 59
- Stars in a day
- 79
- Forks
- 9
- Issues and pull requests
- 3
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 19, 2026
- Last push
- September 21, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Mini-AGI – dynamic continual learning model trained from scratch on 8GB VRAM42 points, September 21, 2026
Spotted in
- September 21, 2026Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/volotat/mini-AGI)Similar projects
-
8.6
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
-
7.6
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
-
7.2
bespokelabsai/nimble
Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition…
-
7.0
FareedKhan-dev/train-llm-from-scratch
Educational project: a from-scratch PyTorch Transformer plus a full LLM training pipeline — from raw text through SFT, reward modeling, PPO/DPO/GRPO to chat, without transformers, trl or peft.
-
6.9
mizorewww/laya-coreml
Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.
-
6.9
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.