Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM
What changed
mini-AGI - is a continual learning byte-level language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. It stores its weights as ordinary files on disk and pages them onto the card as it needs them, so the parameter count is bounded by free disk space rather than by VRAM. It grows new capacity while training when it runs short, prunes what nothing asks for, and reads through exactly the same code path it serves on.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
- Launch HN: Speko (YC S26) – OpenRouter for Voice AI
- Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
Sources
- Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM (hn-frontpage)primary