Developer Tools●●●Banger
GEKO (up to 80% compute savings on LLM fine-tuning)
Mountain Curriculum routing: 5× compute to hard samples, skip mastered ones.
Big BrainWizardryShip It
SyedAbdurR2hman
113mo ago
Back to browse
GitHub Repository
The personal AI that actually remembers what you teach it. Corrections become lessons + temporal-KG facts, retrieved on every future answer. Measured, not asserted. 69 monitors, fully local.
14 starsPython
Nova–Self-hosted personal AI learns from corrections &fine-tunes itself
by heliosnova·Mar 15, 2026·3 points·3 comments
AI Analysis
●●SolidBig BrainNiche Gem
DPO self-fine-tuning from corrections in a sea of Open WebUI clones.
Strengths
- •DPO training pair generation from corrections is a clever self-improvement pipeline
- •Hybrid retrieval with Vector + BM25 + RRF beats vector-only competitors
- •Bundled Ollama means genuine zero-cloud operation out of the box
Weaknesses
- •Personal AI assistant category is extremely crowded with established players
- •20GB+ VRAM requirement limits accessibility for most users
Category
Target Audience
Privacy-conscious developers running local LLMs
Similar To
Open WebUI · Khoj · Continue
Similar Projects
AI/ML●●Solid
Shard-based scheduling for 100x more fine-tuning experiments on 4 GPUs
Shard-based scheduling cuts GPU wait time, though Ray Tune offers similar early stopping.
Big BrainSolve My Problem
kamranrapidfire
102mo ago
AI/ML●Mid
OpenAI CLIP fine tuned on Galaxy morphology
Galaxy classification model, but model card has mostly empty fields.
Niche Gem
mjupp1
102mo ago
AI/ML●●Solid
Pre-training, fine-tuning, and evals platform
Eval-synthesize-train loop automates custom model development better than manual fine-tuning.
SlickBold Bet
oli_kitty
402mo ago
AI/ML●●Solid
Flint – A 30B model fine-tuned for less repetition
Fine-tuned Qwen 30B that prioritizes output diversity over convergent accuracy.
Niche GemSolve My Problem
thmsmxwll
621mo ago
AI/ML●●●Banger
ShadowPEFT – Centralized and Detachable Parameter-Efficient Fine-Tuning
Detachable PEFT modules that version independently, unlike LoRA's weight-coupled adapters.
Big BrainZero to OneNiche Gem
yokee
621mo ago