Lists (9)
Stars
Reverse engineer anything with agents, from app behavior down to native binaries.
A cube that balances itself in a corner or edge using reaction wheels
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
TonyCardillo / NPC-Forge
Forked from gioblu/NPC-Forge(macOS fork) NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs.
MiniCPM5: SOTA on-device LLMs, small yet powerful.
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Unified Schema-Based Information Extraction
Compresses LLM prompts to cut token cost while preserving meaning, with measured before/after numbers rather than claims.
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
The open-source neuro-symbolic AI agent framework.
A modular, multi-node ESP32 anti-tracking decoy swarm. summon the crowd, bury the signal.
A spaCy wrapper of Entity-Fishing (component) for named entity disambiguation and linking on Wikidata
In this project, I used Hebbian, Perceptron and Adaline neural networks to implement AND gate, and OR gate.
Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.
A lightweight and flexible framework for Hebbian learning in PyTorch.
Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686
👋 Motion detection using the doppler effect
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Minimal RNN classifier with self-attention in Pytorch
AI classifier for indicating AI-written text