-
Harvard Medical School
- Boston
- wingillis.github.io
- https://orcid.org/0000-0002-1659-8639
Stars
Fully local web research and report writing assistant
Local AI voice assistant stack for Home Assistant (GPU-accelerated) with persistent memory, follow-up conversation, and Ollama model recommendations - settings designed for low VRAM systems.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Vizro is a low-code toolkit for building high-quality data visualization apps.
The simplest, fastest repository for training/finetuning small-sized VLMs.
A meta-framework for self-improving LLMs with transparent reasoning
Reference PyTorch implementation and models for DINOv3
🏋 Modern open-source fitness coaching platform. Create workout plans, track progress, and access a comprehensive exercise database.
Pydantic AI Research Agent Built with the PRP Framework Template
Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬
Open-source implementation of AlphaEvolve
MAESTRO is an AI-powered research application designed to streamline complex research tasks.
Official Repository of Absolute Zero Reasoner
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
GenAI Agent Framework, the Pydantic way
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
Train your AI self, amplify you, bridge the world
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Torch-activation, a library of activation functions for PyTorch library
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero
Simplifying reinforcement learning for complex game environments
Convert PDF to markdown + JSON quickly with high accuracy
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.