Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- 26.9k
MiniCPM-V
Open multimodal models for images, video, documents and speech on-device
- 33.8k
tinygrad
Small, readable deep learning framework with its own kernel compiler
- Andrej58.8k
nanochat
Minimal codebase for training a small chat LLM end to end on one GPU node
- 19.8k
olmOCR
PDF and image-to-Markdown converter built on a 7B vision-language model
ShiYu42.1k
- 11.2k
PersonaPlex
Full-duplex speech-to-speech model with prompt-set roles and voices
- 12.3k
TRELLIS.2
4B-parameter model that turns a single image into a textured 3D asset
52.2k
- 105k
DeepSeek-V3
Open-weight 671B Mixture-of-Experts language model with 128K context
- 17.2k
Qwen-Agent
Python framework for building tool-using agents on Qwen models
- 18.8k
Agent Lightning
Reinforcement learning framework for training LLM agents in real harnesses
- 34.7k
TimesFM
Pretrained foundation model for zero-shot time-series forecasting
- 39k
LangExtract
Python library for pulling structured, source-linked data out of text with LLMs
49.6k
- 54.9k
VibeVoice
Open speech recognition and text-to-speech models from Microsoft
- 111k
Whisper
Multilingual speech recognition and translation model with a CLI