Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
173 repos
-
TabICLv2: An open tabular foundation model
-
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
-
Access large language models from the command-line
-
Open-source framework for the research and development of foundation models.
-
A framework for few-shot evaluation of language models.
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Train transformer language models with reinforcement learning.
-
Convert models to GGUF
-
A Python library encapsulating best practices for rubric-based evaluation of LLM/VLM outputs using AI judges such as LLMs and decision models.
-
★ 0 dlwh/marinOpen-source framework for the research and development of foundation models.
-
OctoTools: An agentic framework with extensible tools for complex reasoning
-
A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the model picks one at a time until it can answer.
-
Machine Learning Engineering Open Book
-
Code for Scaling Transformer Energy-Based Models for High Quality Image Synthesis
-
Fit DisRNNs to behavioral and neural data, interpret the fits, and discover new useful cognitive models
-
nnScaler: Compiling DNN models for Parallel Training
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
Multimodal RL training framework for diffusion & omni models
-
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
-
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
-
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
-
List of HuggingFace models tracked by Interconnects AI for open model analytics
-
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
-
An open source implementation of CLIP.
-
A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
-
Mathematical reconstruction and verification of dive tables and decompression algorithms, minimal-compartment models, robust inference from incomplete dive histories, and empirical decompression-risk analysis.
-
A dating app where users can match with language models.
-
An open-source database of AI models.
-
Training Code to endow language models with a sense of proprioception
-
RewardBench: the first evaluation tool for reward models.
-
Access large language models from the command-line
-
Runnable examples for building applications with open models on Nebius Token Factory.
-
Official Code for "Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars"
-
LLM models from publicai.co
-
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
-
📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
⚡ Fastest way to serve open source ML models to millions
-
Official implementation of "Correction Training for Diffusion Models"
-
A Python package for probabilistic state space modeling with JAX
-
PSY/COS 360: Computational Models of Cognition
-
Archived restoration of Stanford's 2021 Universal Models (FORUM) website
-
Virtue-Bench: Testing the Cardinal Virtues in Language Models Through Temptation
-
Ungoverned Sins and Agentic Alignment — code & data for ICMI Working Paper No. 25 (sin vs. safety policy in frontier models)
-
VirtueBench V2: Multi-dimensional virtue evaluation benchmark for LLMs with tripartite and Ignatian temptation models
-
LLM plugin providing access to Mistral models using the Mistral API
-
The official CLI and Python client for the Hugging Face Hub.
-
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.