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
16 repos
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
A Python library encapsulating best practices for rubric-based evaluation of LLM/VLM outputs using AI judges such as LLMs and decision models.
-
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
-
🤗 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.
-
Ask an open vision-language model typed questions about an image and get probabilities back, on your own machine.
-
A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.
-
OCR with VLMs running on a single GPU with high throughput
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
Benchmark environment for evaluating vision-language models (VLMs) on popular video games!
-
Project page for Planning with the Views: ViewAgent + ViewSuite, a 6-DoF view planning benchmark for VLM agents
-
[NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
-
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
-
Code for "Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly" (CVPR 2026)