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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
129 repos
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Proxy Policy Steering: inference-time adaptation for robotics foundation models
-
Batched single-token choice inference for open language models, compatible with TypeSafe
-
Jev-compatible API endpoint based on open models (prefill-only)
-
Open-source framework for the research and development of foundation models.
-
Custom AI agent platform to speed up your work.
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
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
-
TabICLv2: An open tabular foundation model
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
-
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.
-
Repository for "User awareness in frontier models: who's asking shifts what models say"
-
Train transformer language models with reinforcement learning.
-
RewardBench: the first evaluation tool for reward models.
-
Central repository for biomolecular foundation models with shared trainers and pipeline components
-
Visualizer for neural network, deep learning and machine learning models
-
A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution
-
Computational models of the evolution of honeybee waggle-dance communication
-
FlashInfer: Kernel Library for LLM Serving
-
[ECCV 2026] RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
-
Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.
-
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
-
Access large language models from the command-line
-
Offline LLM-judged arena for embedding models
-
List of HuggingFace models tracked by Interconnects AI for open model analytics
-
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
LLM plugin for models hosted by OpenRouter
-
LLM access to models by Anthropic, including the Claude series
-
LLM plugin to access Google's Gemini family of models
-
🤗 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.
-
End-to-end project training and building AI models / LLMs to detect AI-written text
-
Sub-real-time MiniMax H3 on Hopper: 13.506 s for a 14.375 s 768p video with audio on 8xH100. Four runtime patches removing 9.72 s of non-model overhead from FastVideo.
-
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream, ICML 2025 Spotlight
-
Multimodal Scaling Laws for Task & Data-Optimized Models of Visual Cortex, ICML 2026
-
Codebase for the paper "Rethinking On-Policy Self-Distillation for Thinking Models"
-
dInfer: An Efficient Inference Framework for Diffusion Language Models
-
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
-
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
-
Convert models to GGUF
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
Tools to make language models a bit easier to use
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.