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
24 repos
-
MaxApki: flash-card apps, scheduled with FSRS
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Multimodal RL training framework for diffusion & omni 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
-
The Modular Platform (includes MAX & Mojo)
-
A Python package for probabilistic state space modeling with JAX
-
High Performance Inter-Thread Messaging Library
-
GPT for real2sim
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
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.
-
Personal website
-
tooling to support clustermax.ai, the industry standard rating system for neoclouds | 为新型 GPU 云服务商（Neocloud）的行业标准评级体系 clustermax.ai 提供支持的工具
-
Fork used for contributing MiniMax Token Plan support to steipete/CodexBar. PR #970 merged.
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
-
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
-
Training terminal-agents
-
Autoresearch for weather dycores
-
Lens is a 3.8B-parameter text-to-image diffusion model that achieves quality competitive with and in several cases surpassing models like FLUX and SD3, while requiring significantly less training compute. Key ideas include maximizing data information density per batch and accelerating convergence.
-
[SIGGRAPH Asia 2026] REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image