State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
- browser
- javascript
- transformers
- webml
Repository Index
56,139 visible repositories in the index
1–23 of 23 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
- agentic-aigc
- video-generation
TranslatedScreenshot, Offline OCR, Search, Translate, Search for picture, Paste the picture on the screen, Screen recorder, Omnidirectional scrolling screenshot, Screen translator. Supports Windows, Linux, macOS
- screenshot
- screen-capture
- clipboard
- search
Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
- background-removal
- javascript
- open-source
- typescript
Turn any script into viral, multi-style animated stickman videos for Faceless YouTube Channels. Automate visuals, voiceover, captions & SFX. 100% Free & Open-Source.
- agent-skills-manager
- ai-animation-generator
- ai-video-production
- automated-video
A library for prototyping realtime hand detection (bounding box), directly in the browser.
- javascript
- javascript-library
- handtracking
- neural-networks
Multi-segment MiniMax H3 Director for official ComfyUI MiniMax-H3
Direct Sparse Odometry
Semi-direct Visual Odometry
Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.
- convolutional-neural-networks
- motion-tracking
- color-detection
- face-detection
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
- kmer
- dnabert-model
- kmer-format
- gpu
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.
Code for the paper “The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions”
Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
- tensorflow
- lstm
- rnn
- stacked-layers
Build an easy-to-use workflow for the next generation of video creation with agent
- agentic-workflow
- video-generation
- plugins
- claude-code
Bi-Directional Equivariant Long-Range DNA Sequence Modeling
Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely
- ane
- apple
- apple-neural-engine
- neural-engine
This repo is the official implementation of "F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation".
PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.
- gnn
- graph-neural-netowrks
- signed-networks
- directed-networks
Faster force-directed graph layouts by reusing force approximations
- graph
- visualization
- d3js
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.