Decky plugin to streamline installation and usage of lsfg-vk; the Lossless Scaling compatibility layer for linux
Repository Index
88,573 visible repositories in the index
1,561–1,584 of 3,276 · Most stars
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
- asr
- industrial-grade
- llm
- multimodal-llm
An open-source AI assistant framework with skills and agent architecture
- agent
- ai
- assistant
- automation
Keras Temporal Convolutional Network. Supports Python and R.
- keras
- tcn
- recurrent-neural-networks
- deep-learning
an open-source, low-cost DIY 360° LiDAR scanner and panoramic 3D reconstruction system.
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
- chatbot
- clip
- computer-vision
- dino
Bilibili视频转文字，一步到位，输入链接即可使用
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
- acoustics
- room-impulse-response
- image-source-model
- beamforming
OpenLane is an automated RTL to GDSII flow based on several components including OpenROAD, Yosys, Magic, Netgen and custom methodology scripts for design exploration and optimization.
- asic
- 130nm
- magic
- netgen
Easy token price estimates for 400+ LLMs. TokenOps.
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
- vae
- benchmarking
- beta-vae
- comparison
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
- lstm
- rnn-tensorflow
- stock-price-prediction
- embeddings
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
- pytorch
- knowledge-distillation
- deep-neural-networks
- cifar10
Safety checks Python dependencies for known security vulnerabilities and suggests the proper remediations for vulnerabilities detected.
- python
- security
- security-vulnerability
- travis
Community maintained hardware plugin for vLLM on Apple Silicon
Versatile audio super resolution (any -> 48kHz) with AudioSR.
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
- ai-agents
- ai-companion
- digital-human
- digital-life
A very simple way to find out which SSL ciphersuites are supported by a target.
Transform geospatial relations into graphs for Graph Neural Networks and spatial network analysis
- network-analysis
- spatial-analysis
- geographical-information-system
- graph-neural-networks
The most complete open-source tool for Twitter intelligence analysis
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Worldwide building footprints derived from satellite imagery
ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.
- ai-skill
- anthropic
- claude
- claude-code