Starred repositories
NocoBase is the most extensible AI-powered no-code/low-code platform for building business applications and enterprise solutions.
DDN: A novel generative model with simple principles and unique properties. (ICLR 2025)
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide
Paper list and source code for multi-object-tracking
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++
TrevorSundberg / minih264
Forked from lieff/minih264Minimalistic H264/SVC encoder single header library
WebCodecs is a flexible web API for encoding and decoding audio and video.
[proof-of-concept] fast MP4 mux / demux using WASM
FFmpeg for browser, powered by WebAssembly
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Go/React开发的端到端webrtc的文件传输/文字传输/桌面共享，安全，隐私，数据不经过服务器。
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
🚀 RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
The simplest, fastest repository for training/finetuning medium-sized GPTs.
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
🐳 A curated list of Docker resources and projects
Fork of yavta from git://git.ideasonboard.org/yavta.git, modified to support MMAL