An open-source framework for training large multimodal models.
- computer-vision
- deep-learning
- in-context-learning
- language-model
Repository Index
78,850 visible repositories in the index
697–720 of 2,544 · Most stars
A multi-threaded download tool written with RxJava and Kotlin
- rxjava
- kotlin
- rxdownload
Single Shot MultiBox Detector in TensorFlow
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
🌴💪 Synchronize your Visual Studio Code Settings Across Multiple Machines using GitHub GIST 💪🌴
- gist
- settings-sync
- sync
- vscode-extension
🚀1K tiny & fast lib for doing addition, subtraction, multiplication and division operations precisely
- floating-point
- number-converter
- rounding-error
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
A shadowsocks manager tool for multi user and traffic control.
197 production-ready AI agent templates for OpenClaw. SOUL.md configs across 24 categories. Submit yours!
Command the forces of The Project in a battle to rebuild the world after mankind has been nearly destroyed by nuclear missiles. A 100% free and open source real-time strategy game for Windows, macOS, Linux, BSD+
- game
- c-plus-plus
- strategy-game
- cheats
[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers
- agent
- multi-agent-systems
- paper
- poster
CN Windows 多网卡聚合与网络加速工具。一键融合有线、Wi-Fi、热点等连接，实现多路径传输与智能流量调度。 EN Windows multi-NIC network accelerator. Combine Ethernet, Wi-Fi, hotspots and more for multi-path transmission and smart traffic routing.
- fluent
- network
- windows-10
- windows-11
Every Code - push frontier AI to it limits. A fork of the Codex CLI with validation, automation, browser integration, multi-agents, theming, and much more. Orchestrate agents from OpenAI, Claude, Gemini or any provider.
Superfast AI decision making and intelligent processing of multi-modal data.
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
🐻 The multi-zone service mesh for containers, Kubernetes and VMs. Built with Envoy. CNCF Sandbox Project.
- service-mesh
- golang
- envoy
- envoyproxy
A terminal for iOS, with multiple windows
:balloon: Modernized and sophisticated tooltips, fully customizable with an arrow and animations for Compose and Kotlin Multiplatform.
- kotlin
- android
- android-library
- popup
A lightweight, powerful framework for multi-agent workflows and voice agents
- agents
- openai
- openai-api
- realtime-api
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.
- multi-object-tracking
- sort
- bytetrack
- oc-sort
The mediator with no regist process to split your iOS Project into multiple project.
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
- speech-synthesis
- text-to-speech
- tensorflow2
- melgan
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Domain-fronted HTTP/SOCKS5 proxy tunneling traffic through Google Apps Script with MITM TLS interception, HTTP/1-2 multiplexing, and DPI evasion.