Stars
Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 supportโ mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualโฆ
Text-audio foundation model from Boson AI
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without โฆ
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
๐ The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
๐ฆ OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
No fortress, purely open ground. OpenManus is Coming.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par withโor even surpassingโtop TTS โฆ
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the siโฆ
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Fully open reproduction of DeepSeek-R1
ๅฉ็จ AI ๅคงๆจกๅๅ่ชๅจๅๅทฅไฝๆต๏ผๆ นๆฎไธป้ขๆๅ ณ้ฎ่ฏไธ้ฎ็ๆ้ซๆธ ็ญ่ง้ขใGenerate HD short videos from a topic or keyword with an automated AI workflow.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
๐ง Train a 64M-parameter LLM from scratch in just 2h!
AIไธ้ฎๆน้็ๆๅ็ฑป็ญ่ง้ข,่ชๅจๆน้ๆททๅช็ญ่ง้ข,่ชๅจๆ่ง้ขๅๅธๅฐๆ้ณ,ๅฟซๆ,ๅฐ็บขไนฆ,่ง้ขๅทไธ,่ต้ฑไปๆฅๆฒกๆ่ฟไนๅฎนๆ่ฟ! ๆฏๆๆฌๅฐ่ฏญ้ณๆจกๅchatTTS,fasterwhisper,GPTSoVITS,ๆฏๆไบ่ฏญ้ณ๏ผAzure,้ฟ้ไบ,่ พ่ฎฏไบใๆฏๆStable diffusion,comfyUI็ดๆฅAI็ๅพใGenerate short videos with one click using Aโฆ
๐ค ๐๐ฒ๐ฎ๐ฟ๐ป for ๐ณ๐ฟ๐ฒ๐ฒ how to ๐ฏ๐๐ถ๐น๐ฑ an end-to-end ๐ฝ๐ฟ๐ผ๐ฑ๐๐ฐ๐๐ถ๐ผ๐ป-๐ฟ๐ฒ๐ฎ๐ฑ๐ ๐๐๐ & ๐ฅ๐๐ ๐๐๐๐๐ฒ๐บ using ๐๐๐ ๐ข๐ฝ๐ best practices: ~ ๐ด๐ฐ๐ถ๐ณ๐ค๐ฆ ๐ค๐ฐ๐ฅ๐ฆ + 12 ๐ฉ๐ข๐ฏ๐ฅ๐ด-๐ฐ๐ฏ ๐ญ๐ฆ๐ด๐ด๐ฐ๐ฏ๐ด
๐คฏ LobeHub is your Chief Agent Operator, organizing your agents into 7ร24 operations by hiring, scheduling, and reporting on your entire AI team.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.