A nearly-live implementation of OpenAI's Whisper.
Projetos de IA de código aberto
Projetos de IA de código aberto do GitHub que vale a pena acompanhar: LLMs, agentes, RAG, implantação local, imagem e voz… 1056 projetos até agora.
Procura projetos que possam ser implantados de graça na Cloudflare, Vercel, Netlify e mais? Veja Deploy gratuito: seleção
Todos 1056🧠 Grandes modelos de linguagem 26🤖 Agentes de IA 166🧩 Plataformas de desenvolvimento de apps 23📚 RAG e bases de conhecimento 46💬 Interfaces de chat e clientes 42🖥️ Inferência e implantação local 87👨💻 Programação com IA 99🛠️ Frameworks e SDKs 48🔌 MCP e ecossistema de ferramentas 35🎨 Geração de imagens 25🎬 Geração de vídeo 17🎙️ Voz e áudio 43👁️ Visão computacional 28📄 Análise de documentos e scraping 25🗄️ Bancos de dados vetoriais 25🏋️ Treinamento, ajuste fino e MLOps 76🧪 Avaliação, observabilidade e segurança 82🚪 Gateways e proxies de API 12🔎 Busca e pesquisa profunda 15⚙️ Bibliotecas de deep learning 57🏷️ Dados e anotação 32🔬 IA para indústria e ciência 35⚡ Ferramentas de produtividade 12
Optimizing inference proxy for LLMs
OpenAI Codex 桌面端/CLI 的可视化管理工具，具有Provider/API 切换、会话同步、提示词注入、Skills/MCP 管理、TOML 配置可视化的跨平台工具。
Machine Learning Pipelines for Kubeflow
OpenAgents - The collaboration OS for AI agents
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
AdalFlow: The library to build & auto-optimize LLM applications.
A system for agentic LLM-powered data processing and ETL
Harness LLMs with Multi-Agent Programming
百川智能开源的 Baichuan 2 系列大模型。
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-p
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to p
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm
小巧易改的 GraphRAG 实现，便于学习和二次开发。
The official CLI and Python client for the Hugging Face Hub.
A library for mechanistic interpretability of GPT-style language models
A retargetable MLIR-based machine learning compiler and runtime toolkit.
阿里的一体化视频创作与编辑框架。
Superfast AI decision making and intelligent processing of multi-modal data.
A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.
Hugging Face 的小而强的语言模型系列及完整训练配方。
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
State-of-the-art LLM compression, built for production inference with vLLM