An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
- ai
- amd-gpu
- apple-silicon
- asr
108,094 visible repositories in the index
505–528 of 2,361 · Most stars
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
SQL Translator is a tool for converting natural language queries into SQL code using artificial intelligence. This project is 100% free and open source.
Open Source version of Claude Cowork with 500+ SaaS app integrations
TranslatedChinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Post-training with Tinker
TranslatedChatGPT Plus sharing solution. ChatGPT Plus / OpenAI API sharing solution.
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Open-Source Generative UI Framework
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
AdalFlow: The library to build & auto-optimize LLM applications.
原样镜像官方 Codex 桌面应用:每 15 分钟探测、SHA256 可校验、国内直连下载、 Mac 可增量更新 | Verbatim, verifiable mirror of the official Codex desktop app — probed every 15 min, with a Sparkle delta-update feed.
A language for constraint-guided and efficient LLM programming.
PyTorch code and models for V-JEPA self-supervised learning from video.
Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.
REAP - Prompts for you to use REA (Reverse Engineer Anything), get the most out of it, and clone or break down any program
Speakr is a personal, self-hosted web application designed for transcribing audio recordings
A live stream development of RL tunning for LLM agents
⚡️ Python client for the ChatGPT API with, conversation tracking, proxy support and more.
Professional-grade, local-first browser extension that transforms any webpage into high-fidelity, LLM-friendly Markdown entirely within the browser's runtime. Zero-cloud, privacy-centric, and designed specifically for AI workflows.
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
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) on the same weights.
Vision infrastructure to turn complex documents into LLM-ready data
The Apache Tika toolkit detects and extracts metadata and text from over a thousand different file types (such as PPT, XLS, and PDF).
A client implementation for ChatGPT and Bing AI. Available as a Node.js module, REST API server, and CLI app.