Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
- llm
- on-device-ai
- sdk
- vlm
89,572 visible repositories in the index
145–168 of 884 · Most stars
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
A Datacenter Scale Distributed Inference Serving Framework
Open GenAI Stack
System prompt builder. Assembles agent identity from workspace config and spark.toml. Part of Unicity AOS.
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
The first GitHub Copilot, Codeium and ChatGPT Xcode Source Editor Extension
Effortlessly build beautiful command-line apps
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Stylish, intuitive and user-friendly prompts. Used by eslint, webpack, yarn, pm2, pnpm, RedwoodJS, FactorJS, salesforce, Cypress, Google Lighthouse, Generate, tencent cloudbase, lint-staged, gluegun, hygen, hardhat, AWS Amplify, GitHub Actions Toolkit, @airbnb/nimbus, and more! Please follow Enquirer's author: https://github.com/jonschlinkert
Multi-account API gateway for Grok Build, Grok Web, and Grok Console
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
TranslatedOpen-source manuscript of 《深入理解 AI Infra:量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
Open Source LLM Gateway 🦚
ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
💼 An enterprise-grade Next.js boilerplate for high-performance, maintainable apps. Packed with features like Tailwind CSS, TypeScript, ESLint, Prettier, testing tools, and more to accelerate your development.
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
TranslatedSelf-hosted AI gateway for multi-channel, multi-credential setups — API keys and subscription accounts, scheduling, failover, request logs and usage.
AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.