beta9
Ultrafast serverless GPU inference, sandboxes, and background jobs
This is the broadest group: chat interfaces, SDKs and frameworks, prompt and evaluation tools, and applications built on large language models. Many work with models from several providers, and some can run models on your own hardware.
For anything you plan to ship, check three facts first: the licence, because some popular projects restrict commercial use; whether it supports the model provider you already use; and whether it is still maintained. The At a glance box on every project page answers the licence and maintenance questions from GitHub data.
Ultrafast serverless GPU inference, sandboxes, and background jobs
Community maintained hardware plugin for vLLM on Apple Silicon
An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.
100 days of LLM inference engineering — daily posts, experiments, and visualizations
Intercept any app, then call it from Python like a library
Web, Desktop & Mobile client for Codex, Claude Code, OpenCode, Kimi, Augment Code, Qwen, fully end-to-end encrypted
Claude Code for Financial Market
A dev agent multiplexer for git worktrees and coding agents.
AI+金融(量化):1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作,包括LLM, Agent, benchmark(evaluation), etc.
Scalable data pre processing and curation toolkit for LLMs
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
GPT-SoVITS ONNX Inference Engine & Model Converter
LM Studio TypeScript SDK
📄 🤖 AI for medical and scientific papers
Samples using the Agent2Agent (A2A) Protocol
Cross-platform desktop application for content-aware file organization and renaming. Supports local and remote LLMs, preview-based workflows, and fully user-controlled changes.
An agent organization for Claude Code, structured as a company — 15+ departments, 125+ skills, each independently installable.
Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system