HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Open Source Continuous Inference Benchmark Research Platform, Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon TPUv6e/v7/Trainium2/3 | , Kimi K2.7-Code MiniMax M3 DeepSeekv4 GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 TPUv6e/v7/Trainium2/3.
Ultrafast serverless GPU inference, sandboxes, and background jobs
Cross-platform desktop application for content-aware file organization and renaming. Supports local and remote LLMs, preview-based workflows, and fully user-controlled changes.
Scalable data pre processing and curation toolkit for LLMs
Claude skill: design any process, idea, or problem into an ICM workspace (folder structure as agent architecture), or restructure an existing folder into one
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
A dev agent multiplexer for git worktrees and coding agents.
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.
GPT-SoVITS ONNX Inference Engine & Model Converter
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.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
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
Samples using the Agent2Agent (A2A) Protocol
LM Studio TypeScript SDK
Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
📄 🤖 AI for medical and scientific papers
One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.
For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system
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