ml-engineering
Machine Learning Engineering Open Book
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Machine Learning Engineering Open Book
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Qiu Xipeng's "Neural Networks and Deep Learning", 2nd edition and the general-audience edition: e-book, table of contents, learning resources, and errata.
The LLM Evaluation Framework
High-performance In-browser LLM Inference Engine
A collection of Flutter examples and demos
Netflix-level subtitle cutting, translation, alignment, and even dubbing: a one-click, fully automated AI video subtitle team.
ARIS (Auto-Research-In-Sleep), Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent.
Tracking ECMAScript Proposals
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Production-grade platform for building agentic IM bots, with Agent and knowledge-base orchestration and a plugin system. Bots for Discord, Slack, LINE, Telegram, WeChat (Work WeChat, WeChat bots, official accounts), Feishu, DingTalk, QQ, and Matrix. Integrates with ChatGPT (GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, OpenClaw/hermes agent, and DeerFlow.
A skill file for removing AI tells from prose
Free, simple, fast interactive diagrams for any GitHub repository
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Chinese LLaMA & Alpaca large language models, with local CPU/GPU training and deployment.
Gas Town - multi-agent workspace manager
Jargon from the functional programming world in simple terms!
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Universal provider proxy for OpenAI Codex & Claude Code, use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code.