how-llms-work
An interactive app that walks through every stage of the LLM pipeline, from pattern matching to training a transformer from scratch, with working code you can run locally.
HYSEN LABS DIRECTORY
Curated AI & Machine Learning repositories with precise tags and practical analysis.
An interactive app that walks through every stage of the LLM pipeline, from pattern matching to training a transformer from scratch, with working code you can run locally.
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence.
A public-opinion analysis assistant combining real-time data from 26 trending lists across 15 major platforms with LLM analysis. Through a front-end page, users can run conversational trending-list queries, topic search, topic clustering and sentiment analysis. Supports hotkey control of crawler start/stop, fast multi-platform data lookup and navigation, accumulates analysis results from news detail pages (including content mined from videos), and pushes hotspot alerts via email, WeChat, WeCom, DingTalk, QQ and Telegram.
Automated modeling and machine learning framework FEDOT
Diagrams of concepts in physics/chemistry/ML
PyTorch Neural Network eXchange
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Frontier Models playing the board game Diplomacy.
ℹ️ A Simple But Advanced WhatsApp Bot!
Capture every activation and gradient of any PyTorch model — forward and backward — with automatic graph visualization, rich metadata, and live interventions. Works on any architecture, including dynamic and recurrent ones.
Run VSCode-based coding agents and extensions seamlessly within other IDE platforms - bridging the gap between VSCode ecosystem and other development environment.
Cake a C23 front end and transpiler written in C
A simple probabilistic programming language.
Claude Code reference: write in Louis Rossmann's voice, never like AI slop. Portable CLAUDE.md plus skills.
[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention
The slow descent into madness
Trame lets you weave various components and technologies into a Web Application solely written in Python.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
Open-source AI-powered video sequence platform built with TanStack Start
QuietHarness: a lightweight AI workflow system shared by Claude Code, Codex and Cursor