Streaming-dLLM
Diffusion Language Model
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Diffusion Language Model
Seeed SenseCraft Model Assistant is an open-source project focused on embedded AI. 🔥🔥🔥
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
An e-commerce data-warehouse Q&A AI agent built with LangGraph, FastAPI, Qdrant, Elasticsearch, MySQL, and React, ideal as a hands-on project for learning LangGraph. Implements a metadata knowledge base, hybrid retrieval, NL2SQL generation and validation, SQL execution, and streaming results, with one-click Docker deployment and the free ai-agents-from-zero tutorial.
Run LLM prompts from your shell
RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.
Python toolkit for building graph-enhanced GenAI applications
A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.
Audit, diagnose, research, plan, implement, experiment on, and verify website SEO across Google, Bing, and AI-search surfaces. Use for technical SEO,
All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.
AutoHarness: Automated Harness Engineering for AI Agents
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
Implementation of Autoregressive Diffusion in Pytorch
The Python toolkit for computing with string diagrams.
Pytorch Library for Relational Table Learning with LLMs.
Turn any content into a personalized AI podcast. NotebookLM-style, except you control the script, voices, and hosts. Listen in Apple Podcasts, Spotify, or any podcast app.
Analyze the followers and following accounts that a private (hidden) Instagram account interacts with.
🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.
An evidence-led, eight-locale LLM playbook: a transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.
Have a rough idea but don't know how to pick a research topic? Feed this skill some data and it automatically extends it into multiple ideas, searches the literature, runs preliminary regressions to check empirical and theoretical feasibility, then scores and ranks them, so the first step of your research is no longer a struggle.