MultiGen
Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration
Autonomous agentic AI for CRA (Cyber Resilience Act) compliance: scans repos, triages findings, opens Jira tickets, and auto-fixes vulnerabilities via PR.
Stop AI agents from doing things you didn't ask for.
Maintenance-mode desktop ChatGPT client built with Flet, kept as a small open-source archive with smoke and startup checks.
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
A mini pen-doodle IP illustration skill for character building and article illustrations.
An elegant PyTorch offline reinforcement learning library for researchers.
Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.
Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful Diffuse Intrinsic Image Decomposition in the Wild" (TOG 2024)
The official repository of SafeIMG.
A lightweight Python package for Automatic Speech Recognition using ONNX models
AI agent skills for TestMu AI (Formerly LambdaTest).
tsl: a PyTorch library for processing spatiotemporal data.
Framework to bring LLM applications to production
BentoDiffusion: A collection of diffusion models served with BentoML
DANCE: a deep learning library and benchmark platform for single-cell analysis
Japanese to romaji converter in Python
An easy-to-use, fast toolkit to scale up RL post-training on a single node.
Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.