HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
CookHero is an intelligent diet and cooking management platform built on LLM, RAG, Agent and multimodal tech, offering smart recipe search, personalized meal plans, AI diet logging, nutrition analysis, web-search augmentation, and an extensible ReAct Agent/Subagent toolset to help kitchen novices become a 'cooking hero'.
Super optimized /goal loop. Massive token savings and higher quality. Smart model designs and reviews, cheaper model builds..
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.
Well tested & Multi-language evaluation framework for text summarization.
Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support
Replicate Claude Science using the 9.9-yuan Doubao API
A Claude Code skill for reducing AIGC detection rates in academic papers
Seedance 2.5 Video Director Skill: prompts, scripts, diagnostics, character locking, continuation, editing, transitions and first-time-use guidance.
Editable reference-media timeline director for ComfyUI MiniMax H3 Reference to Video
A self-hosted, open-source tool for detecting AI API relay services: checks Claude, OpenAI and Gemini relays for authenticity, long-context support and thinking-signature verification, plus a relay blacklist/whitelist.
TimeCopilot: the GenAI Forecasting Agent. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a single API. From finance and energy to web analytics, TimeCopilot turns natural-language queries into production-ready forecasts.
A deep learning framework for multi-animal pose tracking.
ComfyUI standalone pack with 40+ custom nodes (no SD models included)
AI agents that guide you from idea to working code, with you in control at every step.
Mixture-of-experts (MoE) training megakernel for NVL72s
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
A toolkit for building AI-automated trading strategies on Kalshi prediction markets.
MCP to connect your LLM with Spotify.
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.