HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Oracle Skills is a curated, open-source collection of practical, installable skills for working with Oracle technologies. It provides developers, administrators, and AI agents with high-quality, source-backed guidance across the entire Oracle ecosystem.
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
Open source guides/codes for mastering deep learning to deploying deep learning in production in PyTorch, Python, Apptainer, and more.
A pure protocol, reverse-engineered implementation of the ChatGPT website API: supports registration bots to maintain account-pool quotas, GPT-Image-2 and text models, is compatible with the OpenAI API protocol, offers online batch image generation/editing, account-pool management, reverse-engineered editable PPT/PSD files, importing of CPA and sub2api account pools, and integration with Cherry Studio, New API and similar tools.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design and molecule optimization.
sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has you covered.
A minimalist LLM-based PID auto-tuning system (CLI version).
The foundation layer for agentic intelligence.
File your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-27. Claude Code / Codex / Gemini skill.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.
[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.
An 8-stage vulnerability-discovery agent.
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.
BioNeMo Recipes: For building and adapting AI models in drug discovery at scale
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers