HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
LLM reverse-engineered API management -- access ChatGPT / gpt4free / Bard / Claude / HuggingChat / Tongyi Qianwen and other reverse-engineered AI services through the standard OpenAI API format. Converts all reverse-engineered LLM libraries to the OpenAI API format for free access.
ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
Playwright's API on a Rust CDP engine, Chromium browser automation for Python & Node, no driver subprocess. (Alpha).
AgentChat is an LLM-based agent communication platform with a built-in default agent and support for custom agents. Through multi-turn dialogue and task collaboration, agents can understand and help complete complex tasks. It integrates LangChain, function calling, the MCP protocol, RAG, memory, HITL, skills, Milvus and Elasticsearch for efficient knowledge retrieval and tool calling, with a high-performance FastAPI backend.
📚 Process PDFs, Word documents and more with spaCy
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector
PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs, camera-conditioned grounding, and exposure-bracketed supervision transfer.
An AI advisor for China's college entrance exam (Gaokao) major/university choices -- asks follow-up questions, analyzes options, and tells you the truth.
Makes Codex generate titles, comments, commits and PRs based on the final result, reducing the leftover traces of rejected approaches in the delivery.
A code-driven presentation generation framework -- generate presentations the way you'd build software.
NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Token efficient Claude Code full Python rebuild. AI Coding Agent in 270K LoC pure Python. Up to 200X Cost Saving!
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
AI-guided editable scientific figures with Codex and local Origin/OriginPro
Git Based Memory Storage for Conversational AI Agent