serverless-chat-langchainjs
Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure
HYSEN LABS DIRECTORY
Curated repositories with precise taxonomy, verified metadata and practical context.
Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
Official Jina AI Remote MCP Server
A lightning-fast, cross-platform mobile AI Assistant App built with React Native.
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design and molecule optimization.
:zap: A newly designed ultra lightweight anchor free target detection algorithm, weight only 250K parameters, reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
On-demand self-hosted AWS EC2 runner for GitHub Actions
wastebin is a pastebin 📝
Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.
Mission control for your AI agents
An MCP server for interacting with Sentry via LLMs.
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.
🔥机器学习/深度学习/Python/大模型/多模态/LLM/deeplearning/Python/Algorithm interview/NLP Tutorial
BioNeMo Recipes: For building and adapting AI models in drug discovery at scale
Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.
Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.
An 8-stage vulnerability-discovery agent.
Wavelet scattering transforms in Python with GPU acceleration
让 Codex 根据最终结果生成标题、注释、commit 和 PR,减少被否决方案在交付中的残留。