Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
An MCP server for getting AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic's MCP (Model Control Protocol).
mcp-vision-server is an MCP stdio server that lets MCP clients analyze images and run OCR through an existing OpenAI-compatible vision Chat Completions API.
MCP server for Jupyter Notebooks and JupyterLab
把 米醋 的图像接口包装成 MCP server，让 Claude Code / Codex / Cursor 等 MCP 客户端直接生图、改图、批处理、多图参考。
Scout’s local MCP puts metrics, traces and errors right in your AI agent. For teams that do it all.
- - Comprehensive tool documentation with real-world examples - - Data handling and privacy information - - Comprehensive Docker deployment, multi-architecture builds, and production setup
Printed on startup. In a real terminal the box animates in brick-by-brick (set BRICKS_BANNER=anim|static|off).
Local MCP server for COMSOL modeling workflows, validation, and RAG-assisted multiphysics automation.
This repo exposes the TMF620 command layer through two interfaces:
Gives Goose/Cursor access to your iOS/macOS project index through the Model Control Protocol (MCP) and IndexStoreDB.
This server implements long-term memory capabilities for AI assistants using mem0 principles, powered by PostgreSQL with pgvector for efficient vector similarity search.
Ask one model a design question and you get one confident answer, with no signal about which parts it is unsure of. Ask three and the disagreement is the signal.
Agent Skills
Frappe UI provides a set of components and utilities for rapid UI development. Components are built using Vue 3 and Tailwind. Along with generic components like Button, Link, Dialog, etc.
This project is under active development and evolving rapidly. Contributions, feedback, and discussions are warmly welcome.
NeMo Gym is a library for evaluating and improving models and agents using environments. NeMo Gym provides infrastructure to develop environments, scalably run evaluation and training, and a...
Lakehouse graph database for context assembly & multi-agent coordination Multimodal retrieval · Git-style branching · object-storage native
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and...
Built by DeepSeek, for DeepSeek. An AI coding agent that flows through your codebase like a tide. The name: DeepSeek + tide (terminal IDE).
https://github.com/user-attachments/assets/023c0a9c-194a-45a9-bb88-ac8f16f5ffd5
Reactive MobX Form State Management
A collaborative list of awesome Helm resources.
Codex Skill for producing authorized digital-human talking-head videos with MiniMax overseas voice cloning and HeyGen Image-to-Video.
Large Language Models (LLMs) have rapidly evolved into powerful general-purpose reasoning and generation engines.
A curated list of delightful NoCode / LowCode applications and resources. For more awesomeness, check out awesome.