thedaviddias/Front-End-Checklist
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
Awesome AI Agents › MCP Server Framework
cohere-ai/cohere-terrarium
Terrarium is a Python sandbox environment designed to safely execute untrusted Python code, including code generated by large language models (LLMs). It is optimized for low latency, ease of use, and cost efficiency, making it suitable for deployment in cloud environments such as Google Cloud Platform (GCP) Cloud Run. The sandbox operates by running Python code inside a Node.js process using Pyodide, which compiles CPython to WebAssembly. This approach ensures strong compartmentalization by restricting the code's access to the filesystem, threading, subprocesses, network, and host memory, and by recycling the entire Pyodide environment after each execution to prevent state carryover. Terrarium supports native input and output files, allowing users to send various file types as part of the execution request and receive generated files in response. It includes support for many common Python packages such as numpy, pandas, matplotlib, sympy, scikit-learn, and more, enabling a wide range of data processing and visualization tasks. The sandbox is designed to be fast, with typical runtimes of under a second for generating graphical outputs, and economical, with hosting costs reported to be under $30 per month on GCP with modest resource allocation. The project provides easy-to-use interfaces for interacting with the sandbox, including a Python client for sending code and files, and detailed instructions for local development, Docker container deployment, and cloud deployment on GCP Cloud Run. It also addresses operational concerns such as handling timeouts, health checks, and resource scaling. Limitations include restrictions on network access, package installation, and occasional issues with very large or complex computations due to Pyodide's constraints. Overall, Terrarium offers a secure, scalable, and efficient solution for executing untrusted Python code in isolated environments, making it valuable for applications requiring safe code execution, such as data annotation, automated analysis, and interactive coding environments.
https://github.com/cohere-ai/cohere-terrarium
Also in MCP Server Framework
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.
pascalorg/editor
Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.
trycua/cua
c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.
nukeop/nuclear
Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).
apify/apify-mcp-server
Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.
grab/cursor-talk-to-figma-mcp
Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.