Awesome AI AgentsAI Agent Deployment

e2b-dev/E2B

⭐ 13780 MDX added to this list on 2025-04-19 repository created 2023-03-04

E2B is an open-source cloud runtime infrastructure designed to securely run AI-generated code within isolated sandboxes. It provides developers with the ability to execute code safely in the cloud, leveraging secure sandbox environments that prevent code from affecting the host system or other processes. The project offers SDKs in both JavaScript/TypeScript and Python, allowing easy integration and control of these sandboxes programmatically. Users can create sandboxes, run code snippets, and retrieve execution results through simple API calls. E2B is particularly useful for AI applications and AI agents that generate and execute code dynamically, ensuring that such execution happens in a controlled and secure manner. The repository contains the core SDK used by the main E2B Code Interpreter SDK, which facilitates interaction with the sandbox environment. To get started, users install the SDK, obtain an API key from the E2B platform, and set it as an environment variable. The SDK then allows creating sandbox instances and running code inside them with straightforward commands. The project also provides comprehensive documentation and a cookbook with examples demonstrating integration with various large language models (LLMs) and AI frameworks. E2B supports self-hosting, enabling users to deploy the infrastructure on their own cloud environments using Terraform. Currently, it supports Google Cloud Platform (GCP) fully, with AWS support in progress, and plans for Azure and general Linux machine support. This flexibility allows organizations to maintain control over their runtime environments while benefiting from the security and isolation features of E2B. Overall, E2B addresses the need for secure, isolated execution environments for AI-generated code in the cloud, making it a valuable tool for developers building AI applications that require dynamic code execution with strong security guarantees.

https://github.com/e2b-dev/E2B

agentaiai-agentai-agentsai-appsai-frameworksai-generated-codeapi-keyawscloud-runtimecode-executioncode-interpretercopilotdevelopmentdevtoolsgoogle-cloud-platformgptgpt-4isolated-sandboxjavascriptjavascript-sdkllmllm-integrationnextjsopen-sourceopenaipythonpython-sdkreactsdksecure-sandboxself-hostingsoftwareterraformtypescript

Also in AI Agent Deployment

ollama/ollama

Ollama is a versatile platform that enables easy deployment, customization, and management of large language models locally across multiple operating systems with support for various model formats and a REST API.

alibaba/nacos

Nacos is a dynamic service discovery, configuration, and service management platform designed to simplify building and managing cloud-native applications and microservices.

GoogleCloudPlatform/agent-starter-pack

A collection of production-ready Generative AI Agent templates for Google Cloud that accelerates development by addressing deployment, evaluation, customization, and observability challenges.

zebbern/claude-code-guide

Claude Code Guide is a comprehensive and authoritative resource providing detailed instructions, tips, and references for using the Claude Code CLI tool to interact with the Claude AI model, including advanced features and MCP integration.

boxlite-ai/boxlite

Rust engine giving AI agents hardware-isolated persistent micro-VMs that run any OCI image, embeddable as a daemonless library in Python, Node, Go, Rust or C, or run as a CLI, REST server or cloud control plane.

jim-schwoebel/awesome_ai_agents

A comprehensive and community-driven repository offering over 1,500 curated resources, tools, and projects related to AI agents for various applications and development needs.

Forethought-Technologies/AutoChain

AutoChain is a lightweight and extensible framework that simplifies building and automatically evaluating custom generative agents powered by large language models using custom tools and simulated multi-turn conversations.

nndeploy/nndeploy

nndeploy is a workflow-based multi-platform AI deployment tool that enables efficient, high-performance, and customizable deployment of AI models across cloud, desktop, mobile, and edge platforms using a visual drag-and-drop interface and extensive framework support.