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.
Awesome AI Agents › AI Agent Deployment
cloudflare/sandbox-sdk
Cloudflare Sandbox SDK gives Workers applications a programmable, isolated container in which to run untrusted code. The package is published as @cloudflare/sandbox and is designed for scenarios where an LLM or an end user supplies code that must not run in the calling process: AI agent code execution, interactive development environments, data analysis platforms and CI/CD systems. A sandbox is obtained with getSandbox(), backed by a Durable Object namespace, which gives each sandbox a stable identity and persistent state across requests. The API covers shell and interpreter execution through exec(), which returns stdout, stderr and a success flag, plus file operations such as writeFile() and readFile() against a workspace directory, background processes, and exposing services that listen inside the container. Sandbox creation accepts options for lifetime management through sleepAfter, which idles the container after a configurable period, and labels attached to the underlying Cloudflare Container for analytics and observability; labels take effect at the next container start. The tunnels API wraps cloudflared: sandbox.tunnels.get(port) opens a QUIC connection to Cloudflare and returns a public *.trycloudflare.com hostname for a service running in the sandbox, requiring no account DNS setup. Calls are idempotent through a per-sandbox cache in Durable Object storage, list() enumerates cached tunnels and destroy() tears them down; URLs do not survive a container restart because the hostname is assigned during the cloudflared handshake. Requests can be routed into a running sandbox with proxyToSandbox() for preview URLs. Local development runs the container under Docker, and deployment goes through wrangler. Known constraints are documented, including that trycloudflare.com buffers text/event-stream responses while WebSockets pass through. Project templates are available via npm create cloudflare with the minimal example.
https://github.com/cloudflare/sandbox-sdk
Also in AI Agent Deployment
alibaba/nacos
Nacos is a dynamic service discovery, configuration, and service management platform designed to simplify building and managing cloud-native applications and microservices.
e2b-dev/E2B
E2B is an open-source secure cloud runtime infrastructure that enables safe execution of AI-generated code in isolated sandboxes for AI applications and agents.
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.