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
miantiao-me/cloud-code
Cloud Code packages the OpenCode coding agent as a container that runs on Cloudflare infrastructure, so an agent workspace can be deployed to Cloudflare's network instead of a local machine. It is a TypeScript project built on Cloudflare Workers and Cloudflare Containers: a Worker acts as the entry handler and routes requests to an AgentContainer class that extends the Containers base class, while a separate module handles Server-Sent Events streaming so agent output reaches the client incrementally. Development uses pnpm and wrangler, with a local dev server that simulates the Workers environment, a type-generation step that regenerates binding types from wrangler.jsonc, and a one-command deploy; a deploy-to-Cloudflare button is provided for one-click setup. Access control is HTTP Basic Auth: setting a server password environment variable turns authentication on, requests must then carry an Authorization header, and failures return 401. Authentication stays off when no password is configured, which the README states explicitly. Because containers are ephemeral, persistence is handled by mounting S3-compatible object storage, such as Cloudflare R2 or AWS S3, into the container with TigrisFS. The bucket is mounted at a fixed path, the working directory and OpenCode's own XDG configuration directory both live inside it so editor state survives restarts, and a preset workspace is copied in on first start when the bucket or prefix is empty. Endpoint, bucket, credentials, region, path style, prefix and extra mount arguments are all environment variables, and the container falls back to a non-persistent local directory when storage is not configured. The image also ships the cloudflared CLI so services started inside the container, such as a development server or web application, can be exposed publicly through a Cloudflare Tunnel. Documentation is available in English and Simplified Chinese.
https://github.com/miantiao-me/cloud-code
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.