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
docker/compose-for-agents
Compose for Agents is a Docker-maintained set of demonstration projects showing how to define and run an agentic application entirely with Docker Compose. Each demo is self-contained and follows the same three steps: change into the project directory, create a .mcp.env file from the provided example and fill in whatever MCP tokens the demo needs, then run docker compose up --build. The same project can run locally or against a cloud context. Models come from Docker Model Runner, which serves open-weight models such as Qwen3, Gemma 3 and Llama 3.2 on local GPU hardware; machines without a GPU can use Docker Offload instead. Every demo can also be switched to hosted OpenAI models by writing an API key into a secret file and layering a second compose file over the base one, which keeps the model choice out of the agent code. The catalog covers a broad range of agent runtimes rather than a single framework, including Google ADK, CrewAI, LangGraph, Agno, Embabel, the Vercel AI SDK and the A2A agent-to-agent protocol, and it labels each entry as single-agent or multi-agent along with the models and MCP servers it uses. Tooling is supplied as containerized MCP servers wired in through Compose, with examples using DuckDuckGo search, the official GitHub server, Wikipedia, Brave, Postgres, weather, Google Maps and email delivery. Concrete demos include a multi-agent fact checker, a GitHub issue summarizer, a marketing strategy crew, a SQL agent, a travel planner and a chat interface for mixing models and MCP servers. Prerequisites are Docker Desktop 4.43.0 or newer, or Docker Engine with Compose 2.38.1 and GPU support configured. It serves developers who want a reproducible, container-native way to package and ship agent stacks.
https://github.com/docker/compose-for-agents
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.