- Docker Desktop 4.43.0+ or Docker Engine installed
- A laptop or workstation with a GPU (e.g., a MacBook) for running open models locally. If you don't have a GPU, you can alternatively use Docker Offload.
- If you're using Docker Engine on Linux or Docker Desktop on Windows, ensure that the Docker Model Runner requirements are met (specifically that GPU support is enabled) and the necessary drivers are installed
Each of these demos is self-contained and can be run either locally or using a cloud context. They are all configured using two steps.
- change directory to the root of the demo project
- create a
.mcp.envfile from themcp.env.examplefile (if it exists, otherwise the demo doesn't need any secrets) and supply the required MCP tokens - run
docker compose up --build
| Demo | Models | MCPs | project | compose |
|---|---|---|---|---|
| Agno agent that summarizes GitHub issues | deepseek(local), qwen3(local), o3(openai) | github-official, notion, fetch | ./agno | compose.yaml |
| Vercel AI-SDK Chat-UI for mixing MCPs and Model | llama3.2(local), qwen3(local) | wikipedia-mcp, brave, resend(email) | ./vercel | compose.yaml |
| CrewAI Marketing Strategy Agent | qwen3(local) | duckduckgo | ./crew-ai | compose.yaml |
| ADK academic_research agent | gemma3-qat(local) | duckduckgo | ./adk | compose.yaml |
| LangGraph SQL Agent | qwen3(local) | postgres | ./langgraph | compose.yaml |
| Embabel Travel Agent | qwen3, Claude3.7, llama3.2, jimclark106/all-minilm:23M-F16 | brave, github-official, wikipedia-mcp, weather, google-maps, airbnb | ./embabel | compose.yaml and compose.dmr.yaml |
| Spring AI Brace Search | none | brave | ./spring-ai | compose.yaml |