fetchai/innovation-lab-examples

git clone https://github.com/fetchai/innovation-lab-examples.git
cd innovation-lab-examples && python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt

Usage

• •Pick a self-contained example folder (start with fetch-hackathon-quickstarter), copy .env.example to .env, and add your API keys.
• •Run the agent with python agents/alice/agent.py or use the automated setup script ./setup.sh <example-name>.
• •Run any example in a container without local Python: docker build --build-arg EXAMPLE=<name> then docker run --env-file <example>/.env.
• •Contribute new agents under contributors/<your-agent-name>/ per CONTRIBUTING.md.

Key features

• ✓Every folder is a self-contained, runnable AI agent project with its own README, dependencies, and environment template.
• ✓Broad coverage: LLM integration, A2A protocol, MCP agents (Gmail, Calendar, GitHub, etc.), payments, RAG, multi-agent systems, Web3, and external integrations.
• ✓Docker/Docker Compose support for running any example in a container.
• ✓Community contributors folder with per-example linting (ruff) and a per-example test runner.

Best for

Learning and kickstarting autonomous and multi-agent AI workflows on the Fetch.ai stack (uAgents, ASI:One, Agentverse).

Caveats

• ⚠Most examples require at least one API key; an ASI:One key covers the majority, but OpenAI/Anthropic/Google/Stripe/vendor keys may also be needed.
• ⚠This is an examples collection, not a standalone MCP server.
• ⚠Requires Python 3.10+; third-party APIs each example calls have their own terms and pricing.