Python framework for building and orchestrating multi-agent systems with sequential, concurrent, graph-based and hierarchical workflows.
fetchai/innovation-lab-examples
A collection of 80+ runnable Python AI agent examples built on Fetch.ai's uAgents, covering LLM, MCP, A2A, payments and multi-agent patterns.
- Stars
- 1,167
- Forks
- 84
- Open issues
- 7
- Last commit
- 2 months ago
What is it?
This repository is a large set of self-contained AI agent example projects written in Python. Each folder is a runnable project with its own dependencies and environment template. Most examples use the uAgents framework for agent messaging and discovery, and connect to LLM providers such as ASI:One, OpenAI, Anthropic Claude, and Google Gemini.
The examples cover several patterns: single agents, agent-to-agent (A2A) communication, Model Context Protocol (MCP) servers for services like Gmail and GitHub, RAG over documents, and payment flows using Stripe, Skyfire or FET. Multi-agent examples are built with frameworks including LangChain, CrewAI, AG2, LlamaIndex and Google ADK.
A quickstart template, a setup script and a Dockerfile are provided to run any example. Community-contributed agents are kept in a separate contributors folder.
Key features
- 01Dozens of runnable agent projects, each with its own dependencies and .env template
- 02Agent-to-agent (A2A) communication examples built on uAgents
- 03MCP server agents for Gmail, Calendar, GitHub and other services
- 04Integrations with ASI:One, OpenAI, Claude, Gemini, LangChain and CrewAI
- 05Payment examples using Stripe, Skyfire and FET
Use cases
- Learning how to build a first autonomous agent with uAgents
- Starting a hackathon project from a working orchestrator and worker template
- Comparing how different LLM SDKs and agent frameworks are wired into agents
- Adding MCP tools or payment flows to an existing agent
Quick start
- 1
Clone the repository
git clone https://github.com/fetchai/innovation-lab-examples.git - 2
Enter the repository folder
cd innovation-lab-examples - 3
Enter the hackathon quickstarter example
cd fetch-hackathon-quickstarter - 4
Create a virtual environment and install dependencies
python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
Things to know
- Each example is a separate project with its own dependencies, so you pick one and set it up individually.
- Many examples require API keys such as ASI:One, OpenAI or Stripe.
Topics
FAQ
- What is innovation-lab-examples?
- A collection of 80+ runnable Python AI agent examples built on Fetch.ai's uAgents, covering LLM, MCP, A2A, payments and multi-agent patterns. This repository is a large set of self-contained AI agent example projects written in Python. Each folder is a runnable project with its own dependencies and environment template. Most examples use the uAgents framework for agent messaging and discovery, and connect to LLM providers such as ASI:One, OpenAI, Anthropic Claude, and Google Gemini.
- Is innovation-lab-examples free to use? What license does it have?
- innovation-lab-examples is open source under the MIT license. Check the license terms before using it in commercial products.
- Is innovation-lab-examples still maintained?
- Updated within 6 months. The last commit to innovation-lab-examples was on Sep 1, 2026.
- What can I use innovation-lab-examples for?
- Learning how to build a first autonomous agent with uAgents Starting a hackathon project from a working orchestrator and worker template Comparing how different LLM SDKs and agent frameworks are wired into agents Adding MCP tools or payment flows to an existing agent
- How do I install innovation-lab-examples?
- Clone the repository: git clone https://github.com/fetchai/innovation-lab-examples.git Enter the repository folder: cd innovation-lab-examples Enter the hackathon quickstarter example: cd fetch-hackathon-quickstarter Create a virtual environment and install dependencies: python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
- Where can I get innovation-lab-examples?
- The source code and installation instructions are on GitHub: https://github.com/fetchai/innovation-lab-examples
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Python library and runnable Jupyter textbook implementing 35 agentic AI architectures, from Reflexion and ReAct to MemGPT and BrowserAgent, on LangGraph.
Chinese-language AI writing tool for WeChat Official Accounts that aggregates trending topics, generates articles with a CrewAI multi-agent workflow, formats them, and publishes drafts or posts.
Open-source platform for building enterprise-grade AI agents, with RAG knowledge bases, visual workflows and MCP tool use.
A free, MIT-licensed collection of learning paths, tutorials and team guidelines for applying AI in DevOps work, from first tools to AI infrastructure architecture.
TypeScript and Python SDK giving AI agents 1000+ pre-authenticated app toolkits, per-user sessions, and a sandbox to take actions.