This repository offers a curated collection of production-quality agent examples built with Fetch.ai's core technologies, including uAgents, ASI:One, Agentverse, A2A protocol, and MCP. It targets beginners exploring autonomous agents, developers integrating LLMs or Web3 functionalities, and hackathon participants, providing practical, working examples to accelerate development and showcase advanced use cases beyond main documentation.

How It Works

The project provides a diverse set of runnable agent examples demonstrating various Fetch.ai capabilities. It leverages the uAgents framework for agent creation and communication, integrating with services like ASI:One for AI models, Agentverse for deployment, and the A2A protocol for inter-agent interactions. This approach offers practical, hands-on demonstrations of complex agent architectures, LLM integrations, payment systems, and multi-agent coordination, serving as a valuable resource for learning and implementation.

Quick Start & Requirements

Clone the repository (git clone https://github.com/fetchai/innovation-lab-examples.git), navigate into the directory, and set up a Python virtual environment. Install dependencies using pip install -r requirements.txt. Configure environment variables by copying .env.example to .env and editing it with necessary API keys. Run specific examples using python <path_to_example_agent.py> or utilize the ./setup.sh <example_name> script for automated setup. Docker support is available for running examples in containers.

• Prerequisites: Python 3.10+, pip, git.
• Dependencies: API keys for services like ASI:One, OpenAI, Stripe, Google Gemini, Anthropic are often required.
• Links:
  • Innovation Lab Docs: innovationlab.fetch.ai/resources/docs/intro
  • uAgents Framework: github.com/fetchai/uAgents

Highlighted Details

• Features over 30 examples spanning LLM integrations (Anthropic, Gemini, OpenAI), Agent-to-Agent (A2A) communication, Model Context Protocol (MCP), payment systems (FET, Stripe, Skyfire), Retrieval-Augmented Generation (RAG), advanced Multi-Agent Systems (using CrewAI, AG2), Web3 integrations, and external service integrations (Composio, Duffel).
• Includes a beginner-friendly fetch-hackathon-quickstarter template and comprehensive Docker support for isolated execution.
• Examples are categorized by difficulty (Beginner 🟢 to Advanced 🔴), allowing users to select appropriate learning paths.

Maintenance & Community

The repository includes contribution guidelines (CONTRIBUTING.md), issue reporting procedures (ISSUES_GUIDE.md), and a security policy (SECURITY.md), indicating active maintenance and a structured approach to community involvement. Specific community channels (like Discord/Slack) or core maintainer details are not explicitly listed in the provided README snippet.

Licensing & Compatibility

This project is licensed under the Apache License 2.0, which permits commercial use and integration into closed-source projects.

Limitations & Caveats

A significant number of examples necessitate obtaining and configuring external API keys from various third-party services, which may involve associated costs or usage limits. Some advanced examples are marked as requiring significant effort or expertise. The repository serves as a collection of examples rather than a standalone application, requiring users to adapt and integrate the code into their specific projects.