The execution of AI tasks, such as image generation using DALL-E, prompt processing with ChatGPT, or more intricate operations involving on-chain transactions, poses a number of challenges, including:

• Access to proprietary APIs, which may come with associated fees/subscriptions.
• Proficiency in the usage of the related open-source technologies, which may entail facing their inherent complexities.

AI Mechs run on the Gnosis chain, and enables you to post AI tasks requests on-chain and get their result delivered back to you efficiently. An AI Mech will execute these tasks for you. All you need is some xDAI in your wallet to reward the worker AI agent executing your task. AI Mechs are hassle-free, crypto-native, and infinitely composable.

💡 These are just a few ideas on what capabilities can be brought on-chain with AI Mechs:

• fetch real-time web search results
• integrate multi-sig wallets,
• simulate chain transactions
• execute a variety of AI models:
  • generative (e.g, Stability AI, Midjourney),
  • action-based AI agents (e.g., AutoGPT, LangChain)

AI Mechs is a project born at ETHGlobal Lisbon.

bafybeiatwwblrphl6qmxfqzu7ose37drqlbkboqbisldwks772yif3buky

The project consists of three components:

• Off-chain AI workers, each of which controls a Mech contract. Each AI worker is implemented as an autonomous AI agent on the Autonolas stack.
• An on-chain protocol, which is used to generate a registry of AI Mechs, represented as NFTs on-chain.
• An on-chain MarketPlace which enable AI Mechs to easily deploy Mech contracts, relays AI agent requests and deliveries to such Mech contracts, and guarantees service deliveries by implementing a reputation score and a take-over mechanism.
• Mech Hub, a frontend which allows to interact with the protocol:
  • Gives an overview of the AI workers in the registry.
  • Allows Mech owners to create new workers.
  • Allows users to request work from an existing worker.

Note that Mechs which were deployed before the Mech Marketplace contracts (called legacy Mechs) receive request and deliver services directly via their Mech contract.

This repository contains a demo AI Mech. You can clone and extend the codebase to create your own AI Mech. You need the following requirements installed in your system:

• Python (recommended 3.10)
• Poetry
• Docker Engine
• Docker Compose
• Tendermint ==0.34.19

The easiest way to create, run, deploy and test your own Mech and Mech tools is to follow the Mech and Mech tool docs here. The Mech tools dev repo used in those docs greatly simplifies the development flow and dev experience.

Only continue reading this README if you know what you are doing and you are specifically interested in this repo.

Follow these instructions to have your local environment prepared to run the demo below, as well as to build your own AI Mech.

1. Create a Poetry virtual environment and install the dependencies:

   poetry install && poetry shell

2. Fetch the software packages using the Open Autonomy CLI:

   autonomy packages sync --update-packages

   This will populate the Open Autonomy local registry (folder ./packages) with the required components to run the worker AI agents.

To help you integrate your own tools more easily, we’ve created a new base repository that serves as a minimal example of how to run the project. It’s designed to minimize setup time and provide a more intuitive starting point. This new repo is streamlined to give you a clean slate, making it easier than ever to get started.

Why Use the New Base Repo?

• Less Configuration: A clean setup that removes unnecessary complexities.
• Easier to Extend: Perfect for adding your own features and customizations.
• Clear Example: Start with a working example and build from there.

Feature Comparison

We highly encourage you to start with this base repo for future projects. You can find it here.

Warning
The old repo is no longer the recommended approach for running and extending the project. Although it’s still remains available for legacy projects, we advise you to use the new base repo to ensure you are working with the most current and efficient setup. Access the new mech repo here. Start with the preferred method mentioned above.

Follow the instructions below to run the AI Mech demo executing the tool in ./packages/valory/customs/openai_request.py. Note that AI Mechs can be configured to work in two modes: polling mode, which periodically reads the chain, and websocket mode, which receives event updates from the chain. The default mode used by the demo is polling.

First, you need to configure the worker AI agent. You need to create a .1env file which contains the AI agent configuration parameters. We provide a prefilled template (.example.env). You will need to provide or create an OpenAI API key.

# Copy the prefilled template
cp .example.env .1env

# Edit ".1env" and replace "dummy_api_key" with your OpenAI API key.

# Source the env file
source .1env

You may customize the agent's behaviour by setting these environment variables.

:note: The value of PROFIT_SPLIT_BALANCE should correspond to the units of payment based on payment model. By default it will trigger at 10^18 units

• For fixed price mechs, it corresponds to native currency units
• For token mechs, it corresponds to OLAS units
• For NVM mechs, it corresponds to credits. (1 xDAI on Gnosis and 1 USDC on Base correspond to 10^6 credits)

The rest of the common environment variables are present in the service.yaml, which are customizable too.

Warning
The demo AI agent is configured to match a specific on-chain agent blueprint (ID 3 on Mech Hub). Since you will not have access to its private key, your local instance will not be able to transact. However, it will be able to receive Requests for AI tasks sent from Mech Hub. These Requests will be executed by your local instance, but you will notice that a failure will occur when it tries to submit the transaction on-chain (Deliver type).

Now, you have two options to run the worker: as a standalone agent instance or as an AI agent.

1. Ensure you have a file with a private key (ethereum_private_key.txt). You can generate a new private key file using the Open Autonomy CLI:

   autonomy generate-key ethereum

2. From one terminal, run the instance:

   bash run_agent.sh

3. From another terminal, run the Tendermint node:

   bash run_tm.sh

1. Ensure you have a file with the agent instance address and private key (keys.json). You can generate a new private key file using the Open Autonomy CLI:

   autonomy generate-key ethereum -n 1

2. Ensure that the variable ALL_PARTICIPANTS in the file .1env contains the agent instance address from keys.json:

   ALL_PARTICIPANTS='["your_agent_address"]'

3. Run, the AI agent:

   bash run_service.sh

Use the mech-client, which can be used either as a CLI or directly from a Python script.

To perform mech requests from your AI agent, use the mech_interact_abci skill. This skill abstracts away all the IPFS and contract interactions so you only need to care about the following:

• Add the mech_interact_abci skill to your dependency list, both in packages.json, aea-config.yaml and any composed skill.yaml.

• Import MechInteractParams and MechResponseSpecs in your models.py file. You will also need to copy some dataclasses to your rounds.py.

• Add mech_requests and mech_responses to your skills' SynchonizedData class (see here)

• To send a request, prepare the request metadata, write it to synchronized_data.mech_requests and transition into mech_interact.

• You will need to appropriately chain the mech_interact_abci skill with your other skills (see here) and transaction_settlement_abci.

• After the interaction finishes, the responses will be inside synchronized_data.mech_responses

For a complete list of required changes, use this PR as reference.

You can create and mint your own AI Mech that handles requests for tasks that you can define.

You can take a look at the preferred method mentioned above to get started quickly and easily.

Once your AI agent works locally, you have the option to run it on a hosted service like Propel.

🚧 Under Construction 🚧 We are working on adding a simple tool for the quickstart

🚧 Under Construction 🚧

A keyfile is just a file with your ethereum private key as a hex-string, example:

0x0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcd

Make sure you don't have any extra characters in the file, like newlines or spaces.

There is no Mech deployed on the Mech Marketplace at the moment.

If the mech has problems connecting to tendermint make sure that not all the instances are configured to connect to ${TM_P2P_ENDPOINT_NODE_0:str:node0:26656}.

You can update these information inside the : packages/valory/services/mech/service.yaml

If we have more than one agent instances in the AI agent, these instances should not share the same configuration. You can use different nodes like so :

-${TM_P2P_ENDPOINT_NODE_1
-${TM_P2P_ENDPOINT_NODE_2
-${TM_P2P_ENDPOINT_NODE_3