IEKit

An toolkit for autonomous services implementing a decentralized Impact Evaluator built with the Open Autonomy framework.

The demo AI agent for the IEKit tracks mentions of @autonolas on Twitter, assigns scores to them and writes those scores to a Ceramic stream.

Running a demo AI agent

To learn how to run a demo AI agent based on the IEKit, read the IEKit technical docs(Deprecated and docs need to be updated).

For Developers

Prepare the environment to build your own IEKit-based AI agent.

• Clone the repository:

  git clone git@github.com:valory-xyz/iekit.git
  

• System requirements:

  • Python >=3.10, <3.15
  • Tendermint ==0.34.19
  • IPFS node ==0.6.0
  • uv
  • Docker Engine <25.0
  • Docker Compose

• Pull pre-built images:

  docker pull valory/autonolas-registries:latest
  docker pull valory/safe-contract-net:latest
  

• Create development environment:

  uv sync --all-groups
  

• Configure command line:

  autonomy init --reset --author valory --remote --ipfs --ipfs-node "/dns/registry.autonolas.tech/tcp/443/https"
  

• Pull packages:

  autonomy packages sync --update-packages
  

• Create some dummy Ceramic streams

  python create_streams.py
  

• Fill in the required env vars in .sample_env

• Run as a local agent (development):

  aea-helpers run-agent --name valory/impact_evaluator --connection-key
  

  To run multiple agents on the same machine, add --free-ports.

• Run as a service (Docker deployment):

  aea-helpers run-service --name valory/impact_evaluator --env-file .env