Open Autonomy Framework

Open Autonomy is a framework for the creation of AI agents: off-chain autonomous AI agents which run as a multi-agent-system (MAS) and offer enhanced functionalities on-chain. AI agents expand the range of operations that traditional smart contracts provide, making it possible to execute arbitrarily complex operations (such as machine-learning algorithms). Most importantly, AI agents are decentralized, trust-minimized, transparent, and robust.

Get started developing AI agents

Read the Open Autonomy documentation to learn more about AI agents. Follow the set up and quick start guides to start building your own AI agents.

For developers contributing to the framework: install from source

Ensure your machine satisfies the following requirements:
- Python >= 3.10
- Tendermint ==0.34.19
- IPFS node ==v0.6.0
- Pip
- Pipenv >=2021.x.xx
- Go ==1.17.7
- Kubectl
- Docker Engine
- Docker Compose
- Skaffold >= 1.39.1
- Gitleaks

Clone the repository:

git clone git@github.com:valory-xyz/open-autonomy.git

Pull pre-built images:

docker pull valory/autonolas-registries:latest
docker pull valory/acn-node:latest
docker pull valory/contracts-amm:latest
docker pull valory/safe-contract-net:latest
docker pull valory/slow-tendermint-server:0.1.0

Create and launch a virtual environment. Also, run this during development, every time you need to re-create and launch the virtual environment and update the dependencies:
```
make new_env && pipenv shell
```
:information_source: Note: we are using atheris in order to perform fuzzy testing. The dependency is not listed in the Pipfile because it is not supported on Windows. If you need to run or implement a fuzzy test, please manually install the dependency. If you are developing on Mac, please follow the extra steps described here.

Fetch packages:

autonomy packages sync --update-packages

Cite

If you are using our software in a publication, please consider to cite it with the following BibTex entry:

@misc{open-autonomy,
  Author = {David Minarsch and Marco Favorito and Viraj Patel and Adamantios Zaras and David Vilela Freire and Michiel Karrenbelt and 8baller and Ardian Abazi and Yuri Turchenkov and José Moreira Sánchez},
  Title = {Open Autonomy Framework},
  Year = {2021},
}

Metadata

Release files for open-autonomy 0.21.29

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for open-autonomy 0.21.29
File	Size	Uploaded
open_autonomy-0.21.29.tar.gz	1.2 MB	Sep 14, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for open-autonomy 0.21.29
File	Interpreter	ABI	Platform	Reset
open_autonomy-0.21.29-py3-none-any.whl 1.7 MB Sep 14, 2026	Python 3	none	any	Details

Total release size: 2.8 MB

Release files / open_autonomy-0.21.29.tar.gz

Download URL	open_autonomy-0.21.29.tar.gz
Size	1.2 MB
Tags	Source
SHA-256 checksum How to use checksums	`6cc576959fdfb3e97668d1de2e6733a16d1547fc1b0c359c729e7bee35366d5e`
BLAKE2b-256 checksum How to use checksums	`78c27396f77eebf75a2feb32a824df3da253c34c31bc420ba3f2ffd20a06e241`
Upload date	Sep 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Release files / open_autonomy-0.21.29-py3-none-any.whl

Download URL	open_autonomy-0.21.29-py3-none-any.whl
Size	1.7 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`1dc5d8c0d4cd434aebdd2328ed99281bc3239cd34d264c004000d7304e783123`
BLAKE2b-256 checksum How to use checksums	`efbe34143853bbcc55995d225821688a9b58dc4b5d3b114ec2f7387ca82b95eb`
Upload date	Sep 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`