Skip to main content

Installation

Step 1: Install the package

Proto-tools requires Python 3.10+:
bash
To also run the MCP server, which exposes these tools to coding agents, install the mcp extra:
bash
A direct PyPI install (pip install proto-tools) will be available soon.
If you are developing or contributing to this project, follow the setup instructions in CONTRIBUTING.md instead.

Step 2: Configure storage (optional)

All persistent data (model weights and tool environments) is cached under the PROTO_HOME directory on first use (defaults to ~/.proto/). To customize the storage location, you can specify a path via the following environment variable:
bash
For shared filesystems, model weights can be reused to avoid downloading duplicate copies. The PROTO_MODEL_CACHE environment variable lets you point just the weights at that shared location (sharing tool environments is not recommended): export PROTO_MODEL_CACHE=/path/to/shared/weights. See Storage guide for all details and options.

Step 3: Gated model access (optional)

A few tools use gated models or software that require accepting a license / terms-of-use first (e.g. ESM3, AlphaGenome, AlphaFold3, X3DNA). See notes/gated-models.md for the full list and per-model access steps.

Step 4: Remote compute (optional) Modal

proto-tools enables users to scale their tool use beyond their local machine through an integration with Modal, a serverless compute platform that allows users to execute models and tools in remote containers. To learn more about setting up Modal, see proto_tools/modal/README.md for instructions related to account setup, deploying a tool, and costs, or the Cloud Inference guide for a runnable walkthrough.
You’re all set up! Start with the quickstart, then check out the rest of the guides — short notebooks covering tool environments, persistent execution, device management, parallel multi-GPU runs, and remote execution.

You’re all set! Head over to the Quickstart to run your first tool, or browse the tool catalog to see what’s available.