> ## Documentation Index > Fetch the complete documentation index at: https://proto.evodesign.org/docs/llms.txt > Use this file to discover all available pages before exploring further. # Introduction > Computational biology and biological AI tools through a single, consistent Python interface

Google DeepMind

Google DeepMind

UT Southwestern

Broad Institute

The Jackson Laboratory

Yale University

Google DeepMind

Microsoft Research

Google DeepMind

Google DeepMind

Rutgers University

Columbia University

Google DeepMind

Aureka AI Research

Salesforce Research

MIT Jameel Clinic

Google DeepMind

Google DeepMind

UT Southwestern

Broad Institute

The Jackson Laboratory

Yale University

Google DeepMind

Microsoft Research

Google DeepMind

Google DeepMind

Rutgers University

Columbia University

Google DeepMind

Aureka AI Research

Salesforce Research

MIT Jameel Clinic

The Open-Source Infrastructure Layer for Biology

evo-design/proto-tools

```bash bash icon="terminal" theme={null} pip install git+https://github.com/evo-design/proto-tools.git ```

# Proto Tools A lot of computational biology looks like this: find a tool that does what you need, spend half a day getting it to install, spend another day figuring out how to call it, then reformat the output so the next tool can use it. Every tool has its own opinions about Python versions, CUDA, weight paths, and input formats. Proto Tools implements these tools so they all behave the same way. Each one is a Python function with a Pydantic input and output. Fold a protein with AlphaFold3, sample sequences with ProteinMPNN, search with BLAST; the shape of the call is the same, and the first invocation quietly sets up the environment and weights in isolation. Use it on its own, or as the tools layer of the broader [Proto](https://github.com/evo-design/proto-language) framework. ## Key Features A quick tour of what proto-tools handles for you. Each card opens a deeper guide. Consistent Python APIs with standardized Pydantic Input/Config/Output models across all tools Each tool gets its own virtual environment; weights and dependencies are fetched and cached on first use Automatic GPU allocation, LRU eviction, and multi-GPU routing Fan a single tool call out across every visible GPU with ToolPool

## Tool Catalog Every tool we implement, at a glance. Select any to open its page.

## Get Started Set up the package and optional dependencies Run your first tool in 5 minutes Understand the tool pattern and execution model