> ## Documentation Index
> Fetch the complete documentation index at: https://codegeninc-codegen-bot-sdk-docs-2-0.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Codegen

export const CODEGEN_SDK_GITHUB_URL = "https://github.com/codegen-sh/codegen-sdk";

export const COMMUNITY_SLACK_URL = "https://community.codegen.com";

[Codegen](https://github.com/codegen-sh/codegen-sdk) is a python library for manipulating codebases.

It provides a scriptable interface to a powerful, multi-lingual language server built on top of [Tree-sitter](https://tree-sitter.github.io/tree-sitter/).

```python
from codegen import Codebase

# Codegen builds a complete graph connecting
# functions, classes, imports and their relationships
codebase = Codebase("./")

# Work with code without dealing with syntax trees or parsing
for function in codebase.functions:
    # Comprehensive static analysis for references, dependencies, etc.
    if not function.usages:
        # Auto-handles references and imports to maintain correctness
        function.remove()

# Fast, in-memory code index
codebase.commit()
```

<Note>
  Codegen handles complex refactors while maintaining correctness, enabling a broad set of advanced code manipulation programs.
</Note>

<Tip>Codegen works with both Python and Typescript/JSX codebases. Learn more about language support [here](/building-with-codegen/language-support).</Tip>

## Quick Started

<Note>
  Codegen requires Python 3.12 - 3.13 (recommended: Python 3.13+).
</Note>

### Using UV (Recommended)

```bash
uv tool install codegen --python 3.13
```

### Using Pipx

<Warning>
  Pipx is not officially supported by Codegen, but it should still work.
</Warning>

```bash
pipx install codegen
```

<Note>
  For further & more in depth installation instructions, see the [installation guide](/introduction/installation).
</Note>

## What can I do with Codegen?

Codegen's simple yet powerful APIs enable a range of applications, including:

<CardGroup cols={2}>
  <Card title="Build a Code Agent" icon="robot" href="/tutorials/build-code-agent">
    Create an intelligent agent that can analyze and manipulate your codebase using natural language.
  </Card>

  <Card title="Visualize Your Codebase" icon="diagram-project" href="/tutorials/codebase-visualization">
    Generate interactive visualizations of your codebase's structure, dependencies, and relationships.
  </Card>

  <Card title="Mine Codebase Data" icon="database" href="/tutorials/training-data">
    Create high-quality training data for fine-tuning LLMs on your codebase.
  </Card>

  <Card title="Build Codemods" icon="wand-magic-sparkles" href="/tutorials/at-a-glance#api-migrations">
    Create powerful code transformations to automate large-scale changes.
  </Card>
</CardGroup>

See below for an example call graph visualization generated with Codegen.

<Frame caption="Call graph visualization for modal/modal-client/_Client">
  <iframe
    width="100%"
    height="500px"
    scrolling="no"
    src={`https://codegen.sh/embedded/graph?id=66e2e195-ceec-4935-876a-ed4cfc1731c7&zoom=0.5&targetNodeName=_Client`}
    className="rounded-xl"
    style={{
backgroundColor: "#15141b",
}}
  />
</Frame>

<Info>
  View source code on [modal/modal-client](https://github.com/modal-labs/modal-client/blob/cbac0d80dfd98588027ecd21850152776be3ab82/modal/client.py#L70). View codemod on [codegen.sh](https://www.codegen.sh/codemod/66e2e195-ceec-4935-876a-ed4cfc1731c7/public/diff)
</Info>

## Get Started

<CardGroup cols={2}>
  <Card title="Get Started" icon="graduation-cap" href="/introduction/getting-started">
    Follow our step-by-step tutorial to start manipulating code with Codegen.
  </Card>

  <Card title="Tutorials" icon="diagram-project" href="/tutorials/at-a-glance">
    Learn how to use Codegen for common code transformation tasks.
  </Card>

  <Card title="View on GitHub" icon="github" href={CODEGEN_SDK_GITHUB_URL}>
    Star us on GitHub and contribute to the project.
  </Card>

  <Card title="Join our Slack" icon="slack" href={COMMUNITY_SLACK_URL}>
    Get help and connect with the Codegen community.
  </Card>
</CardGroup>

## Why Codegen?

Many software engineering tasks - refactors, enforcing patterns, analyzing control flow, etc. - are fundamentally programmatic operations. Yet the tools we use to express these transformations often feel disconnected from how we think about code.

Codegen was engineered backwards from real-world refactors we performed for enterprises at [Codegen, Inc.](/introduction/about). Instead of starting with theoretical abstractions, we built the set of APIs that map directly to how humans and AI think about code changes:

* **Natural Mental Model**: Express transformations through high-level operations that match how you reason about code changes, not low-level text or AST manipulation.
* **Clean Business Logic**: Let the engine handle the complexities of imports, references, and cross-file dependencies.
* **Scale with Confidence**: Make sweeping changes across large codebases consistently across Python, TypeScript, JavaScript, and React.

As AI becomes increasingly sophisticated, we're seeing a fascinating shift: AI agents aren't bottlenecked by their ability to understand code or generate solutions. Instead, they're limited by their ability to efficiently manipulate codebases. The challenge isn't the "brain" - it's the "hands."

We built Codegen with a key insight: future AI agents will need to ["act via code,"](/blog/act-via-code) building their own sophisticated tools for code manipulation. Rather than generating diffs or making direct text changes, these agents will:

1. Express transformations as composable programs
2. Build higher-level tools by combining primitive operations
3. Create and maintain their own abstractions for common patterns

This creates a shared language that both humans and AI can reason about effectively, making code changes more predictable, reviewable, and maintainable. Whether you're a developer writing a complex refactoring script or an AI agent building transformation tools, Codegen provides the foundation for expressing code changes as they should be: through code itself.