Gepetto

Gepetto is a Python plugin which uses various large language models to provide meaning to functions decompiled by IDA Pro (≥ 7.6). It can leverage them to explain what a function does, and to automatically rename its variables. Here is a simple example of what results it can provide in mere seconds:

Setup

Using hcli (Recommended)

The easiest way to install Gepetto is using the Hex-Rays CLI tool (hcli):

pip install ida-hcli
hcli plugin install gepetto

This will automatically install the plugin to your IDA user directory.

Manual Installation

Alternatively, you can manually install the plugin:

1. Drop this script (gepetto.py, as well as the gepetto/ folder) into your IDA plugins folder ($IDAUSR/plugins).
2. The plugins directory location depends on your system:
   • Windows: %APPDATA%\Hex-Rays\IDA Pro\plugins\
   • macOS: ~/.idapro/plugins/
   • Linux: ~/.idapro/plugins/
3. Install the required packages to IDA's Python installation. Find which interpreter IDA is using by checking the following registry key: Computer\HKEY_CURRENT_USER\Software\Hex-Rays\IDA (default on Windows: %LOCALAPPDATA%\Programs\Python\Python39).
4. With the corresponding interpreter, simply run:

   [/path/to/python] -m pip install -r requirements.txt
   

Configuration

Gepetto keeps its configuration in your IDA user directory, so it survives plugin upgrades:

• Windows: %APPDATA%\Hex-Rays\IDA Pro\cfg\gepetto\config.ini
• macOS / Linux: ~/.idapro/cfg/gepetto/config.ini

The first time the plugin runs it copies gepetto/config.ini there and tells you the path on the console. After that, the copy shipped with the plugin is only a template — edit the one in your user directory. Set GEPETTO_CONFIG_DIR to override the location entirely.

Add your API keys to that file, or supply them through the environment variables named in it. For OpenAI, a key can be created on this page. Please note that API queries are usually not free (although not very expensive) and you will need to set up a payment method with the corresponding provider.

Supported models

• Anthropic
  • claude-opus-4-7
  • claude-sonnet-4-6
  • claude-haiku-4-5
• OpenAI
  • gpt-5
  • gpt-5-mini
  • gpt-5-nano
  • gpt-4-turbo
  • gpt-4o
  • o4-mini
  • gpt-4.1
  • o3
  • o3-pro
• Google Gemini
  • gemini-2.0-flash
  • gemini-2.5-pro
  • gemini-2.5-flash
  • gemini-2.5-flash-lite-preview-06-17
• Azure OpenAI
  • gpt-35-turbo
  • gpt-35-turbo-1106
  • gpt-35-turbo-16k
  • gpt-4-turbo
  • gpt-4-turbo-2024-0409-gs
• Ollama
  • Any local model exposed through Ollama (will not appear if Ollama is not running)
• Groq
  • llama-3.1-70b-versatile
  • llama-3.2-90b-text-preview
  • mixtral-8x7b-32768
• Together
  • mistralai/Mixtral-8x22B-Instruct-v0.1 (does not support renaming variables)
• Novita AI
  • deepseek/deepseek-r1
  • deepseek/deepseek-v3
  • meta-llama/llama-3.3-70b-instruct
  • meta-llama/llama-3.1-70b-instruct
  • meta-llama/llama-3.1-405b-instruct
• Kluster.ai
  • deepseek-ai/DeepSeek-R1
  • deepseek-ai/DeepSeek-V3-0324
  • google/gemma-3-27b-it
  • klusterai/Meta-Llama-3.1-8B-Instruct-Turbo
  • klusterai/Meta-Llama-3.1-405B-Instruct-Turbo
  • klusterai/Meta-Llama-3.3-70B-Instruct-Turbo
  • meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  • meta-llama/Llama-4-Scout-17B-16E-Instruct
  • Qwen/Qwen2.5-VL-7B-Instruct
• LM Studio
  • Any local model exposed through LM Studio (will not appear if LM Studio Developer server is not running)

Adding your own provider

Gepetto loads providers from three places, each overriding the last on a menu name collision: the modules shipped in gepetto/models/, then any .py file in $IDAUSR/cfg/gepetto/providers/, then any installed distribution advertising a gepetto.providers entry point. Overrides are announced on the console, so you can replace a built-in provider without forking the plugin.

A drop-in provider uses exactly the same contract as a built-in one. For an OpenAI-compatible endpoint, the whole file is:

import openai
import gepetto.config
import gepetto.models.model_manager
from gepetto.models.openai import GPT


class MyProvider(GPT):
    @staticmethod
    def get_menu_name() -> str:
        return "MyProvider"

    @staticmethod
    def supported_models():
        return ["my-model-v1"]

    @staticmethod
    def is_configured_properly() -> bool:
        return bool(gepetto.config.get_config("MyProvider", "API_KEY", "MYPROVIDER_API_KEY"))

    def __init__(self, model):
        try:
            super().__init__(model)
        except ValueError:
            pass  # No OpenAI key needed for this provider.
        self.model = model
        self.client = openai.OpenAI(
            api_key=gepetto.config.get_config("MyProvider", "API_KEY", "MYPROVIDER_API_KEY"),
            base_url="https://api.example.com/v1",
        )


gepetto.models.model_manager.register_model(MyProvider)

Add a matching [MyProvider] section to your config.ini and restart IDA: providers are registered at load time, so a new key or a new file needs a restart before it appears in the menu.

To ship one as a package instead, expose the class or a register(register_model) callable:

[project.entry-points."gepetto.providers"]
myprovider = "myprovider:MyProvider"

Files in providers/ execute arbitrary Python when IDA starts. That is the same trust level as any IDA plugin, but only install providers you trust.

Usage

Once the plugin is installed properly, you should be able to invoke it from the context menu of IDA's pseudocode window, as shown in the screenshot below:

Switch between models supported by Gepetto from the Edit > Gepetto menu:

Gepetto also provides a CLI interface you can use to ask questions to the LLM directly from IDA. Make sure to select Gepetto in the input bar:

Hotkeys

The following hotkeys are available:

• Ask the model to explain the function: Ctrl + Alt + G
• Ask the model to add comments to the code: Ctrl + Alt + K
• Request better names for the function's variables: Ctrl + Alt + R

Initial testing shows that asking for better names works better if you ask for an explanation of the function first – I assume because the model then uses its own comment to make more accurate suggestions. There is an element of randomness to the AI's replies. If for some reason the initial response you get doesn't suit you, you can always run the command again.

Limitations

• The plugin requires access to the HexRays decompiler to function.
• All supported LLMs are general-purpose and may very well get things wrong! Always be critical of results returned!

Translations

You can change Gepetto's language by editing the locale in the configuration. For instance, to use the plugin in French, you would simply add:

[Gepetto]
LANGUAGE = "fr_FR"

The chosen locale must match the folder names in gepetto/locales. If the desired language isn't available, you can contribute to the project by adding it yourself! Create a new folder for the desired locale (ex: gepetto/locales/de_DE/LC_MESSAGES/), and open a new pull request with the updated .po file, which you can create by copying and editing gepetto/locales/gepetto.pot (replace all the lines starting with msgstr with the localized version).

Acknowledgements

• OpenAI, for making these incredible models, obviously
• Hex Rays, the makers of IDA for their lightning fast support
• Kaspersky, for initially funding this project
• HarfangLab, the current backer making this work possible
• @vanhauser-thc for contributing ideas of additional models and providers to support via his fork
• Everyone who contributed translations: @seifreed, @kot-igor, @ruzgarkanar, @orangetw