# JusticeRage/Gepetto

IDA plugin which queries language models to speed up reverse-engineering

Repository: https://github.com/JusticeRage/Gepetto
Canonical: https://ross.abutalabs.com/products/gepetto
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ida-pro, reverse-engineering, openai, python, gpt-5-api
Last push: 2026-08-15T17:09:38+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 45, longevity 97
- inputs: {"age_days": 1368, "days_push": 18, "days_rel": 287, "gap_med": 46, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3461, forks 332 (observed 2026-08-28T04:08:05.646827+00:00)

## What it is
Gepetto is an IDA Pro plugin that queries large language models (OpenAI, Anthropic, Gemini, Ollama, and others) to explain decompiled functions and automatically rename variables. It speeds up reverse-engineering workflows by adding AI-assisted analysis directly into the IDA interface.

## Use cases
- explain what a decompiled function does with an LLM
- automatically rename variables in IDA Pro
- speed up reverse-engineering of binaries
- use local models via Ollama for offline binary analysis
- understand obfuscated or unfamiliar code faster

## When to choose
- you use IDA Pro 7.6+ for reverse-engineering and want AI assistance
- you want to quickly understand decompiled functions without manual analysis
- you want automatic variable renaming suggestions from an LLM
- you prefer choosing among multiple LLM providers including local Ollama models

## When to avoid
- you don't use IDA Pro or use a version older than 7.6
- you need fully offline analysis without any LLM provider (unless using Ollama)
- you can't accept sending binary code to external API services
- you want a standalone decompiler rather than an IDA plugin

## Facets
- artifact type: plugin
- maturity: active
- function: reverse-engineering, llm-inference, nlp, developer-tools
- domain: reverse-engineering, security, large-language-models, developer-tools
- platform: windows, python
- tags: ida-pro, decompiler, openai, anthropic, ollama, binary-analysis, static-analysis, macos, linux

## Member repositories
- JusticeRage/Gepetto (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.646827+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:36:54.789558+00:00, confidence not recorded.
  - readme: https://github.com/JusticeRage/Gepetto (fetched 2026-08-28T04:08:05.646827+00:00, sha 269c0978aa84)
- Data as of 2026-08-30T08:39:29.467469+00:00.
