Apps · Reverse-engineering plugin for Ghidra (needs a local model server)
ReVa
Ghidra extension that gives an AI model small, focused reverse-engineering tools over MCP, in the Ghidra window or headless.
macOSWindowsLinux
At a glance
- Best for
- Letting an agent triage and explore a binary step by step, with less guessing.
- Inference engine
- uses your MCP client’s model server
- GPU support
- None of its own: it talks to a llama.cpp or MLX LM server
- Opens
- GGUF
- MLX
- Features
- MCP tools
- Tool calling
- Agent workflows
- Platforms
- Runs inside Ghidra 12 or later (Java 21; Ghidra 12.2+ needs Java 25).
Install
macOS
Download the release for your Ghidra version, then in Ghidra choose File › Install Extensions
Windows
Download the release for your Ghidra version, then in Ghidra choose File › Install Extensions
Linux
Download the release for your Ghidra version, then in Ghidra choose File › Install Extensions
5 models on this site run in ReVa
Models tagged for reverse engineering that support tool calling, with a GGUF or MLX build to serve locally. Raw decompilers such as LLM4Decompile run on their own in llama.cpp or LM Studio instead.
| Model | Made by | Type | Size | Opens it as | Quality tier |
|---|---|---|---|---|---|
| GLM-4.7 Flash (30B-A3B) | Zhipu AI | LLM | 31B (3.0B active) | GGUF or MLX | 88 |
| Devstral 2 (123B) | Mistral AI | LLM | 125B | GGUF or MLX | 86 |
| Qwen3 Coder 30B-A3B | Alibaba | LLM | 31B (3.3B active) | GGUF or MLX | 78 |
| Qwen3 30B-A3B | Alibaba | LLM | 31B (3.3B active) | GGUF or MLX | 74 |
| gpt-oss 20B | OpenAI | LLM | 21B (3.6B active) | GGUF or MLX | 70 |
Alternatives
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.