ReverserAI

Requirements & limits

• The reviewed main commit is the v1.2 release of 2026-05-20, and plugin.json and setup.py both declare version 1.2. It installs through Binary Ninja’s plugin manager, or by cloning into Binary Ninja’s plugins folder and installing requirements.txt (huggingface-hub, llama-cpp-python, networkx, toml, typer) and the package; setup.py asks for Python 3.10+, and plugin.json lists macOS, Windows and Linux with minimum Binary Ninja build 2487.
• On first use the plugin downloads the selected GGUF model from Hugging Face: by default mistral-7b-instruct-v0.2.Q4_K_M.gguf, about 5 GB and needing about 5 GB of RAM, or a Mixtral-8x7B-Instruct quantization needing about 25 GB. Inference then runs on the local CPU or GPU, which the README describes as entirely offline. It advises at least 16 GB of RAM and 12 CPU threads and reports 20 to 30 seconds per query on CPU, or 2 to 5 seconds with GPU offload such as on Apple silicon. Model, memory mapping, CPU threads, GPU layers and seed are Binary Ninja settings that take effect after a restart.
• Three Plugins → ReverserAI commands cover the naming modes: Rename Current Function, Rename All Functions, and Enhance Function Naming with Context, which limits renaming to default-named functions referencing strings or import, library or external symbols. Each request puts one function’s HLIL text into a fixed prompt asking for a name of up to 20 characters, keeps the first line of the reply and writes it to the database as the function name without a confirmation step, logging the old and new names. Functions whose decompiler output exceeds the 4,000-token context fail with a logged warning.
• The README calls ReverserAI a proof of concept, notes that local models do not match cloud models, and plans code explanation, other decompilers and server-hosted inference only as future work. The examples folder ships a password-protected samples.zip of test samples, including the PowerPC stub triton_inject.bin from the Triton malware, and its README describes their results qualitatively. CI runs only ruff formatting and lint checks, a setup.py metadata check and a Python syntax parse; there are no tests. This collection reviewed source and documentation without running the plugin or any model.
• GPL-2.0 per LICENSE; plugin.json and setup.py state version 2 or later. Binary Ninja and the downloaded model weights keep their own licences and terms. The reviewed sources establish no REA connection.

About this entry

Type

Integration

Category

Independent agent workflows

Relationship

Independent agent integration

Targets

Binary

Sources reviewed 2026-10-20

The description was reviewed against primary sources. This does not establish runtime testing, security auditing or verified compatibility.

Report an outdated entry ↗Suggest a translation fix ↗

Primary sources

1. README.md GitHub · mrphrazer/reverser_ai · Revision 1d572da
2. plugin.json GitHub · mrphrazer/reverser_ai · Revision 1d572da
3. setup.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
4. requirements.txt GitHub · mrphrazer/reverser_ai · Revision 1d572da
5. __init__.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
6. reverser_ai/binary_ninja/__init__.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
7. reverser_ai/binary_ninja/function_name_gpt_wrapper.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
8. reverser_ai/gpt/function_name_gpt.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
9. reverser_ai/gpt/models.py GitHub · mrphrazer/reverser_ai · Revision 1d572da
10. examples/README.md GitHub · mrphrazer/reverser_ai · Revision 1d572da
11. .github/workflows/ci.yml GitHub · mrphrazer/reverser_ai · Revision 1d572da
12. LICENSE GitHub · mrphrazer/reverser_ai · Revision 1d572da
13. https://github.com/mrphrazer/reverser_ai/releases/tag/v1.2