# mrphrazer/reverser_ai

Provides automated reverse engineering assistance through the use of local large language models (LLMs) on consumer hardware.

Repository: https://github.com/mrphrazer/reverser_ai
Canonical: https://ross.abutalabs.com/products/reverser_ai
Language: Python
License: GPL-2.0
License Family: copyleft
Last push: 2026-05-20T11:24:36+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 52, longevity 64
- inputs: {"age_days": 899, "days_push": 105, "days_rel": 105, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1127, forks 86 (observed 2026-08-28T04:03:41.554322+00:00)

## What it is
ReverserAI is a Binary Ninja plugin that provides automated reverse engineering assistance using locally-hosted large language models running entirely offline on consumer hardware. Its initial feature automatically suggests semantically meaningful function names derived from decompiler output, with a modular architecture intended to extend to IDA and Ghidra.

## Use cases
- rename stripped binary functions automatically with local llm
- offline ai-assisted reverse engineering for confidential binaries
- suggest meaningful function names from decompiler output
- run llm analysis on consumer hardware like apple silicon
- extend ai-assisted binary analysis to ida and ghidra
- combine static analysis with llm suggestions in binary ninja

## When to choose
- you need AI-assisted reverse engineering without sending code to cloud services
- you work in Binary Ninja and want automatic function name suggestions
- you have consumer-grade hardware and want offline LLM inference
- confidentiality requirements prevent using cloud-based LLMs

## When to avoid
- you need cloud-grade LLM performance for complex analysis
- you use a disassembler other than Binary Ninja without writing an adapter
- your hardware cannot run local LLMs with acceptable performance

## Facets
- artifact type: plugin
- maturity: active
- function: reverse-engineering, llm-inference, nlp
- domain: reverse-engineering, security, large-language-models, developer-tools
- platform: python, cross-platform
- tags: binary-ninja-plugin, local-llm, offline, function-naming, decompiler, ai-assisted-analysis, desktop

## Member repositories
- mrphrazer/reverser_ai (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:41.554322+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 2026-08-30T06:38:51.325973+00:00, confidence not recorded.
  - readme: https://github.com/mrphrazer/reverser_ai (fetched 2026-08-28T04:03:41.554322+00:00, sha 837851751d3f)
- Data as of 2026-08-30T08:39:29.467469+00:00.