# Dryxio/auto-re-agent

Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions from binaries.

Repository: https://github.com/Dryxio/auto-re-agent
Canonical: https://ross.abutalabs.com/products/auto-re-agent
Language: Python
License: MIT
License Family: permissive
Topics: ai-agent, autonomous-agent, binary-analysis, c-plus-plus, claude, codex, cybersecurity, decompilation, ghidra, llm, reverse-engineering, source-code-recovery, static-analysis
Last push: 2026-07-23T11:22:05+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 94, longevity 14
- inputs: {"age_days": 197, "days_push": 41, "days_rel": 41, "gap_med": 7, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1410, forks 163 (observed 2026-08-28T04:04:38.626670+00:00)

## What it is
auto-re-agent is an open-source AI reverse-engineering agent that combines Ghidra binary analysis with LLMs (Claude, Codex, OpenAI-compatible) to reconstruct and validate C/C++ functions from compiled binaries. It runs an autonomous reverser/checker/fix loop with structural verification, build/test gates, and parity analysis.

## Use cases
- reconstruct C/C++ source from compiled binaries
- decompile functions with Ghidra and have an LLM rewrite them
- validate recovered functions against build and test gates
- recover source code when original source is lost
- analyze malware or third-party binaries without source
- automate static binary analysis with an AI agent

## When to choose
- you need to recover readable C/C++ implementations from stripped or compiled binaries
- you already use Ghidra and want LLM-assisted decompilation with verification
- you want conservative, evidence-driven reconstruction rather than blind LLM output

## When to avoid
- you need guaranteed semantic equivalence - the tool only provides conservative structural verification
- you want to automatically patch your original source tree - it only generates candidate implementations
- you have no access to any LLM API or CLI
- you need a fully interactive GUI reversing workflow rather than an autonomous agent

## Facets
- artifact type: cli-tool
- maturity: active
- function: reverse-engineering, agent-framework, llm-inference, linter, cli, security
- domain: reverse-engineering, security, artificial-intelligence, developer-tools
- platform: python, cli, windows
- tags: ghidra, decompilation, binary-analysis, llm-agent, source-code-recovery, claude, codex, autonomous-agent, ai-agents, command-line, linux, macos

## Member repositories
- Dryxio/auto-re-agent (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.626670+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 2026-08-30T04:38:26.242576+00:00, confidence not recorded.
  - readme: https://github.com/Dryxio/auto-re-agent (fetched 2026-08-28T04:04:38.626670+00:00, sha 16610a9d7ee7)
  - registry_pypi: https://pypi.org/pypi/auto-re-agent/json (fetched 2026-08-29T11:51:45.019511+00:00, sha b99ea56f0d00)
- Data as of 2026-08-30T08:39:29.467469+00:00.