GitHub Repository

LLM-powered automated reverse-engineering engine for vendor-abandoned hardware and software

0 starsPython

Revenant – automatic LLM powered reverse engineering and reimplement

Name: Revenant – automatic LLM powered reverse engineering and reimplement
Availability: InStock
Author: sylwester

by sylwester·Jun 22, 2026·5 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Automates firmware analysis and hardware bringup — radare2 plus agentic LLM workflows in Docker.

Strengths

•Stage-DAG pipeline produces pin maps, device trees, and buildable firmware projects automatically.
•Built by actual hardware engineer solving their own reverse engineering workflow pain.

Weaknesses

•Early stage with zero stars — unproven at scale on real abandoned hardware.
•LLM-powered reverse engineering is emerging space with similar tools appearing.

Post Description

I am a hardware engineer and security researcher and I've been wondering whether my work could be partially automated, so I can focus on other topics as well, so I build revenant - a LLM powered (Claude, OpenAI, local AI) toolkit that builds around radare2, ghidra etc and can fully automatically analyze firmware, implement open source skeletons incl. pinouts, hardware bringup, peripheral bringup etc. or can even 1:1 replicate existing firmware so old hardware can be resurrected with modern toolchains.

Some applications are:

- Give old hardware new life

- Security Analysis of shady firmware

Check it at: https://github.com/DatanoiseTV/revenant

I would love some input on this and maybe some recommendations for improvements.