---
type: "raw_signal"
id: "kong-the-world-s-first-agentic-reverse-engineer-6b2533"
slug: "kong-the-world-s-first-agentic-reverse-engineer-6b2533"
title: "kong: The world's first agentic reverse engineer"
description: "Kong is a public open-source project for LLM-assisted binary reverse engineering in Ghidra."
retrieval_nugget: "Kong is a public open-source project for LLM-assisted binary reverse engineering in Ghidra."
observed_at: "2026-09-27"
record_date: "2026-09-27"
date_kind: "observed_at"
why_it_matters: "Source: https://github.com/amruth-sn/kong"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "github.com"
topics: []
entities: []
related_patterns: []
source_url: "https://github.com/amruth-sn/kong"
source_urls: ["https://github.com/amruth-sn/kong"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:kong-the-world-s-first-agentic-reverse-engineer-6b2533"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/kong-the-world-s-first-agentic-reverse-engineer-6b2533/","markdown":"https://newruntime.com/signals/kong-the-world-s-first-agentic-reverse-engineer-6b2533.md","json":"https://newruntime.com/signals/kong-the-world-s-first-agentic-reverse-engineer-6b2533.json"}
---

# kong: The world's first agentic reverse engineer

## Retrieval answer

Kong is a public open-source project for LLM-assisted binary reverse engineering in Ghidra.

Kong is a public open-source project for LLM-assisted binary reverse engineering in Ghidra. Its repository presents an agentic workflow intended to recover higher-level program meaning from stripped or obfuscated binaries, including function names, data types, and structures. The project includes tests, benchmark material, tagged releases, and code across Rust and Python components, giving readers a concrete implementation to inspect rather than only a product claim.

Source: https://github.com/amruth-sn/kong

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)