RRepoGEO

REPOGEO REPORT · LITE

buzzer-re/Rikugan

Default branch main · commit 7eb1f8b2 · scanned 6/5/2026, 1:22:13 PM

GitHub: 632 stars · 73 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface buzzer-re/Rikugan, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README's opening to explicitly state its category and differentiator

    Why:

    CURRENT
    # Rikugan (六眼)

A reverse-engineering agent for **IDA Pro** and **Binary Ninja** that integrates a multi-provider LLM directly into your analysis UI. This project was vibecoded together with my friend, Claude Code.
    COPY-PASTE FIX
    # Rikugan (六眼)

Rikugan is an **LLM agent for reverse engineering**, integrating a multi-provider LLM directly into your **IDA Pro** and **Binary Ninja** analysis UI. It's an in-process agent, not a web framework or a generic RE tool, designed to automate and assist with binary analysis tasks.
  • hightopics#2
    Add relevant topics to the repository

    Why:

    CURRENT
    (none)
    COPY-PASTE FIX
    reverse-engineering, llm, agent, ida-pro, binary-ninja, binary-analysis, security-research, ai-assistant, disassembler
  • mediumreadme#3
    Add a dedicated 'What Rikugan Is (and Isn't)' section to the README

    Why:

    COPY-PASTE FIX
    ## What Rikugan Is (and Isn't)

Rikugan is an **LLM agent** designed to live *inside* your reverse engineering host (IDA Pro, Binary Ninja). It's not:

*   **A standalone LLM client:** Rikugan has its own agentic loop, context management, and in-process tool orchestration, distinct from generic LLM APIs or CLI tools.
*   **A web framework:** Unlike projects focused on web development, Rikugan is purpose-built for binary analysis.
*   **A replacement for your disassembler:** It enhances, rather than replaces, IDA Pro or Binary Ninja by providing an intelligent assistant directly within your workflow.

Instead, Rikugan offers a unique, integrated LLM experience for automating and assisting complex reverse engineering tasks.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface buzzer-re/Rikugan
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
IDA Pro
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. IDA Pro · recommended 2×
  2. IDAPython · recommended 2×
  3. OpenAI API · recommended 2×
  4. ollama/ollama · recommended 2×
  5. NationalSecurityAgency/ghidra · recommended 2×
  • CATEGORY QUERY
    How can I use an LLM to assist with reverse engineering tasks directly within my disassembler?
    you: not recommended
    AI recommended (in order):
    1. IDA Pro
    2. IDAPython
    3. OpenAI API
    4. Ollama (ollama/ollama)
    5. llama-cpp-python (abetlen/llama-cpp-python)
    6. Ghidra (NationalSecurityAgency/ghidra)
    7. Binary Ninja
    8. Radare2 (radareorg/radare2)
    9. Cutter (rizinorg/cutter)
    10. R2Pipe (radareorg/r2pipe)
    11. VS Code (microsoft/vscode)
    12. Reverse Engineering (microsoft/vscode-reverse-engineering)
    13. GitHub Copilot
    14. Codeium
    15. Llama 3
    16. Mixtral
    17. llama.cpp (ggerganov/llama.cpp)

    AI recommended 17 alternatives but never named buzzer-re/Rikugan. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for an AI agent to automate and improve binary analysis within existing RE tools.
    you: not recommended
    AI recommended (in order):
    1. IDA Pro
    2. IDAPython
    3. OpenAI API
    4. GPT-4
    5. GPT-3.5 Turbo
    6. Llama 3
    7. Mixtral
    8. Code Llama
    9. Ollama (ollama/ollama)
    10. LM Studio
    11. Ghidra (NationalSecurityAgency/ghidra)
    12. GhidraDev
    13. Eclipse
    14. Binary Ninja
    15. Binary Ninja API
    16. Panda (panda-re/panda)
    17. QEMU (qemu/qemu)
    18. Angr (angr/angr)
    19. Radare2 (radareorg/radare2)
    20. Cutter (rizinorg/cutter)
    21. R2pipe (radareorg/r2pipe)

    AI recommended 21 alternatives but never named buzzer-re/Rikugan. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of buzzer-re/Rikugan?
    pass
    AI named buzzer-re/Rikugan explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts buzzer-re/Rikugan in production, what risks or prerequisites should they evaluate first?
    pass
    AI named buzzer-re/Rikugan explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo buzzer-re/Rikugan solve, and who is the primary audience?
    pass
    AI named buzzer-re/Rikugan explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of buzzer-re/Rikugan. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/buzzer-re/Rikugan.svg)](https://repogeo.com/en/r/buzzer-re/Rikugan)
HTML
<a href="https://repogeo.com/en/r/buzzer-re/Rikugan"><img src="https://repogeo.com/badge/buzzer-re/Rikugan.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

buzzer-re/Rikugan — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite