buzzer-re/Rikugan

• highreadme#1

  Reposition the README's opening to explicitly state its category and differentiator

  原因：

  当前

  # 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.

  复制粘贴的修复

  复制

  # 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.

  待办完成忽略
• hightopics#2

  Add relevant topics to the repository

  原因：

  当前

  (none)

  复制粘贴的修复

  复制

  reverse-engineering, llm, agent, ida-pro, binary-ninja, binary-analysis, security-research, ai-assistant, disassembler

  待办完成忽略
• mediumreadme#3

  Add a dedicated 'What Rikugan Is (and Isn't)' section to the README

  原因：

  复制粘贴的修复

  复制

  ## 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.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How can I use an LLM to assist with reverse engineering tasks directly within my disassembler?

  你：未被推荐
  AI 推荐顺序：

  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 推荐了 17 个替代方案，却始终没点名 buzzer-re/Rikugan。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  Looking for an AI agent to automate and improve binary analysis within existing RE tools.

  你：未被推荐
  AI 推荐顺序：

  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 推荐了 21 个替代方案，却始终没点名 buzzer-re/Rikugan。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  warn

  建议：

• README presence

  pass

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

  pass
  ✓AI 明确点名了 buzzer-re/Rikugan

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

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

  pass
  ✓AI 明确点名了 buzzer-re/Rikugan

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

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

  pass
  ✓AI 明确点名了 buzzer-re/Rikugan

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？