RRepoGEO

REPOGEO REPORT · LITE

xenodium/agent-shell

Default branch main · commit 3f3f91ea · scanned 5/19/2026, 4:42:33 PM

GitHub: 1,177 stars · 167 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 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 xenodium/agent-shell, 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 core value proposition to the top of the README

    Why:

    CURRENT
    The current README structure where the 'This project needs your funding' section appears before the 'agent-shell' description.
    COPY-PASTE FIX
    Move the 'agent-shell' section (starting with 'A native Emacs shell to interact with LLM agents powered by ACP...') to immediately follow the title and badges, before any funding requests.
  • mediumreadme#2
    Add a 'What problem does agent-shell solve?' section to the README

    Why:

    COPY-PASTE FIX
    Add a new section, perhaps titled 'What problem does agent-shell solve?' or 'Why agent-shell?', that clearly states: 'agent-shell provides a native Emacs buffer for developers to securely integrate and interact with various LLM agents (like Gemini CLI, Claude Agent, Auggie, Mistral Vibe) from a single, unified interface, powered by the Agent Client Protocol (ACP). It enables direct, structured execution of local shell commands via natural language.'
  • lowtopics#3
    Add more specific topics related to Emacs workflow and agent integration

    Why:

    CURRENT
    ai, claude, claude-code, codex, emacs, emacs-lisp, gemini, goose, llm, openai
    COPY-PASTE FIX
    ai, claude, claude-code, codex, emacs, emacs-lisp, emacs-workflow, gemini, goose, llm, llm-integration, openai, agent-protocol

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 xenodium/agent-shell
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Emacs-Eglot-Copilot
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Emacs-Eglot-Copilot · recommended 1×
  2. Emacs-OpenAI · recommended 1×
  3. Emacs-GPT · recommended 1×
  4. Emacs-LLM · recommended 1×
  5. Emacs-Shell-GPT · recommended 1×
  • CATEGORY QUERY
    How can I integrate large language model agents directly into my Emacs workflow?
    you: not recommended
    AI recommended (in order):
    1. Emacs-Eglot-Copilot
    2. Emacs-OpenAI
    3. Emacs-GPT
    4. Emacs-LLM
    5. Emacs-Shell-GPT
    6. url.el

    AI recommended 6 alternatives but never named xenodium/agent-shell. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What Emacs tools allow me to chat with various AI models from a single interface?
    you: not recommended
    AI recommended (in order):
    1. llm-mode (karthink/llm-mode)
    2. chatgpt.el (joshcho/ChatGPT.el)
    3. ollama.el (emacs-ollama/ollama.el)
    4. gptel (karthink/gptel)
    5. emacs-openai (emacs-openai/emacs-openai)

    AI recommended 5 alternatives but never named xenodium/agent-shell. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    pass

  • 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 xenodium/agent-shell?
    pass
    AI named xenodium/agent-shell explicitly

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

  • If a team adopts xenodium/agent-shell in production, what risks or prerequisites should they evaluate first?
    pass
    AI named xenodium/agent-shell 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 xenodium/agent-shell solve, and who is the primary audience?
    pass
    AI named xenodium/agent-shell 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 xenodium/agent-shell. 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/xenodium/agent-shell.svg)](https://repogeo.com/en/r/xenodium/agent-shell)
HTML
<a href="https://repogeo.com/en/r/xenodium/agent-shell"><img src="https://repogeo.com/badge/xenodium/agent-shell.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

xenodium/agent-shell — 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