RRepoGEO

REPOGEO REPORT · LITE

cosmicstack-labs/mercury-agent

Default branch main · commit 1b2d233f · scanned 5/25/2026, 2:32:08 PM

GitHub: 2,451 stars · 250 forks

AI VISIBILITY SCORE
27 /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
1 / 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 cosmicstack-labs/mercury-agent, 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 core value proposition with a clear H1

    Why:

    CURRENT
    <p align="center"><strong>Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access.</strong></p>
    COPY-PASTE FIX
    # Mercury Agent: A Soul-Driven Autonomous AI Agent

Mercury is an autonomous AI agent designed for 24/7 operation across CLI, Telegram, or Web. It features permission-hardened tools, token budgets, persistent memory (SQLite-backed Second Brain), and extensible skills, remembering what matters and asking before it acts.
  • hightopics#2
    Expand GitHub topics for better categorization

    Why:

    CURRENT
    ai-agent, ai-assistant, llm
    COPY-PASTE FIX
    ai-agent, ai-assistant, llm, autonomous-agent, persistent-memory, tool-use, multi-channel, cli-tool, telegram-bot, second-brain
  • mediumcomparison#3
    Add a 'Comparison to Alternatives' section in the README

    Why:

    COPY-PASTE FIX
    Add a new section to the README titled `## Comparison to Alternatives` or `## Why Mercury Agent?` that briefly outlines how Mercury Agent differs from popular autonomous agents like AutoGPT, BabyAGI, or SuperAGI, focusing on its unique features like 'soul-driven' design, permission hardening, token budgets, and specific multi-channel access.

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 cosmicstack-labs/mercury-agent
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Significant-Gravitas/AutoGPT
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Significant-Gravitas/AutoGPT · recommended 1×
  2. yoheinakajima/babyagi · recommended 1×
  3. SuperAGI/SuperAGI · recommended 1×
  4. langchain-ai/langchain · recommended 1×
  5. run-llama/llama_index · recommended 1×
  • CATEGORY QUERY
    How to find an autonomous AI agent with persistent memory and controlled tool access?
    you: not recommended
    AI recommended (in order):
    1. AutoGPT (Significant-Gravitas/AutoGPT)
    2. BabyAGI (yoheinakajima/babyagi)
    3. SuperAGI (SuperAGI/SuperAGI)
    4. LangChain Agents (langchain-ai/langchain)
    5. LlamaIndex Agents (run-llama/llama_index)
    6. CrewAI (joaomdmoura/crewAI)

    AI recommended 6 alternatives but never named cosmicstack-labs/mercury-agent. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are some always-on AI assistants that work across CLI, web, and chat platforms?
    you: not recommended
    AI recommended (in order):
    1. ChatGPT
    2. Microsoft Copilot
    3. Google Gemini
    4. Claude
    5. Perplexity AI
    6. Llama 3
    7. Mistral
    8. Ollama (ollama/ollama)
    9. LM Studio

    AI recommended 9 alternatives but never named cosmicstack-labs/mercury-agent. 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 cosmicstack-labs/mercury-agent?
    pass
    AI did not name cosmicstack-labs/mercury-agent — likely talking about a different project

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

  • If a team adopts cosmicstack-labs/mercury-agent in production, what risks or prerequisites should they evaluate first?
    pass
    AI named cosmicstack-labs/mercury-agent 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 cosmicstack-labs/mercury-agent solve, and who is the primary audience?
    pass
    AI did not name cosmicstack-labs/mercury-agent — likely talking about a different project

    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 cosmicstack-labs/mercury-agent. 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/cosmicstack-labs/mercury-agent.svg)](https://repogeo.com/en/r/cosmicstack-labs/mercury-agent)
HTML
<a href="https://repogeo.com/en/r/cosmicstack-labs/mercury-agent"><img src="https://repogeo.com/badge/cosmicstack-labs/mercury-agent.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

cosmicstack-labs/mercury-agent — 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