RRepoGEO

REPOGEO REPORT · LITE

leo-lilinxiao/codex-autoresearch

Default branch main · commit 2b69caca · scanned 5/25/2026, 4:46:49 PM

GitHub: 1,781 stars · 107 forks

AI VISIBILITY SCORE
22 /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
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 leo-lilinxiao/codex-autoresearch, 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
  • highabout#1
    Update the repository's 'About' description

    Why:

    CURRENT
    Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
    COPY-PASTE FIX
    An autonomous AI agent for Codex that iteratively improves code through self-correction, verification, and experimentation. Inspired by Karpathy’s autoresearch, it automates software development tasks like fixing bugs, optimizing performance, and enhancing test coverage.
  • highreadme#2
    Strengthen README's opening statement

    Why:

    CURRENT
    <p align="center"><i>Autonomous goal-driven experimentation for Codex.</i></p>
    COPY-PASTE FIX
    <p align="center"><i>An autonomous AI agent for iterative code improvement and self-correction with Codex.</i></p>
  • mediumhomepage#3
    Add a homepage URL

    Why:

    COPY-PASTE FIX
    https://github.com/leo-lilinxiao/codex-autoresearch

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 leo-lilinxiao/codex-autoresearch
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Cursor
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Cursor · recommended 2×
  2. GitHub Copilot X · recommended 2×
  3. OpenAI API · recommended 2×
  4. LangChain · recommended 1×
  5. Smol-developer · recommended 1×
  • CATEGORY QUERY
    How to automate iterative code improvements and experimentation using an AI agent?
    you: not recommended
    AI recommended (in order):
    1. Cursor
    2. GitHub Copilot X
    3. OpenAI API
    4. LangChain
    5. Smol-developer
    6. Replit AI

    AI recommended 6 alternatives but never named leo-lilinxiao/codex-autoresearch. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a tool for autonomous code generation with built-in verification and self-correction.
    you: not recommended
    AI recommended (in order):
    1. Cursor
    2. GitHub Copilot X
    3. GPT-Engineer (gpt-engineer-org/gpt-engineer)
    4. Meta's Code Llama
    5. SWE-agent (princeton-nlp/SWE-agent)
    6. Pants Build System (pantsbuild/pants)
    7. OpenAI API

    AI recommended 7 alternatives but never named leo-lilinxiao/codex-autoresearch. 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 leo-lilinxiao/codex-autoresearch?
    pass
    AI did not name leo-lilinxiao/codex-autoresearch — 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 leo-lilinxiao/codex-autoresearch in production, what risks or prerequisites should they evaluate first?
    pass
    AI named leo-lilinxiao/codex-autoresearch 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 leo-lilinxiao/codex-autoresearch solve, and who is the primary audience?
    pass
    AI did not name leo-lilinxiao/codex-autoresearch — 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 leo-lilinxiao/codex-autoresearch. 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/leo-lilinxiao/codex-autoresearch.svg)](https://repogeo.com/en/r/leo-lilinxiao/codex-autoresearch)
HTML
<a href="https://repogeo.com/en/r/leo-lilinxiao/codex-autoresearch"><img src="https://repogeo.com/badge/leo-lilinxiao/codex-autoresearch.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

leo-lilinxiao/codex-autoresearch — 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