RRepoGEO

REPOGEO REPORT · LITE

uditgoenka/autoresearch

Default branch master · commit 98398ba5 · scanned 5/18/2026, 5:03:20 PM

GitHub: 4,515 stars · 345 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 uditgoenka/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
  • highreadme#1
    Reposition the README H1 and opening paragraph to emphasize "autonomous agent" and "code research."

    Why:

    CURRENT
    # Autoresearch

**Turn Claude Code, OpenCode, or OpenAI Codex into a relentless improvement engine.**

Based on Karpathy's autoresearch — constraint + mechanical metric + autonomous iteration = compounding gains.
    COPY-PASTE FIX
    # Autoresearch: An Autonomous Agent for Iterative Code Research

**Turn Claude Code, OpenCode, or OpenAI Codex into a relentless, goal-directed improvement engine.** This project implements an autonomous agent inspired by Karpathy's autoresearch, focusing on continuous modification, verification, and refinement of code.
  • mediumabout#2
    Update the "About" description to explicitly state it's an autonomous agent for code research.

    Why:

    CURRENT
    Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
    COPY-PASTE FIX
    An autonomous agent for goal-directed code research and iterative improvement, inspired by Karpathy's autoresearch. It continuously modifies, verifies, and refines code using Claude, OpenCode, or OpenAI Codex.
  • lowtopics#3
    Add more specific topics related to LLM agents and code generation.

    Why:

    CURRENT
    ai, autonomous-agent, autoresearch, claude, claude-code, iteration, karpathy, productivity, skill
    COPY-PASTE FIX
    ai, autonomous-agent, autoresearch, claude, claude-code, iteration, karpathy, productivity, skill, llm-agent, code-generation, code-improvement

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 uditgoenka/autoresearch
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
GitHub Actions
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. GitHub Actions · recommended 2×
  2. GitLab CI/CD · recommended 1×
  3. Azure Pipelines · recommended 1×
  4. jenkinsci/jenkins · recommended 1×
  5. SonarSource/sonarqube · recommended 1×
  • CATEGORY QUERY
    What tools automate the iterative refinement of code for continuous improvement?
    you: not recommended
    AI recommended (in order):
    1. GitHub Actions
    2. GitLab CI/CD
    3. Azure Pipelines
    4. Jenkins (jenkinsci/jenkins)
    5. SonarQube (SonarSource/sonarqube)
    6. DeepSource (deepsourcelabs/deepsource-cli)
    7. CodeClimate (codeclimate/codeclimate)
    8. Codacy
    9. Renovate (renovatebot/renovate)
    10. Dependabot (dependabot/dependabot-core)
    11. Pre-commit (pre-commit/pre-commit)
    12. Snyk (snyk/snyk)
    13. Black Duck
    14. WhiteSource
    15. Jira
    16. Asana
    17. Trello

    AI recommended 17 alternatives but never named uditgoenka/autoresearch. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I deploy an autonomous agent to continuously improve my codebase towards specific metrics?
    you: not recommended
    AI recommended (in order):
    1. GitHub Copilot for Business
    2. GitHub Actions
    3. Prometheus client
    4. Datadog API
    5. JaCoCo
    6. JMeter
    7. SonarQube
    8. Snyk
    9. ast (Python)
    10. OpenAI API (GPT-4/GPT-3.5)
    11. LangChain
    12. LlamaIndex
    13. CodiumAI
    14. SonarQube/SonarCloud
    15. DeepCode AI
    16. Snyk Code

    AI recommended 16 alternatives but never named uditgoenka/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
    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 uditgoenka/autoresearch?
    pass
    AI named uditgoenka/autoresearch explicitly

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

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

Subscribe to Pro for deep diagnoses

uditgoenka/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