RRepoGEO

REPOGEO REPORT · LITE

google-deepmind/funsearch

Default branch main · commit cc53f274 · scanned 5/25/2026, 4:32:49 AM

GitHub: 1,066 stars · 178 forks

AI VISIBILITY SCORE
30 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 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 google-deepmind/funsearch, 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
    Add a concise project description

    Why:

    COPY-PASTE FIX
    FunSearch is a system that leverages large language models within an evolutionary search framework to discover novel and more efficient algorithms for challenging mathematical and computer science problems.
  • hightopics#2
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    large-language-models, llm, algorithm-discovery, combinatorial-optimization, evolutionary-algorithms, program-synthesis, deepmind, research
  • mediumreadme#3
    Reposition the README's opening to clearly state the project's purpose and method

    Why:

    CURRENT
    # FunSearch

This repository accompanies the publication

> Romera-Paredes, B. et al. Mathematical discoveries from program search with large language models. *Nature* (2023)
    COPY-PASTE FIX
    # FunSearch

FunSearch is a novel system that combines large language models (LLMs) with an evolutionary search framework to discover new and more efficient algorithms for complex mathematical and computer science problems. This repository provides the implementation and examples accompanying the publication:

> Romera-Paredes, B. et al. Mathematical discoveries from program search with large language models. *Nature* (2023)

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 google-deepmind/funsearch
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
DeepMind's AlphaZero/AlphaDev
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. DeepMind's AlphaZero/AlphaDev · recommended 1×
  2. pyg-team/pytorch_geometric · recommended 1×
  3. dglai/dgl · recommended 1×
  4. ray-project/ray · recommended 1×
  5. DLR-RM/stable-baselines3 · recommended 1×
  • CATEGORY QUERY
    How can AI help discover novel algorithms for combinatorial optimization problems?
    you: not recommended
    AI recommended (in order):
    1. DeepMind's AlphaZero/AlphaDev
    2. PyTorch Geometric (PyG) (pyg-team/pytorch_geometric)
    3. Deep Graph Library (DGL) (dglai/dgl)
    4. RLlib (ray-project/ray)
    5. Stable Baselines3 (DLR-RM/stable-baselines3)
    6. Auto-WEKA
    7. Auto-Sklearn (automl/auto-sklearn)
    8. SMAC (Sequential Model-based Algorithm Configuration) (automl/SMAC3)
    9. Hyperopt (hyperopt/hyperopt)
    10. DEAP (Distributed Evolutionary Algorithms in Python) (deap/deap)
    11. GP-GOMEA (Genetic Programming - Gene-pool Optimal Mixing Evolutionary Algorithm)
    12. TensorFlow (tensorflow/tensorflow)
    13. PyTorch (pytorch/pytorch)
    14. DeepCoder
    15. AlphaCode

    AI recommended 15 alternatives but never named google-deepmind/funsearch. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the best tools for generating code and heuristics using large language models?
    you: not recommended
    AI recommended (in order):
    1. OpenAI API
    2. Anthropic Claude
    3. Google Gemini API
    4. GitHub Copilot
    5. Hugging Face Transformers Library
    6. Replicate
    7. Tabnine

    AI recommended 7 alternatives but never named google-deepmind/funsearch. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    fail

    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 google-deepmind/funsearch?
    pass
    AI named google-deepmind/funsearch explicitly

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

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

Subscribe to Pro for deep diagnoses

google-deepmind/funsearch — 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