REPOGEO REPORT · LITE

princeton-nlp/WebShop

Default branch master · commit 64fa2a5c · scanned 6/2/2026, 2:23:19 AM

GitHub: 545 stars · 99 forks

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 princeton-nlp/WebShop, 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 README H1 to clearly state project type
Why:
CURRENT
```
# 🛒 WebShop
```
COPY-PASTE FIX
```
# 🛒 WebShop: A Realistic Web-Based Simulation Environment for Grounded Language Agents
```

mediumtopics#2

Add more specific topics to refine categorization

Why:

CURRENT

decision-making, language, language-grounding, ml, nlp, rl, rl-environment, shopping, sim-to-real, web-based

COPY-PASTE FIX

decision-making, language, language-grounding, ml, nlp, rl, rl-environment, shopping, sim-to-real, web-based, language-agents, e-commerce-environment, web-interaction, llm-evaluation, agent-training

lowreadme#3

Clarify the initial README paragraph's description of the environment

Why:

CURRENT

Implementation of the WebShop environment and search agents for the paper:

**WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents**  
Shunyu Yao*, Howard Chen*, John Yang, Karthik Narasimhan

COPY-PASTE FIX

This repository provides the WebShop environment, a simulated e-commerce website designed for training and evaluating grounded language agents on complex, real-world web interaction tasks. It includes code for reproducing results from the paper:

**WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents**  
Shunyu Yao*, Howard Chen*, John Yang, Karthik Narasimhan

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 princeton-nlp/WebShop

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

google-research/recsim

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

google-research/recsim · recommended 1×
openai/gym · recommended 1×
Microsoft's Personalizer (Azure Cognitive Services) · recommended 1×
RUCAIBox/RecBole · recommended 1×
lyst/lightfm · recommended 1×

CATEGORY QUERY
What are good reinforcement learning environments for training agents on e-commerce websites?
you: not recommended
AI recommended (in order):
1. RecSim by Google Research (google-research/recsim)
2. OpenAI Gym (openai/gym)
3. Microsoft's Personalizer (Azure Cognitive Services)
4. RecBole (RUCAIBox/RecBole)
5. LightFM (lyst/lightfm)
6. Selenium (SeleniumHQ/selenium)
7. Playwright (microsoft/playwright)
AI recommended 7 alternatives but never named princeton-nlp/WebShop. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Need a realistic web-based simulation for training grounded language agents to interact with shopping sites.
you: not recommended
AI recommended (in order):
1. MiniWoB++
2. Playwright
3. Selenium
4. WebArena
5. Puppeteer
AI recommended 5 alternatives but never named princeton-nlp/WebShop. 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 princeton-nlp/WebShop?
pass
AI named princeton-nlp/WebShop explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts princeton-nlp/WebShop in production, what risks or prerequisites should they evaluate first?
pass
AI named princeton-nlp/WebShop 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 princeton-nlp/WebShop solve, and who is the primary audience?
pass
AI named princeton-nlp/WebShop 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 princeton-nlp/WebShop. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/princeton-nlp/WebShop.svg)](https://repogeo.com/en/r/princeton-nlp/WebShop)

HTML

<a href="https://repogeo.com/en/r/princeton-nlp/WebShop"><img src="https://repogeo.com/badge/princeton-nlp/WebShop.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

princeton-nlp/WebShop — 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