REPOGEO REPORT · LITE

THUDM/WebGLM

Default branch main · commit dd03d8fe · scanned 5/22/2026, 7:53:29 PM

GitHub: 1,603 stars · 134 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

35 /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

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 THUDM/WebGLM, 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

hightopics#1

Expand topics to include specific web interaction keywords

Why:

CURRENT

chatgpt, llm, rlhf, webglm

COPY-PASTE FIX

chatgpt, llm, rlhf, webglm, web-enhanced-qa, web-agent, web-interaction, html-dom, visual-language-model

highreadme#2

Clarify WebGLM's unique web interaction approach in the README intro

Why:

CURRENT

This is the official implementation of WebGLM. If you find our open-sourced efforts useful, please 🌟 the repo to encourage our following developement!

COPY-PASTE FIX

This is the official implementation of WebGLM, an efficient web-enhanced question answering system. Unlike generic RAG or LLM fine-tuning, WebGLM directly interacts with web pages using a structured action space based on HTML DOM trees, enabling deep understanding of visual and HTML information for zero-shot web agents. If you find our open-sourced efforts useful, please 🌟 the repo to encourage our following developement!

mediumhomepage#3
Add the paper link as the repository homepage
Why:
COPY-PASTE FIX
```
https://arxiv.org/pdf/2306.07906.pdf
```

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 THUDM/WebGLM

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

LlamaIndex

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

LlamaIndex · recommended 1×
LangChain · recommended 1×
Haystack · recommended 1×
RAGatouille · recommended 1×
OpenWebText · recommended 1×

CATEGORY QUERY
What open-source LLM solutions provide efficient web-augmented question answering capabilities?
you: not recommended
AI recommended (in order):
1. LlamaIndex
2. LangChain
3. Haystack
4. RAGatouille
5. OpenWebText
6. Hugging Face Transformers
7. FastRAG
AI recommended 7 alternatives but never named THUDM/WebGLM. This is the gap to close.
Show full AI answer
CATEGORY QUERY
How to build an LLM-powered QA system with human preference alignment for better results?
you: not recommended
AI recommended (in order):
1. Hugging Face Transformers (huggingface/transformers)
2. PEFT (huggingface/peft)
3. TRL (huggingface/trl)
4. Argilla (argilla-io/argilla)
5. OpenAI API
6. LangChain (langchain-ai/langchain)
7. HumanLoop
8. LlamaIndex (run-llama/llama_index)
9. Weights & Biases
10. Ax (facebook/Ax)
11. Ray Tune (ray-project/ray)
12. Anthropic API
13. Haystack (deepset-ai/haystack)
14. Label Studio (heartexlabs/label-studio)
15. MLflow (mlflow/mlflow)
16. PyTorch (pytorch/pytorch)
17. TensorFlow (tensorflow/tensorflow)
AI recommended 17 alternatives but never named THUDM/WebGLM. 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 THUDM/WebGLM?
pass
AI named THUDM/WebGLM explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts THUDM/WebGLM in production, what risks or prerequisites should they evaluate first?
pass
AI named THUDM/WebGLM 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 THUDM/WebGLM solve, and who is the primary audience?
pass
AI named THUDM/WebGLM 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 THUDM/WebGLM. 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/THUDM/WebGLM.svg)](https://repogeo.com/en/r/THUDM/WebGLM)

HTML

<a href="https://repogeo.com/en/r/THUDM/WebGLM"><img src="https://repogeo.com/badge/THUDM/WebGLM.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

THUDM/WebGLM — 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