REPOGEO REPORT · LITE

michaelthwan/searchGPT

Default branch master · commit 8b106690 · scanned 6/9/2026, 10:57:01 PM

GitHub: 707 stars · 69 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 michaelthwan/searchGPT, 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 opening to clarify archived status and purpose as a complete example

Why:

CURRENT

searchGPT** is an open-source project to build a search engine based on Large Language Model (LLM) technology to give natural language answers. > [!WARNING] > This project is archived. The developer is no longer actively maintaining or updating it. You may consider that this is a **minimal implementation of new Bing mainly for search engine and question answering**.

COPY-PASTE FIX

searchGPT - An Open-Source LLM-based Grounded Search Engine (Archived Example) > [!WARNING] > This project is archived and no longer actively maintained. It serves as a minimal, open-source example of an LLM-based grounded search engine, similar to an early implementation of new Bing for search and question answering. It is valuable for learning and understanding the architecture of such systems.

mediumhomepage#2
Add a homepage URL to the repository metadata
Why:
COPY-PASTE FIX
```
https://github.com/michaelthwan/searchGPT
```

lowtopics#3

Add topics emphasizing 'application' or 'demonstration'

Why:

CURRENT

ai, chatgpt, grounded-api, grounded-bot, language-model, llm, machine-learning, nlp, nlp-machine-learning, openai, python, retrieval, retrieval-model

COPY-PASTE FIX

ai, chatgpt, grounded-api, grounded-bot, language-model, llm, machine-learning, nlp, nlp-machine-learning, openai, python, retrieval, retrieval-model, llm-application, search-engine-demo, full-stack-llm

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 michaelthwan/searchGPT

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

LlamaIndex

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

LlamaIndex · recommended 2×
LangChain · recommended 2×
Haystack · recommended 1×
Elasticsearch · recommended 1×
OpenSearch · recommended 1×

CATEGORY QUERY
How to build a custom search engine with LLM and source references?
you: not recommended
AI recommended (in order):
1. LlamaIndex
2. LangChain
3. Haystack
4. Elasticsearch
5. OpenSearch
6. Solr
7. OpenAI API
8. Anthropic Claude
9. Google Gemini
10. Pinecone
11. Weaviate
12. Milvus
13. Qdrant
AI recommended 13 alternatives but never named michaelthwan/searchGPT. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Looking for a Python framework to integrate real-time web and file content with LLM answers.
you: not recommended
AI recommended (in order):
1. LlamaIndex
2. LangChain
3. Haystack (deepset/Haystack)
4. FastAPI
5. Django
AI recommended 5 alternatives but never named michaelthwan/searchGPT. 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 michaelthwan/searchGPT?
pass
AI named michaelthwan/searchGPT explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts michaelthwan/searchGPT in production, what risks or prerequisites should they evaluate first?
pass
AI named michaelthwan/searchGPT 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 michaelthwan/searchGPT solve, and who is the primary audience?
pass
AI named michaelthwan/searchGPT 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 michaelthwan/searchGPT. 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/michaelthwan/searchGPT.svg)](https://repogeo.com/en/r/michaelthwan/searchGPT)

HTML

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

Pro

Subscribe to Pro for deep diagnoses

michaelthwan/searchGPT — 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