REPOGEO REPORT · LITE

ErlichLiu/DeepClaude

Default branch main · commit b6e40164 · scanned 6/25/2026, 2:23:14 AM

GitHub: 2,928 stars · 503 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)

3 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 ErlichLiu/DeepClaude, 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

Add a concise English value proposition to the README's opening

Why:

CURRENT

The README starts with a Chinese section after the H1.

COPY-PASTE FIX

DeepClaude is an OpenAI-compatible API gateway that combines the power of multiple leading AI models for specialized tasks. Unleash next-level AI for unparalleled code generation (DeepSeek r1 + Claude 3.7 Sonnet) and superior content creation (DeepSeek r1 + Gemini 2.5 Pro). It offers streaming and non-streaming support, making it a versatile solution for developers.

mediumtopics#2

Expand repository topics to include functional and compatibility keywords

Why:

CURRENT

ai, claude-3-7-sonnet, deepseek, gemini

COPY-PASTE FIX

ai, claude-3-7-sonnet, deepseek, gemini, openai-compatible, llm-gateway, model-proxy, code-generation, content-creation, multi-model

lowreadme#3

Add a dedicated "Key Features" section in English to the README

Why:

COPY-PASTE FIX

## Key Features

*   **OpenAI-Compatible API:** Seamlessly integrate with existing OpenAI API tools and workflows.
*   **Optimized Model Combinations:**
    *   **Code Generation:** Leverage DeepSeek r1 + Claude 3.7 Sonnet for unparalleled performance.
    *   **Content Creation:** Utilize DeepSeek r1 + Gemini 2.5 Pro for superior quality.
*   **Flexible API Support:** Supports both streaming and non-streaming requests.
*   **Easy Deployment:** Features a user-friendly configuration interface for simplified setup.

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 ErlichLiu/DeepClaude

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

LiteLLM

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

LiteLLM · recommended 1×
OpenRouter · recommended 1×
LangChain · recommended 1×
LlamaIndex · recommended 1×
MindsDB · recommended 1×

CATEGORY QUERY
Need an OpenAI-compatible solution to integrate multiple powerful AI models for diverse applications.
you: not recommended
AI recommended (in order):
1. LiteLLM
2. OpenRouter
3. LangChain
4. LlamaIndex
5. MindsDB
6. LocalAI
AI recommended 6 alternatives but never named ErlichLiu/DeepClaude. This is the gap to close.
Show full AI answer
CATEGORY QUERY
How can I achieve superior code generation and content creation using combined AI models?
you: not recommended
AI recommended (in order):
1. OpenAI GPT-4
2. GitHub Copilot
3. DeepMind AlphaCode 2
4. Code Llama
5. StarCoder
6. Anthropic Claude 3 Opus
7. Google Gemini Advanced
8. Hugging Face Transformers
9. T5
10. BART
11. Llama 2
12. Mistral Large
13. Mixtral 8x7B
14. Cursor AI
15. Google Codey APIs
16. Perplexity AI
17. Writer
18. Tabnine
AI recommended 18 alternatives but never named ErlichLiu/DeepClaude. 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 ErlichLiu/DeepClaude?
pass
AI named ErlichLiu/DeepClaude explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts ErlichLiu/DeepClaude in production, what risks or prerequisites should they evaluate first?
pass
AI named ErlichLiu/DeepClaude 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 ErlichLiu/DeepClaude solve, and who is the primary audience?
pass
AI named ErlichLiu/DeepClaude 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 ErlichLiu/DeepClaude. 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/ErlichLiu/DeepClaude.svg)](https://repogeo.com/en/r/ErlichLiu/DeepClaude)

HTML

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

Pro

Subscribe to Pro for deep diagnoses

ErlichLiu/DeepClaude — 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