REPOGEO REPORT · LITE

AgentTeam-TaichuAI/ScienceClaw

Default branch master · commit 3817e56a · scanned 6/5/2026, 11:37:47 AM

GitHub: 519 stars · 62 forks

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 AgentTeam-TaichuAI/ScienceClaw, 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 emphasize 'self-hosted platform' and 'multi-agent system'

Why:

CURRENT

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

COPY-PASTE FIX

ScienceClaw is a **self-hosted, multi-agent AI platform** designed as a personal research assistant. Built with LangChain DeepAgents and AIO Sandbox infrastructure, it offers a completely new architecture beyond OpenClaw, ensuring stronger security, better transparency, and a more user-friendly experience for scientific workflows.

highlicense#2

Add a LICENSE file and declare the license in README

Why:

COPY-PASTE FIX

Create a `LICENSE` file in the repository root with the chosen license text (e.g., Apache-2.0, MIT). Add a section to the README, perhaps under 'Project Structure' or 'Acknowledgements', stating: `ScienceClaw is licensed under the [Your Chosen License Name] License. See the [LICENSE](LICENSE) file for details.`

mediumreadme#3

Add a 'Comparison with Alternatives' section to the README

Why:

COPY-PASTE FIX

Add a new section to the README, for example, `## 🆚 ScienceClaw vs. Alternatives`, that explicitly compares ScienceClaw to common alternatives like Elicit, Scite.ai, or BioBERT. Highlight ScienceClaw's unique strengths such as being **fully self-hosted**, a **multi-agent system**, offering **comprehensive workflow automation**, and **strong security via sandboxing**, contrasting these with SaaS models or single-purpose libraries.

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 AgentTeam-TaichuAI/ScienceClaw

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Elicit

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Elicit · recommended 1×
Scite.ai · recommended 1×
Semantic Scholar · recommended 1×
ChatGPT · recommended 1×
Humata AI · recommended 1×

CATEGORY QUERY
How can I automate scientific literature review and data analysis using AI agents?
you: not recommended
AI recommended (in order):
1. Elicit
2. Scite.ai
3. Semantic Scholar
4. ChatGPT
5. Humata AI
6. Connected Papers
7. Zotero
AI recommended 7 alternatives but never named AgentTeam-TaichuAI/ScienceClaw. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Looking for a self-hosted AI research assistant for bioinformatics and drug discovery.
you: not recommended
AI recommended (in order):
1. ChemDataExtractor
2. BioBERT
3. SciBERT
4. Hugging Face Transformers
5. OpenNMT
6. MarianMT
7. DeepChem
8. KNIME Analytics Platform
AI recommended 8 alternatives but never named AgentTeam-TaichuAI/ScienceClaw. 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 AgentTeam-TaichuAI/ScienceClaw?
pass
AI named AgentTeam-TaichuAI/ScienceClaw explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts AgentTeam-TaichuAI/ScienceClaw in production, what risks or prerequisites should they evaluate first?
pass
AI named AgentTeam-TaichuAI/ScienceClaw 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 AgentTeam-TaichuAI/ScienceClaw solve, and who is the primary audience?
pass
AI named AgentTeam-TaichuAI/ScienceClaw 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 AgentTeam-TaichuAI/ScienceClaw. 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/AgentTeam-TaichuAI/ScienceClaw.svg)](https://repogeo.com/en/r/AgentTeam-TaichuAI/ScienceClaw)

HTML

<a href="https://repogeo.com/en/r/AgentTeam-TaichuAI/ScienceClaw"><img src="https://repogeo.com/badge/AgentTeam-TaichuAI/ScienceClaw.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

AgentTeam-TaichuAI/ScienceClaw — 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