REPOGEO REPORT · LITE
OpenBMB/AgentCPM-GUI
Default branch main · commit 2168ae21 · scanned 5/21/2026, 2:02:51 AM
GitHub: 1,365 stars · 130 forks
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.
2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).
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 OpenBMB/AgentCPM-GUI, 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.
- hightopics#1Add relevant topics to the repository
Why:
COPY-PASTE FIXandroid-automation, llm-agent, gui-automation, on-device-ai, reinforcement-learning, mobile-ai, multimodal-llm, minicpm-v, chinese-apps
- highreadme#2Add a concise, direct positioning statement at the very top of the README
Why:
CURRENTThe README currently starts with a <div> and then a navigation bar, with the main description under 'Overview'.
COPY-PASTE FIXAdd this line right after the initial <div> (or as the first line of text): "AgentCPM-GUI is an open-source, on-device LLM agent for Android app control via screenshots, uniquely enhanced with RFT for reasoning and optimized for bilingual (Chinese & English) app operation."
- mediumhomepage#3Add a homepage URL to the repository metadata
Why:
COPY-PASTE FIXhttps://huggingface.co/openbmb/AgentCPM-GUI
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.
- Appium · recommended 2×
- Python · recommended 1×
- OpenCV · recommended 1×
- TensorFlow Lite · recommended 1×
- TensorFlow · recommended 1×
- CATEGORY QUERYHow can I automate Android app interactions using an on-device AI agent?you: not recommendedAI recommended (in order):
- Appium
- Python
- OpenCV
- TensorFlow Lite
- TensorFlow
- PyTorch
- UI Automator
- Java
- Kotlin
- Frida
- MacroDroid
- Tasker
- Robot Framework
- Appium Library
AI recommended 14 alternatives but never named OpenBMB/AgentCPM-GUI. This is the gap to close.
Show full AI answer
- CATEGORY QUERYWhat are the best open-source LLM agents for controlling Android apps via screenshots?you: not recommendedAI recommended (in order):
- AppAgent
- AndroidEnv (DeepMind)
- LLaMA
- Mistral
- SeeClick (Google Research)
- YOLO
- DETR
- uiautomator2
- Appium
- UI-LLM (Microsoft Research)
- Mini-GPT4
- LLaVA
- BLIP-2
- InstructBLIP
AI recommended 14 alternatives but never named OpenBMB/AgentCPM-GUI. This is the gap to close.
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesswarn
Suggestion:
- README presencepass
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 OpenBMB/AgentCPM-GUI?passAI did not name OpenBMB/AgentCPM-GUI — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- If a team adopts OpenBMB/AgentCPM-GUI in production, what risks or prerequisites should they evaluate first?passAI named OpenBMB/AgentCPM-GUI 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 OpenBMB/AgentCPM-GUI solve, and who is the primary audience?passAI named OpenBMB/AgentCPM-GUI 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 OpenBMB/AgentCPM-GUI. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
[](https://repogeo.com/en/r/OpenBMB/AgentCPM-GUI)<a href="https://repogeo.com/en/r/OpenBMB/AgentCPM-GUI"><img src="https://repogeo.com/badge/OpenBMB/AgentCPM-GUI.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
OpenBMB/AgentCPM-GUI — 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