RRepoGEO

REPOGEO REPORT · LITE

ErlichLiu/Proma

Default branch main · commit c0467dfe · scanned 6/27/2026, 5:52:10 AM

GitHub: 1,394 stars · 186 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/Proma, 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
  • highabout#1
    Reposition the 'About' description to emphasize 'desktop application' and 'agent workbench'

    Why:

    CURRENT
    把最丝滑的通用 Agent 体验带进你的工作流，为 100x 专业用户而生的未来产品，正在实现 proactive Agent 阶段。基于 Claude Agent SDK 的完整开源实践，原生支持飞书群聊调用、灵活接入任意大模型供应商 —— 让顶级 Agent 能力真正跑在你每天用的地方。
    COPY-PASTE FIX
    Proma 是一个本地优先的 AI 桌面应用，为专业用户提供多模型聊天和通用 Agent 工作台。它基于 Claude Agent SDK，支持飞书群聊和灵活的大模型接入，将顶级 Agent 能力无缝集成到你的日常工作流中。
  • hightopics#2
    Add specific topics for desktop applications and agent workbenches

    Why:

    CURRENT
    agent, agent-sdk, agents, chatbot, chatgpt, claude, gemini, llm
    COPY-PASTE FIX
    agent, agent-sdk, agents, chatbot, chatgpt, claude, gemini, llm, desktop-app, ai-assistant, workflow-automation, local-llm, multi-model, feishu-bot, agent-workbench
  • mediumreadme#3
    Add a clear differentiator against common agent frameworks and local LLM servers

    Why:

    COPY-PASTE FIX
    在 README 的 '现在能做什么' 或 '快速开始' 部分之前，添加如下内容：

与 [Open Interpreter](https://github.com/KillianLucas/open-interpreter) 或 [AutoGPT](https://github.com/Significant-Gravitas/AutoGPT) 等命令行 Agent 框架不同，Proma 是一个开箱即用的桌面应用，专注于提供集成式的多模型聊天和 Agent 工作流管理，而非仅仅是 Agent 库或本地 LLM 服务器。

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/Proma
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
KillianLucas/open-interpreter
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. KillianLucas/open-interpreter · recommended 1×
  2. Significant-Gravitas/AutoGPT · recommended 1×
  3. yoheinakajima/babyagi · recommended 1×
  4. reworkd/AgentGPT · recommended 1×
  5. TransformerOptimus/SuperAGI · recommended 1×
  • CATEGORY QUERY
    How to integrate advanced AI agents into my local desktop workflow for complex tasks?
    you: not recommended
    AI recommended (in order):
    1. Open Interpreter (KillianLucas/open-interpreter)
    2. AutoGPT (Significant-Gravitas/AutoGPT)
    3. BabyAGI (yoheinakajima/babyagi)
    4. AgentGPT (reworkd/AgentGPT)
    5. SuperAGI (TransformerOptimus/SuperAGI)
    6. LangChain (langchain-ai/langchain)
    7. Llama.cpp (ggerganov/llama.cpp)
    8. Ollama (ollama/ollama)
    9. OpenAI API
    10. pandas (pandas-dev/pandas)
    11. selenium (SeleniumHQ/selenium)
    12. Taskade
    13. Notion AI
    14. Cursor

    AI recommended 14 alternatives but never named ErlichLiu/Proma. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What open-source desktop clients offer multi-model AI chat and remote bot integration for teams?
    you: not recommended
    AI recommended (in order):
    1. Jan
    2. LM Studio
    3. Ollama
    4. LocalAI
    5. AnythingLLM

    AI recommended 5 alternatives but never named ErlichLiu/Proma. 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/Proma?
    pass
    AI named ErlichLiu/Proma 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/Proma in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ErlichLiu/Proma 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/Proma solve, and who is the primary audience?
    pass
    AI named ErlichLiu/Proma 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/Proma. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/ErlichLiu/Proma.svg)](https://repogeo.com/en/r/ErlichLiu/Proma)
HTML
<a href="https://repogeo.com/en/r/ErlichLiu/Proma"><img src="https://repogeo.com/badge/ErlichLiu/Proma.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ErlichLiu/Proma — 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