REPOGEO REPORT · LITE

proma-ai/Proma

Default branch main · commit 39530b4f · scanned 6/1/2026, 2:57:06 PM

GitHub: 1,186 stars · 163 forks

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 proma-ai/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

highreadme#1

Reposition the README's opening paragraph to highlight desktop/local-first personal AI agent capabilities

Why:

CURRENT

# Proma

Proma 是一个本地优先的 AI 桌面应用，把多模型 Chat、通用 Agent、工作区、Skills、MCP、远程机器人和记忆能力放在同一个开源客户端里。

它不是只面向闲聊的聊天框，而是一个可以长期沉淀个人工作流的 Agent 工作台：简单问题用 Chat，复杂任务交给 Agent，数据和配置尽量留在本地。

COPY-PASTE FIX

# Proma

Proma 是一个本地优先的 AI 桌面应用，专为 100x 专业用户设计，将多模型 Chat、通用 Agent、工作区、Skills、MCP、远程机器人和记忆能力整合在一个开源客户端中，旨在成为您管理复杂个人工作流的终极 AI Agent 工作台。它不是一个简单的聊天框，而是让顶级 Agent 能力真正跑在你每天用的地方，实现 proactive Agent 阶段。

mediumtopics#2

Add more specific topics to improve categorization for desktop and personal workflow tools

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, personal-ai-agent, workflow-automation, local-first, productivity-tool

lowreadme#3

Add a brief 'Why Proma?' or 'Comparison' section to the README

Why:

COPY-PASTE FIX

## 为什么选择 Proma？

Proma 区别于其他通用 AI Agent 框架（如 SuperAGI, AutoGPT）或纯粹的聊天机器人，它是一个本地优先的桌面应用，专注于为个人用户提供一个集成的 Agent 工作台。我们强调数据本地存储、桌面级体验和对复杂个人工作流的深度支持，而非仅仅提供一个开发框架或云端服务。

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 proma-ai/Proma

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

SuperAGI

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

SuperAGI · recommended 1×
AutoGPT · recommended 1×
AgentGPT · recommended 1×
Open Interpreter · recommended 1×
LangChain · recommended 1×

CATEGORY QUERY
What are good desktop AI agent tools for managing complex personal workflows locally?
you: not recommended
AI recommended (in order):
1. SuperAGI
2. AutoGPT
3. AgentGPT
4. Open Interpreter
5. LangChain
6. Ollama
AI recommended 6 alternatives but never named proma-ai/Proma. This is the gap to close.
Show full AI answer
CATEGORY QUERY
How can I integrate powerful AI agents with group chat platforms for daily tasks?
you: not recommended
AI recommended (in order):
1. Slack
2. Zapier
3. Make
4. OpenAI's GPT-4
5. Google Cloud AI Platform
6. Microsoft Azure AI Services
7. slack_sdk (slackapi/python-slack-sdk)
8. LangChain (langchain-ai/langchain)
9. LlamaIndex (run-llama/llama_index)
10. Anthropic's Claude
11. Cohere
12. Hugging Face models
13. Microsoft Teams
14. Microsoft Power Automate
15. Azure OpenAI Service
16. Azure Cognitive Services
17. Microsoft Bot Framework (microsoft/botframework-sdk)
18. Azure Bot Service
19. Discord
20. discord.py (Rapptz/discord.py)
21. Hugging Face Transformers (huggingface/transformers)
22. Midjourney
23. DALL-E 3
24. Google Chat
25. Google Apps Script
26. Vertex AI
27. Generative AI on Vertex AI
28. Gemini
29. Google Cloud Functions
30. Telegram
31. Telegram Bot API
32. python-telegram-bot (python-telegram-bot/python-telegram-bot)
33. Mattermost (mattermost/mattermost-server)
34. Hugging Face Inference API
AI recommended 34 alternatives but never named proma-ai/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 proma-ai/Proma?
pass
AI named proma-ai/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 proma-ai/Proma in production, what risks or prerequisites should they evaluate first?
pass
AI named proma-ai/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 proma-ai/Proma solve, and who is the primary audience?
pass
AI named proma-ai/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 proma-ai/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.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/proma-ai/Proma.svg)](https://repogeo.com/en/r/proma-ai/Proma)

HTML

<a href="https://repogeo.com/en/r/proma-ai/Proma"><img src="https://repogeo.com/badge/proma-ai/Proma.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

proma-ai/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