Skip to content

Latest commit

ย 

History

History
263 lines (182 loc) ยท 9.1 KB

File metadata and controls

263 lines (182 loc) ยท 9.1 KB

๐Ÿงฌ KnowMe

Your AI conversations reveal your personality.

KnowMe analyzes your ChatGPT / Claude / DeepSeek chat history to uncover your MBTI type, personality strengths & weaknesses, and actionable life advice.

Python 3.8+ License: MIT Stars Issues

English | ็ฎ€ไฝ“ไธญๆ–‡


KnowMe analysis output example

๐Ÿ’ก The Idea

Traditional MBTI tests ask what you think you'd do.

KnowMe analyzes what you actually do โ€” how you ask questions, how you make decisions, how you structure your thoughts, what topics consume your attention โ€” all extracted from your real conversations with AI.

No surveys. No self-reporting bias. Just your authentic behavior.

Think about it: you've had hundreds (maybe thousands) of conversations with ChatGPT. Those conversations contain your real thinking patterns and personality fingerprint. KnowMe extracts them.


๐Ÿ†š Why KnowMe?

Capability Traditional MBTI Tests AI Chat Assessments KnowMe
Based on real behavior (not self-report) โŒ โŒ โœ…
Supports ChatGPT / Claude / DeepSeek data โŒ โŒ โœ…
50+ behavioral signal detection โŒ โŒ โœ…
Bilingual signal detection (EN + CN) โŒ Partial โœ…
100% local โ€” data never leaves your device โŒ โŒ โœ…
Confidence scoring per dimension โŒ โŒ โœ…
Personalized advice for all 16 types โœ… Partial โœ…
Free & open source โŒ โŒ โœ…

The core difference: we don't ask you to pick answers. We let your behavior answer for you.


๐Ÿš€ Quick Start (30 seconds)

Option 1: Command Line (Recommended)

# Clone the repo
git clone https://github.com/AIPMAndy/KnowMe.git
cd KnowMe

# Analyze your ChatGPT data (export from Settings โ†’ Data Controls โ†’ Export Data)
python3 scripts/collect.py --source chatgpt --file ~/Downloads/conversations.json --output data.json
python3 scripts/analyze.py --input data.json --output report.md
python3 scripts/advise.py --report report.md --output advice.md

# Read your personality report!
cat report.md

Option 2: As an OpenClaw Skill

# Install the skill
openclaw skill install knowme

# Then just ask your AI assistant:
# "Analyze my personality from our conversations"
# "What's my MBTI type?"
# "Give me personality insights"

๐Ÿ“Š What You Get

1. MBTI Type with Confidence Scores

Your MBTI Type: INTJ (Architect)

E [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘] I  (28% / 72%) โ†’ I โฌ…๏ธ (high confidence)
S [โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] N  (15% / 85%) โ†’ N โฌ…๏ธ (high confidence)
T [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘] F  (78% / 22%) โ†’ T โฌ…๏ธ (high confidence)
J [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘] P  (68% / 32%) โ†’ J โฌ…๏ธ (medium confidence)

Each dimension includes:

  • ๐Ÿ“Š Percentage scores (not binary labels)
  • ๐ŸŽฏ Confidence level (high / medium / low)
  • ๐Ÿ“ Behavioral evidence (what you said that led to the score)

2. Communication Style Analysis

  • Message length patterns (are you concise or thorough?)
  • Question / exclamation rates
  • Emoji usage frequency
  • Topic distribution (tech vs business vs relationships vs self-growth)
  • Collaborative vs independent tendencies

3. Personalized Life Advice

  • ๐Ÿ’ช Your Superpowers โ€” Top 3 strengths
  • ๐ŸŒฑ Growth Edges โ€” 3 areas most worth developing
  • ๐ŸŽฏ Career Lens โ€” What roles and work styles fit you
  • ๐Ÿ’ฌ Communication Blind Spots โ€” Issues you might not notice
  • โค๏ธ Relationship Insights โ€” Your social patterns
  • โšก 30-Day Challenge โ€” One specific growth experiment

๐Ÿ“ฆ Supported Data Sources

Source Command How to Export
ChatGPT --source chatgpt --file conversations.json Settings โ†’ Data Controls โ†’ Export Data
Claude --source claude --file claude_export.json Settings โ†’ Account โ†’ Export Data
OpenClaw --source openclaw Auto-reads from workspace memory files
Any Text --source text --file ./chats/ Any .md/.txt files with User:/Assistant: markers

๐Ÿ’ก Tip: More data = better analysis. We recommend 50+ messages. Merging data from multiple platforms gives the best results.


๐Ÿ”ฌ How It Works

KnowMe does not call any AI API for analysis (that would be slow, expensive, and inconsistent).

Instead, it uses a signal-based scoring system:

Your chat history โ†’ 50+ behavioral signal scan โ†’ 8-dimension weighted scoring โ†’ MBTI + personality profile

Signal Examples

What you said Detected signal Dimension affected
"Let me think about that..." Needs solo processing time I +3
"Let's brainstorm together" Collaborative tendency E +2
"How exactly do I do this step by step?" Practical orientation S +2
"What if we look at it from another angle..." Abstract thinking N +2
"The data shows..." Data-driven reasoning T +2
"How would this make the team feel?" People-centered concern F +2
"What's the next action item?" Closure-driven J +2
"It depends, let's stay flexible" Open adaptability P +2

Why this approach?

  • โšก Fast โ€” Analyzes 1000+ messages in seconds
  • ๐Ÿ”’ Private โ€” Zero API calls, data never leaves your device
  • ๐Ÿ“Š Explainable โ€” Every score has traceable behavioral evidence
  • ๐Ÿ”„ Reproducible โ€” Same input always gives the same output

๐Ÿ› ๏ธ Advanced Usage

Merge multiple data sources

# Collect from multiple sources
python3 scripts/collect.py --source chatgpt --file chatgpt.json --output /tmp/gpt.json
python3 scripts/collect.py --source claude --file claude.json --output /tmp/claude.json

# Merge with jq
jq -s '{messages: (.[0].messages + .[1].messages), source: "merged", total_messages: (.[0].total_messages + .[1].total_messages)}' \
  /tmp/gpt.json /tmp/claude.json > /tmp/merged.json

# Analyze merged data
python3 scripts/analyze.py --input /tmp/merged.json --output report.md

Export raw scores

python3 scripts/analyze.py --input data.json --output report.md --json raw_scores.json

๐Ÿ—๏ธ Architecture

knowme/
โ”œโ”€โ”€ README.md                         # ไธญๆ–‡ๆ–‡ๆกฃ
โ”œโ”€โ”€ README_EN.md                      # English docs
โ”œโ”€โ”€ scripts/
โ”‚   โ”œโ”€โ”€ collect.py                    # Multi-source data collector
โ”‚   โ”œโ”€โ”€ analyze.py                    # Signal-based personality analyzer
โ”‚   โ””โ”€โ”€ advise.py                     # 16-type personalized advice engine
โ”œโ”€โ”€ references/
โ”‚   โ”œโ”€โ”€ mbti_signals.md               # Signal taxonomy (50+ signals)
โ”‚   โ””โ”€โ”€ advice_frameworks.md          # Advice generation frameworks
โ”œโ”€โ”€ assets/                           # Demo images and media
โ”œโ”€โ”€ SKILL.md                          # OpenClaw Skill definition
โ”œโ”€โ”€ CONTRIBUTING.md                   # Contributing guide
โ””โ”€โ”€ LICENSE                           # Apache 2.0 License

๐Ÿ—บ๏ธ Roadmap

  • Core MBTI 4-dimension analysis
  • ChatGPT / Claude / OpenClaw data sources
  • Personalized advice for all 16 types
  • Bilingual signal detection (EN + CN)
  • OpenClaw Skill integration
  • ๐Ÿ”œ Web UI (upload file โ†’ see report in browser)
  • ๐Ÿ”œ Gemini / Copilot / DeepSeek data sources
  • ๐Ÿ”œ Big Five personality analysis module
  • ๐Ÿ”œ Timeline analysis (how has your personality shifted?)
  • ๐Ÿ”œ Anonymous benchmarking (how do you compare to 100K people?)
  • ๐Ÿ”œ AI style analysis (how do different AIs change your expression?)

๐Ÿค Contributing

PRs welcome! Especially for:

  • ๐Ÿ”Œ New data source parsers (Gemini, Copilot, DeepSeek, etc.)
  • ๐Ÿ” New behavioral signal patterns
  • ๐ŸŒ Signal detection for more languages
  • ๐Ÿ“Š Visualization and Web UI
  • ๐Ÿงช Big Five / Enneagram and other personality frameworks

See CONTRIBUTING.md for details.


โš ๏ธ Disclaimer

KnowMe is a self-discovery tool, not a clinical assessment. MBTI is a preference model โ€” use these results as conversation starters for self-reflection, not as fixed labels. Analysis quality improves with more conversation data (50+ messages recommended).


๐Ÿ“„ License

Apache 2.0 โ€” Use it, fork it, improve it, share it.


If KnowMe helped you understand yourself better, give it a โญ Star!

Built with โค๏ธ by AI้…‹้•ฟAndy

You've had thousands of conversations with AI. It's time those conversations worked for you.