You pick history files. Your browser reads and analyses them.
Conversations, results and exports never leave the device.
No account, no analytics, no AI models: the score comes from fixed rules.
Data stays in this browser until you clear it. Export an archive to keep a copy.
Optional · needs sign-in
Connected
Sign in and combine histories from several devices.
Only after you agree to upload, and only the files you pick. Our server can read uploaded data to process it.
Optional public profile and optional model-based analysis, each with its own consent.
Opening this website downloads the app, and the host may keep ordinary access logs (for example your IP address). The on-device promise covers your conversations and results: those are never sent.
A sample report
Invented numbers so you can see the format. Pick a score to see how the signed scale reads, from −100 to +100, with 0 in the middle.
Demo · sample data, not yours
Demo AI Karma
AI Karma +67 on a scale from −100 to +100
+67
The Ray of Sunshine
Thanks and praise everywhere. Your assistant would probably write you a thank-you note.
57% nice · 41% neutral · 2% mean
Average tone per message: +0.20 (from −1 to +1)
-1000+100
A playful score based on the words you used. It covers only the files you imported, and it isn’t a verdict on you.
What moved the needle
Your signature moves
106messages said thanks, out of 371
105requests came with a please
18corrections (fair game, not counted against you)
2messages aimed an insult at the assistant
Kind vs. harsh
Where your words landed
211 kind messages and 7 harsh messages out of 371 readable messages.
Warm praise or apology53
Thanks or positive feedback95
Polite request63
Passive-aggressive3
Rude or dismissive2
Hostile1
Insult1
Each message gets a small score: a please adds a little, thanks and praise add more; passive-aggressive remarks take a little away, rude ones more, insults the most. Plain instructions, corrections and frustration with the problem are neutral: 153 of your 371 readable messages.
Activity
The ground covered
Your messages
412
Conversations
58
Active days
41
What we read
371 of your 412 messages were readable
That’s 90% of your messages. The rest were set aside, never counted against you:
Language we can’t read yet (English only for now)12
Only code, quotes or empty29
No date in the source7
Not clearly written by you2
Assistant replies, tools and system text (never scored)2,980
Missing dates and unknown authors are disclosed, never guessed. Nothing here counts as harsh.
Method
How this was worked out
Fixed, versioned rules give each readable message a tone between −1 and +1: polite requests +0.1, thanks and positive feedback +0.3, warm praise and apologies +0.5, passive-aggressive remarks −0.15, rude or dismissive ones −0.3, hostile ones −0.6 and targeted insults −1. Everything else, including direct instructions and corrections, is 0. No AI model is involved. A score appears once there are at least 30 readable messages.
score = round(100 × average tone ÷ 0.3), kept between −100 and +100
Karma processor
2.1.0
Rules
karma-en-2.0.0
Text extraction
extract-1
Language check
lang-heuristic-1
Demo data: invented for illustration.
What you can import
Each source says how well it has been checked. “Unverified” means we built it from documentation and have not tested it against a real export yet.
Supported sources and their verification status
Source
Status
Where to find it
Claude Code
Tested on real local data
Session files in ~/.claude/projects (one folder per project).
Codex CLI
Tested on real local data
Session files in ~/.codex/sessions and ~/.codex/archived_sessions.
Claude (web export)
Unverified
A claude.ai data export: the ZIP file itself, its folder, or its conversations.json.
ChatGPT (data export)
Unverified
A ChatGPT data export: the ZIP file itself or its folder (conversations.json, or conversations-000.json and so on).