Lettertrace measures how often Claude, ChatGPT, and Gemini mention your company. But there's a catch: it's free end-to-end, developer-first, and open source.
works with ChatGPT, Claude & Gemini · self-host in minutes
$ lettertrace run --project acme
› querying claude-opus-4-8 across 24 prompts…
✓ acme mentioned in 15 / 24 answers
share of voice ████████░░░░░░░░ 41%
sentiment +0.34 positive
top competitor notion · 28%
$
watches the assistants your buyers ask
- Claude
- ChatGPT
- Gemini
- AI Overviews
watch it trace
One run, start to finish
- 01
Track a topic.
Add what your buyers ask about. One line is enough.
- 02
Generate the questions.
Lettertrace writes the real prompts people put to assistants, dozens per topic.
- 03
Ask every model.
Claude, ChatGPT and Gemini answer. Each answer is read for mentions, position and sentiment.
- 04
Trace the trend.
Every run is a datapoint. The line tells you whether it’s working.
share of voice
Every run is a datapoint.
Every answer in your category, split between you and the brands you track. Watch your share grow, and see what moved it.
acme, 12 weeks
22% → 41%
▲ +19 pts share of voice
| Week | Acme (you) | Notion | Linear | Others |
|---|---|---|---|---|
| Week 1 | 22% | 38% | 24% | 16% |
| Week 2 | 23% | 37% | 25% | 15% |
| Week 3 | 22% | 39% | 23% | 16% |
| Week 4 | 26% | 38% | 22% | 14% |
| Week 5 | 31% | 35% | 21% | 13% |
| Week 6 | 33% | 34% | 21% | 12% |
| Week 7 | 32% | 35% | 20% | 13% |
| Week 8 | 36% | 33% | 20% | 11% |
| Week 9 | 38% | 31% | 19% | 12% |
| Week 10 | 39% | 30% | 19% | 12% |
| Week 11 | 40% | 29% | 19% | 12% |
| Week 12 | 41% | 28% | 19% | 12% |
- 1Week 4: Published a comparison page
- 2Week 8: Cited in a Claude answer roundup
- 3Week 11: Competitor launched v2
features
Everything you need to diagnose AI mentions.
Bring your own key
Use your own Anthropic, OpenAI & Google keys. They’re encrypted at rest and never leave your infrastructure.
Multi-model
Monitor Claude, ChatGPT, Gemini, and Google AI Overviews side by side. Add more answer engines as they matter.
Variation generation
Turn one topic into dozens of natural prompts automatically, no manual prompt-writing.
Sentiment & recommendations
Know not just if you appear, but whether the answer speaks well of you, and recommends you.
Share of voice
See exactly how often you win the answer versus each competitor you track.
Scheduled monitoring
Run daily or weekly on autopilot and build a trend line you can act on.
open source
Yours to run, inspect, and extend.
- MIT licensed, fork it, self-host it, make it yours.
- Bring your own keys. No usage markup, no middleman.
- Your data lives in your own Supabase, no vendor lock-in.
$ git clone lettertrace && cd lettertrace
$ npm install
$ cp .env.example .env.local
# add Supabase URL + keys
$ npm run dev
→ http://localhost:3000
Find out what AI says about you.
Set up your brand, add a key, and run your first monitor in minutes.
Start monitoring, free