Open Source

Track your brand
across every LLM

See where ChatGPT, Perplexity, and Gemini mention your brand. Find the gaps. Run real prompts against real models.

Get Started See it in action
ChatGPT
Perplexity
Google Gemini
// live demo

See it working

Interactive walkthrough of the dashboard, prompt generator, and analysis pipeline.

// capabilities

Everything you need to
monitor LLM visibility

01

Prompt Generation

AI creates brand-neutral prompts across topics relevant to your industry. Add your own. Reuse across runs.

02

Multi-Model Testing

Runs against ChatGPT, Perplexity, and Google Gemini via real browser sessions. Not APIs — exactly what your users see.

03

Competitor Tracking

Auto-detects competitors from responses. Merge duplicates, block noise, compare head-to-head.

04

Source Analysis

Track which domains LLMs cite. See brand, competitor, and neutral sources. Find citation gaps.

05

Scheduled Runs

Set it and forget it. Run analysis hourly, daily, weekly, or monthly. Auto-expire stuck runs after 24 hours.

06

MCP Integration

Query your brand data directly from Claude Code or Claude Desktop. 16 built-in tools for deep analysis.

// get started

Up and running in 60 seconds

Two ways to deploy. Pick whichever fits your workflow.

Requirements

1
Docker — that's it for infrastructure
2
OpenAI or Anthropic API key — powers prompt generation and response analysis
3
Browser runtime — Perplexity, ChatGPT, and Gemini responses are fetched via real browser sessions. Pick one:
Local Container Free
~1 prompt/min Included with Docker Compose
Running locally not recommended. May get blocked by anti-bot protections
or
3rd Party Proxy ~$0.05/prompt
~15 prompts/min Residential proxies, no anti-bot issues
Supported: Apify — free credits included on sign up
Option A

Docker Compose

Pull the image and start. Everything runs locally, including the browser automation container.

# Download and start curl -O https://raw.githubusercontent.com/jakubsuchy/traceaio/main/docker-compose.yml docker compose up -d # Open http://localhost:3000

Create an admin account, add your API key, and configure your brand in the setup wizard. Switch to Apify in Settings → Credentials if you want faster parallel runs.

Option B

Claude Code

Let Claude set it up for you. Paste this into Claude Code and it handles the rest.

# Tell Claude: Download docker-compose.yml from https://raw.githubusercontent.com/jakubsuchy/traceaio/main/docker-compose.yml and run docker compose up -d Then open http://localhost:3000

After setup, connect Claude to your data via MCP:

claude mcp add --transport http brand-tracker http://localhost:3000/mcp