Local by default. Optional by choice.
See where evidence goes and which activities can cost money.
The core tracker and code scans run on your machine. Optional connections have their own data paths and costs. Inspect the path before enabling it.
| Feature | Data goes to | Cost |
|---|---|---|
| Code scans and activity import | Your local tracker | Local CPU and disk |
| Task report | Your local tracker | Writing uses the active agent's existing tokens |
| Optional model analysis | Your configured provider | Provider billing |
| GitHub enrichment | Local records read through your GitHub access | Your existing GitHub access |
The website does not receive your project data. Model analysis is separate from browsing or saving a report.
Keep private evidence private
Reports store the feedback you submit. Analyzer artifacts can include code fragments, diagnostics, and local paths. These local records are not automatically scrubbed public exports.
This website receives no tracker evidence or source code. Your coding host has its own data handling and billing.
The core runs locally
Your project tracker runs on loopback and stores its data in a local SQLite database. Code scans use your machine's CPU and disk. They don't call a model.
This website is documentation. It doesn't connect to your tracker, receive your project evidence, or upload your source code.
What gets stored
Native activity import keeps a restricted projection for recorded sessions, turns, usage, and tool activity. OpenCode, Grok Build, Claude Code, Gemini CLI and Cursor telemetry also retains only normalized metadata and counters. It doesn't import raw prompts, private reasoning, command arguments, or full transcript output into that projection.
Agent reports store the feedback you submit. Analyzer artifacts can contain diagnostic messages, code fragments, and local paths. Keep reports concise and free of secrets or customer information.
The database and analyzer artifacts are private local evidence, not automatically scrubbed public exports.
Costs you can expect
| Activity | Where the cost comes from |
|---|---|
| Browsing your local dashboard | Local application; no model call |
| Structural and full scans | Local CPU, disk, and possible dependency downloads |
| Agent work in Codex, Muse, or another host | Your existing host or provider billing |
| Optional checkpoint classification | A configured model provider |
| Running a personal benchmark task | The agent host you choose to execute it |
Some scans take longer and use more storage than others. Sampled structural history is bounded; full historical analysis can require additional dependency environments.
Optional model analysis
Optional checkpoint analysis can classify friction, causes, and suggestions through the configured Typesafe/Jev integration. Provider access and policy must be configured explicitly. Read the source reports behind a classification.
You can collect reports, create concrete proposals, test changes, and retrieve lessons without enabling paid analysis. Opening a report isn't a request to analyze it.
For setup, see Analyze reports with Jev. Request limits and the report payload are covered in the Jev reference. The key belongs in the connected project's root .env.local as TYPESAFE_API_KEY. Analysis also needs an explicitly enabled project policy.
Optional GitHub enrichment
GitHub collection uses your local gh authentication to read PRs, reviews, findings, and checks. It doesn't comment on or merge PRs.
Retain and recover your evidence
Managed upgrades make a database backup before migration. Removing a project registration retains its data. Settings provides storage and retention controls; inspect those controls before pruning anything.
Use phasedrift stop to stop a manager-owned tracker. Never remove a lock belonging to a running instance.