Privacy Policy

The pip-installed CLI runs entirely on your infrastructure. Your source code, git history, generated docs, embeddings, and the dependency graph never leave your machine. The CLI sends anonymous usage telemetry to repowise (commands and tools used, versions, OS, success and duration), never code, file paths or repository names. It is on by default and announced once on first run. Turn it off with repowise telemetry disable, DO_NOT_TRACK=1, REPOWISE_TELEMETRY_DISABLED=1 or REPOWISE_OFFLINE=1.

When you bring your own LLM API key (for example Anthropic, OpenAI, Gemini, Azure OpenAI or a local Ollama model), the prompts and code excerpts go directly from your machine to that provider under their privacy terms. repowise is not in the path.

When you sign up for the hosted Service, we collect: account email, name, and avatar (from your OAuth provider); GitHub installation metadata (repos you grant access to); billing details (handled by our payment processor, we never see card numbers); and product telemetry (page views, feature use, error reports).

When you index a repository, we clone it onto an ephemeral compute instance, parse it into a dependency graph, mine git history, run embedding and LLM jobs against it, and store the resulting artifacts (wiki, graph, hotspots, decisions) in our database. The cloned working tree is deleted at the end of every indexing run; only the derived artifacts persist.

When you request one of our guides, we collect your email, the optional first name, company and role you give us, and the campaign link you arrived from. We use them to send you the guide and occasional emails about our research and product updates. You can unsubscribe at any time, and we keep these details until you ask us to delete them.

We use your data to: provide and improve the Service; authenticate you; bill you; send transactional email (re-index notifications, receipts); diagnose errors; and (for aggregate, non-identifying metrics) measure adoption.

We do not sell your data. We do not use your code or repository content to train any model.

Hosted Service relies on the following sub-processors:

• A managed database provider: primary database, auth, storage
• A cloud compute provider: ephemeral, isolated indexing compute
• A cloud application host: backend API hosting
• A web hosting and edge network provider: frontend hosting
• LLM providers: only when you trigger a generation or chat
• An object storage provider: large index artifacts
• An email delivery provider: transactional email
• A payments provider: billing and subscription management
• A website analytics provider: heatmaps and session replay on our website, loaded only after you accept cookies

The current list of named sub-processors is available on request at hello@repowise.dev.

Indexed snapshots are retained while your account is active. You can delete a repository, a workspace, or your entire account from settings. On account deletion we soft-delete with a 7-day grace period; after grace, data is purged from primary storage within 30 days and from backups within 90 days. Billing ledger entries, public documentation pages, feedback you sent and product analytics events are kept with the link to your account removed. A repository is deleted, with its index and derived artifacts, once no account links it.

You may request access, export, correction, or deletion of your personal data at any time. Email hello@repowise.dev. EU/UK residents have the rights described under GDPR/UK-GDPR including the right to lodge a complaint with a supervisory authority. California residents have CCPA rights including the right to know and the right to delete.

See our Security overview for transport encryption, encryption at rest for sensitive columns, access controls, and incident-response procedures.

We will post material changes to this policy on this page and update the “Last updated” date. Continued use after a change constitutes acceptance.

Questions or requests: hello@repowise.dev.