Privacy Policy
How Neumann collects, uses, and protects your information.
Last updated: 27 July 2026
Neumann is a code editor where agents work across your codebase, with optional cloud agents that run on infrastructure we operate. This notice explains what personal information Neumann collects, how it is used, who it is shared with, and the choices you have.
Who this policy applies to
This policy applies to everyone who downloads the Neumann editor, creates an account, or uses Neumann's cloud agents and related services. It explains what we collect, why, who we share it with, and the choices you have.
Local-first by default
Neumann is a desktop editor. Opening a project, running a local agent, and reviewing a diff happen on your machine and involve no upload. Your repository and working tree stay local unless you explicitly use a feature that requires our servers, such as a cloud run or indexing.
Information we collect
- Account information — your name, email address, and authentication identifiers from the provider you sign in with.
- Billing information — plan and subscription details, processed by our payment provider; we do not store full card numbers.
- Diagnostics and usage — crash reports and aggregate feature usage, where you have not opted out, used to keep the app stable.
- Cloud run data — for cloud agents, a copy of the repository and the instructions you provide, for the duration of the run.
- Indexing data — for features that need embeddings, file contents may be uploaded temporarily for processing and deleted afterwards.
How we use information
We use the information above to provide and secure the service, run the tasks you start, process payments, respond to support requests, and improve reliability. We do not sell your personal information, and we do not use the contents of your repositories to train models.
Privacy Mode and the ignore list
Privacy Mode keeps plaintext out of requests to hosted features. Combined with the ignore list, it lets you decide exactly how much of a repository any hosted feature can see. Paths on the ignore list are excluded from indexing and never leave your machine through those features.
Cloud runs
A cloud run necessarily places a copy of the repository on the machine executing it. Access is restricted, transmission is encrypted, and the machine is torn down when the run ends. The resulting diff is returned to you and nothing is merged without your approval.
Regional deployment
Cloud infrastructure and data are pinned to your account's region — United States, Singapore, or Malaysia — so data residency follows the account rather than the request.
Data retention
We keep account and billing records for as long as your account is active and as required for legal and accounting purposes. Repository data used for a cloud run is retained only as long as needed to complete the run and deliver its result. Files uploaded for indexing are deleted after processing.
Security
We use encryption in transit, access controls, and short-lived cloud environments to protect your information. No system is perfectly secure, but we work to limit what is collected and how long it is kept.
Your rights
Depending on where you live, you may have the right to access, correct, export, or delete your personal information, and to object to certain processing. Contact us using the address below to make a request.
Children
Neumann is not directed to children and is not intended for use by anyone under 16.
Changes to this policy
We may update this policy as the product and applicable law change. Material changes will be announced in the app or by email, and the effective date above will be updated.
Contact
Questions about this policy or your information can be sent to: