Privacy Policy

1. Introduction

ContextStream ("we," "our," or "us") respects your privacy and is committed to protecting the data you entrust to us. This Privacy Policy explains how we collect, use, disclosure, and safeguard your information when you use our application, API, and website.

2. Information We Collect

• Account Information: When you register, we collect your email address, name, and authentication credentials (via OAuth providers like GitHub or Google).
• Codebase Context: To provide our core service, we process file content to build embeddings, file structure metadata, and dependency graphs. We store an encrypted index (embeddings + metadata + limited file content for search/browsing). For Full graph tier plans (Elite/Team/Enterprise), we may also store full file content encrypted in object storage when enabled. Your code is never shared with other customers, and ContextStream staff do not access it unless you explicitly grant support access.
• Usage Data: We collect telemetry on how you interact with the MCP server and API (e.g., tool calls, error rates) to improve system performance.
• Memory & Decisions: Data explicitly captured by you or the AI agents (decisions, notes, project context) is stored in our database to provide persistent memory.

3. How We Use Your Information

We use the collected data for the following purposes:

• To provide and maintain the ContextStream service.
• To generate embeddings and retrieve relevant context for your AI coding assistants.
• To detect and prevent technical issues or security breaches.
• To notify you about changes to our service.

4. Data Storage and Security

Your data is stored on secure servers hosted by major cloud providers (AWS). We use industry-standard encryption for data at rest and in transit.

We isolate data by Workspace and Tenant ID to ensure that your code context is never accessible to other users or organizations.

5. Third-Party Services

We may share data with third-party vendors only as necessary to provide the service:

• LLM Providers: (e.g., OpenAI, Anthropic) for generating summaries or embeddings.
• Cloud Infrastructure: (e.g., AWS, Supabase, Neon) for hosting and database services.
• Payment Processors: (e.g., Stripe) for subscription handling.

6. Third-Party Integrations (ChatGPT, AI Assistants)

ContextStream integrates with third-party AI platforms including OpenAI ChatGPT Apps. When you connect ContextStream to these platforms:

• OAuth Authorization: You explicitly authorize access via OAuth 2.0. We never share your credentials with third parties.
• Data Shared: Only data you request through the integration is shared (workspace names, project names, memory/decisions, search results). Your code files are not directly shared.
• Read vs Write Operations: Read operations (list workspaces, search, recall) retrieve existing data. Write operations (capture memory, remember) create new entries in your workspace.
• Token Scope: OAuth tokens are scoped to specific permissions. You can revoke access at any time from your ContextStream settings.
• Third-Party Privacy: When using ChatGPT Apps, OpenAI's privacy policy also applies to data processed through their platform. We encourage you to review OpenAI's Privacy Policy.

7. Your Rights

You have the right to request access to, correction of, or deletion of your personal data. You can delete your Workspace and all associated data (embeddings, memories) directly from the dashboard or by contacting support.

8. Contact Us

If you have any questions about this Privacy Policy, please contact us at [email protected].