Your project stays on your computer. You grant the permissions. AI can work only when it receives the relevant data it needs.
This page explains the boundary between local data, ChatCode, the operational server và the AI provider so you know exactly what you are allowing.
Your repository is not bulk-uploaded to ChatCode servers for storage.
The project remains on the computer running ChatCode.
Project / files
They remain in your computer's filesystem. ChatCode works only with projects you added.
Project Brain
A local indexing/context layer that helps navigate the workspace efficiently.
ChatCode server
Used for licensing, accounts, updates and necessary connection/routing functions; it is not a repository storage service.
“Local” does not mean file content can never leave the computer.
When AI needs content for analysis, the context/results returned by a tool may be sent to the AI provider you are chatting with.
For sensitive data, choose an appropriate provider/plan, review its policies, scope projects and permissions, and expose only data that is genuinely needed.
Permissions are real boundaries, not just prompt instructions.
Each project has an independent scope and permission set.
| Permission | Use when | Safer default |
|---|---|---|
| Read/Search | Understand source/data, review | Allow when needed |
| Edit files | Fix/refactor/content | Enable only on target projects |
| Create/delete/rename | Create output, scaffold | Off for review-only work |
| Task | Test/build/lint | Allow-listed tasks only |
| Git write | Local stage/commit | Does not mean auto-push |
| Remote/SSH | Deploy/operations | Separate and least-privilege |
Secrets and credentials must be treated differently from ordinary files.
ChatCode blocks many common sensitive paths and does not return remote passwords/private keys to the AI.
Local sensitive paths
Names/formats such as .env, .ssh, private key, credential store… are blocked by policy.
Remote credentials
AI selects a profile and allowed operation; ChatCode uses the password/private key internally without exposing it back to the model.
Safest pattern: Inspect → Plan → Change → Verify → Review.
Do not grant every permission and ask AI to “do everything” in the first message.
Inspect
Read-only. Confirm the project, state and root cause.
Plan
Ask AI to list files to change, tests to run and risks.
Change + Verify
Enable only necessary permissions, make minimal changes, verify, then review the diff.
Dùng ChatCode với project shop. Chỉ đọc và xác định root cause lỗi checkout. Liệt kê file dự kiến phải sửa và test cần chạy. Chưa sửa file.Tiến hành thay đổi tối thiểu theo kế hoạch. Chạy test liên quan. Trả diff và rủi ro còn lại. Không deploy.A connection link is a capability that must be protected.
Use token rotation and advanced OAuth when appropriate.
Standard mode is simpler but the link/token must remain secret. Advanced security requires additional authorization. If you suspect a link leaked, rotate it and update the connector.