Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.
- GitHub stars
- 15
- License
- BSD-3-Clause
- Added
- 2026-08-14
GitHub info
- GitHub stars
- 15
- License
- BSD-3-Clause
- Primary language
- TypeScript
- Last push
- Aug 20, 2026, 3:08 PM
- Maintainer
- slywalker2006
- Added
- 2026-08-14
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
black-login.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/black-login.png
card-back.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/card-back.png
card-front.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/card-front.png
chat.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/chat.png
main-ui.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/main-ui.png
white-login-en.png
https://raw.githubusercontent.com/slywalker2006/dsh-passwords/main/docs/screenshots/white-login-en.png
Install
dsh plugin --profile web add dsh-passwordsTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/slywalker2006/dsh-passwords)Related plugins
Security & Permissionsdsh-full-remote
★ 29Remote DeepSeek Harness with full server-side API access (`settings.*` / `credentials.*` / `host.listDirectory`). Token-gated reverse proxy, per-device sessions, phone invite QR, fence self-check, optional approval / CIDR / idle timeout / local TLS, WebSocket/SSE.
dsh-remote
★ 51Remote access & authentication for DeepSeek Harness web UI: account/password login gate, MFA (TOTP), signed session cookies, role-based access, in-browser directory picker, account management settings, fully localized in English and Chinese.
dsh-defend
★ 5Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.