DEEPSEEK • SUPER AGENT • SETUP GUIDE

Your project.
Always monitored.
Carefully automated.

Build a reproducible DeepSeek Super Agent setup on Windows 11, keep its Linux environment on an external SSD, and connect an OpenRouter model. Choose an AI-assisted or manual installation path.

Community installation guide • Not affiliated with DeepSeek • Last reviewed: November 4, 2026

EVENT → POLICY → EXECUTION
Superagent / Workflow
GitHub
Event
→
Router
Policy
→
Worker
Ticket
Isolated test repository • Human-reviewed pull requests
02Installation paths
WSL2Linux environment
$0*Optional free-tier model
MITPrototype license
01 / BEFORE YOU BEGIN

Understand the setup

Super Agent is a research prototype that runs as a DeepSeek Harness bundle, not a standalone model. Its worker presets have broad OS access; don't point them at your personal files.

01

Dedicated external SSD

Place Ubuntu's virtual disk and the Linux-side tools, Harness state and workspaces on the SSD. Some WSL host components remain on Windows.

02

Separate GitHub identity

Use a disposable repository and a dedicated bot user. Do not give the worker your primary GitHub credentials.

03

Human approval

Leave auto-merge disabled and proactive acceptance in observe mode. Review changes and logs yourself.

Security: DeepSeek documents the Router/Worker presets as danger-full-access. WSL alone is not a security boundary. For strong isolation, use a separate OS user/VM with only test credentials. The guide does not silently grant privileged access.
02 / INSTALLATION

Pick your installation path

Both paths end in the same Harness + Super Agent installation. Commands are provided for a Windows 11 host and an Ubuntu WSL2 environment on an external SSD.

Step zero — identify the external SSD

Open My Computer → right-click the SSD → Properties. Confirm its drive letter, free space, and filesystem. Never format the drive. The examples use E: only as a placeholder.

Choose a folder name or a relative subfolder path. The install commands and Codex prompt update automatically.

Ubuntu install pathE:\TunnelLab-AI\Ubuntu
Use an NTFS-formatted SSD with at least 20–30 GB free. If your disk is exFAT or FAT32, do not run the WSL location command before choosing a compatible destination.
PowerShell · inspect only
wsl --version
wsl --list --verbose
Get-Volume

AI-assisted: let Codex handle the setup

Run Codex Desktop in a local environment that can actually access Windows and WSL. Paste this prompt into Codex. It performs discovery first and asks permission before any modifications.

NEW — TunnelLab installer preview. One prompt coordinates the full installation with safety checkpoints, resume support and no automatic Windows reboot. The consolidated scripts are not yet end-to-end tested on a fresh machine.
Codex Desktop · complete setup prompt
You are my local Windows 11 installation agent. Set up DeepSeek Super Agent on my external SSD from preflight through an inactive local panel using the TunnelLab single-prompt workflow. Read and follow this complete, version-pinned operator guide first:
https://github.com/pouramin/dshsuperagent/blob/main/installer/CODEX_PROMPT.md
Official upstream remains https://github.com/deepseek-ai/dsh-superagent-prototype — TunnelLab is independent.

My external SSD drive is E: (verify this yourself; it may be different).
Goal: store the Ubuntu WSL virtual disk, Harness packages, DSH_HOME, source checkout, caches, state, worktrees and logs on that SSD, not the internal C: drive whenever supported.

One conversation, no repeated prompts for normal stages. First verify the exact disk and present the complete safety plan for approval. Obtain separate authorization for administrator changes or any potentially forced reboot. NEVER reboot Windows, interrupt OBS, format disks, fall back to C:, overwrite an existing profile, expose credentials, or enable workers / auto-merge. Resume safely after a manual reboot. Stop at the first authenticated panel and hand over GitHub/model setup to me. If you cannot read the full guide, stop instead of improvising.

Codex cannot approve Windows UAC prompts, create accounts or supply private API keys on your behalf. Those are manual checkpoints.

03 / MODEL PROVIDER

Connect OpenRouter

Harness supports a custom OpenAI Chat Completions-compatible provider. Free OpenRouter models may work, but tool use, context limits and reliability vary; compatibility must be tested rather than assumed.

Settings → Models → Custom model API

Provider configuration
Provider ID: openrouter
Base URL: https://openrouter.ai/api/v1
API protocol: openai-completions
API Key: enter privately in Harness
Model ID: openrouter/free (automatic free-model routing; verify tool calling)

Select Fetch available models, check tool-calling support and test a small task. A free API tier does not guarantee unlimited requests or uninterrupted operation.

Costs and limits

The prototype's source code is MIT-licensed. Using a free model may cost $0 in model tokens within the provider's applicable limits. Storage, networking, paid models, retries and hosted compute can still cost money.

Do not rotate multiple accounts to evade free-tier limits. Use one account or independent providers under their terms.
OpenRouter API Keys ↗
04 / FIRST TEST

Verify before trusting the agent

Use a disposable GitHub repository with a trivial reproducible bug. Mention the dedicated bot in a NEW issue comment, then watch the Ticket and review every proposed change.

Verification checklist0 / 7
Do not treat a generated PR as proof that the bug was fixed. Run tests yourself; inspect differences and check API usage.
05 / OFFICIAL REFERENCES

Sources & documentation

Documentation can change. These are the primary sources used for this installation guide; verify version-specific commands before applying upgrades.