Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

On Ubuntu, launch DeepSeek Harness with Node.js and its official npm command, then connect a model either by configuring a compatible self-hosted provider endpoint or by using Ollama’s documented launcher. The Harness opens at http://127.0.0.1:3080 by default. A local-looking endpoint alone does not guarantee local inference: choose a model that actually runs on your machine.

Before you install

DeepSeek Harness is an open-source agent harness from DeepSeek AI, currently in developer preview. Its official README warns: “DeepSeek Harness is in developer preview and iterating rapidly. THERE WILL BE COMPATIBILITY-BREAKING CHANGES.” Check the current README if a command or screen differs from the steps below.

You need Node.js for the npm launch route. The project’s setup instructions do not specify an Ubuntu release or a Node.js installation method, so use the current installation instructions for your Ubuntu version and the official Node.js download page. The reviewed setup sources do not state minimum hardware requirements.

Install and start the Harness

  1. Install Node.js using the instructions appropriate to your Ubuntu release.

    Free tools Windows power users keep installed

    One-click scans. No signup required.

    Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
    #1 Best Overall
    Panasonic Toughbook CF-31 MK5 Rugged Laptop, 13.1in i5, 8GB 256GB (Renewed)
    • [ULTRA-RUGGED DESIGN] MIL-STD-810G and IP65 certified. Built to survive 6-foot drops, heavy rain, and extreme vibrations. Features a magnesium alloy chassis with an integrated carry handle for maximum portability
    • [4G LTE - WORK ANYWHERE] Integrated 4G LTE Multi-Carrier Mobile Broadband. Stay connected to the internet in remote areas or on the road without relying on Wi-Fi or phone hotspots. True mobile freedom for field professionals
    • [1200-NIT SUNLIGHT READABLE] 13.1" XGA Touchscreen with CircuLumin technology. At 1200 nits, it is nearly 4x brighter than a standard laptop, ensuring perfect visibility under direct, intense sunlight
    • [LINUX UBUNTU PRE-INSTALLED] Fast, secure, and bloatware-free. Optimized for developers, network engineers, and diagnostic software that thrives in a stable, open-source environment
    • [LEGACY SERIAL PORT] Features a native RS-232 Serial Port, HDMI, and USB 3.0. Essential for connecting directly to industrial machinery, CNCs, and automotive diagnostic tools without unreliable adapter
  2. Open a terminal and run npx @deepseek-ai/dsh web. This invokes the Harness Web UI through npm.

  3. When the server starts, open http://127.0.0.1:3080 in a browser on the same machine. This is the default address in the project README.

The address uses the loopback interface, so it is for access from the machine running the Harness; it is not a public network address.

Choose how to connect the local model

There are two documented routes. Use the custom provider setup when your model server exposes an API and you want to enter its connection details yourself. Use Ollama’s integration launcher if you want its documented Harness integration and model selector.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
Route What you configure What to verify
Harness Web UI with custom provider Provider ID, base URL, API protocol, credential, and model ID The server’s URL and API protocol must match what the provider endpoint supports.
Ollama integration Launch with ollama launch dsh; optionally select a model with --model or configure with --config Select a model that runs locally if local inference is the goal; Ollama’s examples include cloud as well as local models.

Configure a self-hosted provider in the Web UI

The Harness supports custom model APIs for self-hosted servers. Follow the official provider guide and take the endpoint values from the model server you actually run; there is no universal local URL or credential that applies to every server.

  1. In the Harness, open the Models page and add a provider.

    Rank #2
    HP 17 Business Laptop - Linux Mint Cinnamon - Intel Quad-Core i5-10210U, 32GB RAM, 1TB PCIe NVMe SSD + 1TB Storage HDD, 17.3" Inch HD+ (1600x900) Display
    • Intel Core i5-10210U (up to 4.2GHz) - 1TB PCIe NVMe + 1TB HDD - 32GB DDR4 SDRAM
    • 17.3" HD+ (1600x900) Display, Intel UHD Graphics 620
    • Built in HD 720p Webcam with Microphone - Bluetooth Version4.2
    • I/O Ports: 2x USB 3.1 (Data Only), 1x USB 2.0, 1x HDMI, 1x Headphone/Microphone Combo Jack
    • Linux Mint Cinnamon 64-Bit - 6-Row Keyboard w/ Full Numberpad
  2. Enter a provider ID and the server’s endpoint base URL.

  3. Select the API protocol implemented by that endpoint. The guide lists OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages.

    Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
  4. Provide the credential expected by the provider, then add the model ID used by the server.

  5. Select that configured model for use in the Harness.

These fields must agree with the server’s actual API behavior. A protocol mismatch or an incompatible gateway can prevent requests from working even when the endpoint is reachable.

Use Ollama’s documented launcher

Ollama documents a separate integration path for DeepSeek Harness. Run ollama launch dsh to launch the integration. To select a model explicitly, use ollama launch dsh --model <model>; use ollama launch dsh --config to configure without starting it. See Ollama’s DeepSeek Harness integration documentation for the current behavior and model selection details.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
Rank #3
Lenovo IdeaPad Slim 3 Linux Laptop, 15.6" FHD Touchscreen Laptop, 8-Core AMD Ryzen 7 5825U, 16GB RAM, 512GB SSD, Keypad, SD Card Reader, Stylus Pen + External Portable SSD + USB Hub, Linux Ubuntu OS
  • Powerful Linux Laptop: This IdeaPad Slim 3 Laptop comes pre-installed with Ubuntu Linux, offering fast performance, robust security, and a clean, user-friendly experience. Enjoy full customization, seamless hardware compatibility, and access to thousands of open-source apps. Whether you're working, creating, or coding, it's built to keep up with everything you do.
  • A Multitasking Master: The latest AMD Ryzen 7 5825U processor (up to 4.5 GHz) delivers powerful performance with 8 cores and 16 threads for smooth multitasking. Integrated AMD Radeon Graphics provide crisp visuals for streaming, browsing, photo editing, and casual gaming. With smart machine intelligence, it adapts to your needs for a fast, responsive experience.
  • 15.6" Full HD Display: The IdeaPad Slim 3 boasts an 88% screen-to-body ratio for a floating, edge-to-edge visual experience. TÜV Low Blue Light certification reduces eye strain, making it perfect for long work or study sessions.
  • Military-Grade Durability: The smart IdeaPad Slim 3 combines portability and durability, letting you work, study, and play on the go. With a profile 10% slimmer than the previous generation, it's lightweight yet military-grade rugged, ready for anything, anywhere.
  • Versatile Connectivity: Enjoy the security of a built-in webcam with a privacy shutter. Connect effortlessly with multiple ports: 2x USB A, 1x USB C, 1x HDMI, 1x SD Card Reader, 1x Headphone/Microphone combo. Bundle comes with Stylus Pen, 256GB Portable SSD and 5-in-1 Docking Station.

Check the selected model rather than assuming that every option is local: Ollama’s integration page illustrates both a local model and a cloud model. A cloud selection does not satisfy an all-local inference requirement.

Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Support on Ko-Fi

Troubleshoot provider setup

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.