Featured

Building a Fully Local, System-Wide AI Agent CLI on Linux

on
Cloud-based agentic CLI tools are undeniably convenient, but sending internal terminal workflows, system commands, and proprietary files to third-party endpoints is a persistent privacy risk. Running a fully local, autonomous agent directly on your workstation eliminates subscription costs, avoids rate limits, and grants you unconstrained access across all your attached drives. This guide details how to pair Ollama with Open Interpreter on modern Linux (Ubuntu), resolve tricky runtime quirks like Python 3.14 native builds and removed modules, map persistent storage, and create a one-click desktop launcher. System Architecture The setup consists of two layers: Inference Engine (Ollama): Serves local open-weight models with hardware GPU acceleration. Agent Harness (Open Interpreter): Interprets natural language queries, writes code, and executes Bash or Python commands directly on your system. For agentic coding and file management, qwen2.5-coder:14b provides an optimal balance of c...
0

Install Windows Recall on a non-Copilot+ PC

on

Steps to Install Recall on Unsupported Hardware:

  1. Ensure You Have the Right Windows Version

    • You need Windows 11 build 26100.712 from the Release Preview Channel.
    • Microsoft removed Recall components from newer builds, so this method only works with older versions.

  2. Download the Amperage Tool

    • Amperage is a third-party tool that bypasses hardware restrictions.
    • You can find it on GitHub.

  3. Install AI Components

    • Recall requires additional AI components to function.
    • These can be downloaded separately and placed in the correct directory.

  4. Run the Installation Command

    • Open Command Prompt as Administrator.
    • Navigate to the Amperage folder and run: 
      amperage /install
    • Restart your PC after installation.

Important Notes:

  • This method is not officially supported by Microsoft.
  • It may not work on all devices, especially non-ARM-based machines.
  • If your PC isn’t ARM-based, you might need to emulate an ARM installation using a virtual machine.

Setting up a virtual machine for an ARM-based Windows installation can be done using Hyper-V or Azure. Here’s a general guide:

Option 1: Using Hyper-V (Local VM)

  1. Enable Hyper-V

    • Open Command Prompt as Administrator and run: 
      DISM /Online /Enable-Feature /All /FeatureName:Microsoft-Hyper-V
    • Restart your PC.

  2. Download Windows 11 ARM64 ISO

    • Get the ISO from UUP Dump or Microsoft’s official sources.

  3. Create a Virtual Machine

    • Open Hyper-V Manager → New Virtual Machine.
    • Select Generation 2 and allocate RAM (at least 4GB).
    • Attach the Windows 11 ARM64 ISO as the boot disk.

  4. Adjust VM Settings

    • Disable Secure Boot (Windows 11 ARM64 doesn’t support TPM in Hyper-V).
    • Set the virtual hard disk size to at least 64GB.

  5. Install Windows

    • Start the VM and follow the installation steps.

More details on setting up Hyper-V for ARM can be found here.

Option 2: Using Azure (Cloud VM)

  1. Sign in to Azure

    • Go to the Azure portal and create a new VM.

  2. Select Windows 11 ARM64

    • Choose Windows 11 Professional on ARM as the image.

  3. Configure VM Settings

    • Select Ampere Altra ARM-based processors.
    • Set up Remote Desktop (RDP) for access.

  4. Deploy and Connect

    • Click Create and wait for deployment.
    • Connect via RDP to start using the VM.

You can find a detailed guide on Azure-based ARM VMs here.

Comments

Post a Comment