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

WSA with Google Play store and Magisk

on
Download the WSA (windows subsystem for Android) from here and adb from here

Extract the platform tools to a folder named adb in C:\

Unzip the package with 7zip or WinRAR 

right-click, extract to \ 

Find the install PowerShell script , right-click and open in PowerShell

This will install the package 

Open WSA and turn on developer options , also turn on developer mode in windows settings

Open Windows Terminal in admin mode in the adb folder and type : 

adb connect localhost:58526

Or use your IP address 

adb connect <your IP address> 

Copy the path to the magisk.apk in the  WSA folder 

  
Then use this command to install magisk : 

adb install <paste the copied path> 




Comments

Post a Comment