Note
This is a quick copy-paste-observe guide for people in a hurry to quickly set up a local coding agent at no additional costs using OpenCode and Ollama.
- Install Ollama using the command below:
Note
This is a quick copy-paste-observe guide for people in a hurry to quickly set up Open-WebUI such that one can run and access a local Large Language Model (LLM) as a web application similar to OpenAI's ChatGPT.
Tip
This setup is recommended if your GPU hardware specifications falls below what is the typical minimum 64000 token context window required for agentic coding. Eg. Nvidia Geforce RTX 3060 with 12GB VRAM.
Note
This is a quick copy-paste-observe guide for people in a hurry to quickly set up a Deep Local Research Agent where there are no reliance on proprietary web search api usage while still being useful in providing detailed reports on selected user topics.
For this guide, we will be using LearningCircuit's local_deep_research implementation with the following setup structure:
Note
This is a quick reference guide on how to set up your Docker usage such that docker images are stored on an external drive.
If, like me, you are constantly having to worry about limited disk space on your host device where you doing your development, it would likely benefit you to have the images stored separately.
Warning
This guide makes a loose assumption that your external drive will be mounted on the following:
/home/$USER/Mountsmap-DGOtniGL.js:3852 THREE.WebGLRenderer: A WebGL context could not be created. Reason: Could not create a WebGL context, VENDOR = 0x1b36, DEVICE = 0x0100, GL_VENDOR = Google Inc. (Mesa), GL_RENDERER = ANGLE (Mesa, llvmpipe (LLVM 19.1.1 256 bits), OpenGL ES 3.2 Mesa 24.2.8-1ubuntu1~24.04.1), GL_VERSION = 24.2.8, Sandboxed = no, Optimus = no, AMD switchable = no, Reset notification strategy = 0x8252, ErrorMessage = BindToCurrentSequence failed: .Note
This is usually because your web browser cannot load 3D graphics because it is using a slow, software-based renderer called llvmpipe instead of your actual graphics card (GPU).