Articles

Articles about Doka and AI agents

How Doka works, why a desktop agent matters, and what is happening with AI. page 4.

July 30, 2026·3 min read

Notion MCP: Connecting a Knowledge Base to a Local AI

Connecting the official Notion MCP to Doka through OAuth: searching a knowledge base, building reports, and updating pages without pasting notes into a chat.

mcpnotionknowledge base
July 30, 2026·5 min read

Ollama or LM Studio: Which One to Choose for a Local Model

How Ollama differs from LM Studio in practice: interface vs. daemon, local API addresses, hardware requirements, licensing, and common model-loading errors.

ollamalm studiolocal
July 30, 2026·4 min read

OpenClaw Locally: Installing With Ollama and Hardware Requirements

How to run OpenClaw with Ollama, what to pick during setup, why a small local model handles the agentic loop poorly, and where privacy actually stops.

openclawollamaagents
July 30, 2026·4 min read

OpenCode Locally: How to Connect Ollama and Pick a Model

How to run OpenCode with a local model through Ollama, what stays on your computer, why the agent needs a big context, and how OpenCode differs from desktop Doka.

opencodeollamacode
July 30, 2026·4 min read

Decoding a Medical Report With AI, Locally

How to locally break down terms and values from a medical report without sending the document to a cloud chat, and where you absolutely still need a doctor.

medicaldocumentsprivacy
July 19, 2026·3 min read

n8n Alternatives for Personal Tasks: When an Agent Beats a Workflow Engine

What to use instead of n8n for simple automation, and when a workflow engine is overkill. An honest comparison of approaches: a graph of nodes versus an AI agent that does a task from a plain-language description.

n8nalternativesautomation
July 19, 2026·4 min read

GGUF Format Explained: What It Is and Which Quantization to Choose

What the GGUF format is, why quantization matters, how Q4_K_M, Q5, and Q8 differ, how to pick a variant for your hardware, and how to run a .gguf model. No unnecessary theory.

ggufmodelslocal
July 19, 2026·2 min read

Gemma Locally: Running Google's Model on Your Computer, and When It's the Right Call

What Gemma from Google is, how to run it locally, and where it's a good fit compared to Qwen and other open models. A practical look, no overhyped claims.

gemmamodelslocal
July 19, 2026·4 min read

Enterprise AI: Rolling Out AI at a Company Without a Data Leak

Why cloud AI tools don't get past security review, and how to roll out AI inside a company within its own perimeter — on local models, with access to internal systems.

businesssecurityon-prem
July 19, 2026·3 min read

An Enterprise AI Assistant: Help for Employees on the Company's Own Infrastructure

What an enterprise AI assistant needs to look like so it can be used without risking data: local models, working inside the perimeter, access to internal systems, and a managed rollout.

businessassistantsecurity
July 19, 2026·3 min read

A Personal AI Assistant on Your Desktop: A Helper on Your Computer, Not in the Cloud

What a personal AI assistant is, how it differs from cloud services, and why it belongs right on your desktop. A breakdown of what a private assistant living on your computer can do.

assistantdesktopprivacy
July 19, 2026·3 min read

A Local Model Instead of a Cloud API: Ollama, LM Studio, and Qwen in an Agent

How to use a local model in an AI agent instead of a cloud API — through Ollama, LM Studio, or your own .gguf. Why this matters, how it differs, and how to set it up so you stop paying for tokens.

localmodelsollama