Articles
Articles about Doka and AI agents
How Doka works, why a desktop agent matters, and what is happening with AI. page 3.
Open WebUI and Ollama on Your Own PC: Do You Need Two Services
How to install Open WebUI through Docker or pip, how to connect Ollama through OLLAMA_BASE_URL, and at what point a web interface on top of a local model stops paying for itself.
A Server for a Local LLM: Do You Need a Dedicated Computer for the Model
What an LLM server actually means, when a dedicated machine for the model is worth it, what it really costs, and why for a single user a regular computer usually wins.
vLLM, Ollama, and llama.cpp: Why the Fastest Engine Isn't What You Need at Home
How vLLM differs from llama.cpp and Ollama, why it needs Linux and a server-grade GPU, what workloads it's built for, and when it's actually worth installing.
DeepSeek or Qwen for Local Use: Which One to Pick
Comparing DeepSeek and Qwen with no cloud involved: which versions you can actually run at home, how much memory to budget, and what to pick for code versus everyday tasks.
Goose AI and Other Terminal Agents: A Look Without the Subscription
What the open-source agent Goose can do, how it works with local models and MCP, and how it differs from desktop Doka and other CLI agents.
Hermes Agent Desktop: Setup and Local Models
What Hermes Agent Desktop can do, how to pick a provider or a local model through LM Studio, where data is stored, and how the app differs from Doka.
LM Studio Bionic: What the AI Agent for Open Models Can Do
A breakdown of LM Studio Bionic: how the standalone app differs from regular LM Studio, how Work and Code Projects are structured, what's free versus billed by the token, and where 'local' stops once you switch to Secure Cloud.
MCP in LM Studio: Connecting Servers to a Local Model
Where mcp.json lives in LM Studio, how to add a local or remote MCP server, why servers built for cloud models can break a local one, and what actually stays on your computer.
MCP for the Browser: Giving a Local AI Agent Access to the Web
Connecting Playwright MCP to Doka: the agent opens sites, clicks buttons, fills in forms, and checks interfaces right in the browser.
MCP Server for GitHub: Code, Issues, and Pull Requests
How to connect the official GitHub MCP Server to a local AI agent, give it access to code and issues, and not hand over more permissions than you need.
MCP Server for PostgreSQL: Querying a Database Through an AI Agent
How to connect PostgreSQL to a local AI agent through MCP, ask questions about your data in plain language, and restrict access to read-only.
AI for Lawyers With No Data Leak — Locally
How a lawyer can analyze contracts and case materials with a local AI, without uploading documents to an external chat, while keeping full control over the files.