DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to chat with local models through Ollama with Chatbox

Point Chatbox at Ollama to use open models like Mistral or Mixtral with a polished desktop UI.

Short answer: Install Chatbox from the releases page; then make sure Ollama is running with a model such as Mistral or Mixtral; choose Ollama as the provider in Chatbox settings. All steps.

Who it is forA privacy-minded user who already runs Ollama but wants a friendlier chat window.

The problemOllama's terminal is fine for testing but awkward for daily chats and saving conversations.

The outcomeA desktop chat app talking to local models, with your data kept on your device.

What you need first

  • Windows 10 x64, macOS 11 or later, or Ubuntu 20.04+ / AppImage distros
  • An API key for a cloud provider, or Ollama for local models
  • To build from source: Node.js and pnpm

Steps

  1. Install Chatbox from the releases page
  2. Make sure Ollama is running with a model such as Mistral or Mixtral
  3. Choose Ollama as the provider in Chatbox settings
  4. Chat as normal; Markdown, LaTeX and code highlighting render in replies

Prompt for your agent

Configure chatboxai/chatbox to use my local Ollama models and set <model> as the default. Confirm a test chat works with no cloud provider configured.

Caveat. Local model quality and speed depend on your hardware and the model you pull in Ollama.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for chatboxai/chatbox and "Chat with local models through Ollama"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer