A GTK4/Adwaita desktop client for Ollama that lets you manage and chat with local models, with optional third-party cloud APIs.
sheshbabu/Chital
A native macOS app for chatting with local LLMs served by Ollama, with multiple threads, markdown rendering and vision image support.
Open-source alternative to:ChatGPT
- Stars
- 417
- Forks
- 23
- Open issues
- 2
- Last commit
- 21 days ago
What is it?
Chital is a native macOS client for chatting with models hosted through Ollama. It runs locally as a SwiftUI app, so you can keep multiple concurrent chat threads, switch models mid-conversation, and work with the same local models you already have installed.
The app covers the common chat workflow: markdown rendering for formatted replies, image attachments for vision models, a reasoning display and thinking level picker for thinking models, and auto-generated thread titles. Threads can be searched, renamed, branched, exported as Markdown, and messages can be edited, resent or retried. Keyboard shortcuts cover new threads, stopping generation and navigating between threads.
Chital requires macOS 14 Sonoma or later and a running Ollama installation with at least one model downloaded. Settings include the default model, Ollama base URL, context length, system prompt, font size and the title summarization prompt.
Key features
- 01Multiple concurrent chat threads with search, rename and branching
- 02Model switching during conversations
- 03Image attachments and paste support for vision models
- 04Reasoning display and thinking level picker for thinking models
- 05Markdown rendering with copy buttons on replies and code blocks
- 06Export threads as Markdown
Use cases
- Chatting privately with models running on your own Mac via Ollama
- Comparing answers from different local models within the same workflow
- Asking questions about images with local vision models
- Archiving or sharing conversations as Markdown files
Quick start
- 1
Install Ollama and download at least one model from the Ollama library
- 2
Download Chital from the GitHub releases page
- 3
Move Chital.app into the Applications folder
- 4
Allow the app in System Settings > Privacy & Security by clicking Open Anyway
Things to know
- Runs only on macOS 14 Sonoma or later.
- Requires Ollama to be installed separately and at least one model downloaded.
- The author states it is a personal project and may not review pull requests or respond to issues.
In collections
Topics
FAQ
- What is Chital?
- A native macOS app for chatting with local LLMs served by Ollama, with multiple threads, markdown rendering and vision image support. Chital is a native macOS client for chatting with models hosted through Ollama. It runs locally as a SwiftUI app, so you can keep multiple concurrent chat threads, switch models mid-conversation, and work with the same local models you already have installed.
- Is Chital free to use? What license does it have?
- Chital has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is Chital still maintained?
- Actively maintained. The last commit to Chital was on Oct 18, 2026.
- What can I use Chital for?
- Chatting privately with models running on your own Mac via Ollama Comparing answers from different local models within the same workflow Asking questions about images with local vision models Archiving or sharing conversations as Markdown files
- How do I install Chital?
- Install Ollama and download at least one model from the Ollama library Download Chital from the GitHub releases page Move Chital.app into the Applications folder Allow the app in System Settings > Privacy & Security by clicking Open Anyway
- Where can I get Chital?
- The source code and installation instructions are on GitHub: https://github.com/sheshbabu/Chital
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A free macOS menu bar app that generates, builds, and saves small native SwiftUI Mac apps from text prompts using AI.
Cross-platform AI chat client that connects LLMs such as OpenAI, Claude, Ollama and DeepSeek to MCP servers.
A native macOS AI workspace in SwiftUI that runs locally, with chat, agent tools, email, calendar, memory and document editing.
A native macOS Swift app for chatting with Amazon Bedrock models, with document, image, and local tool support.
A locally deployed desktop AI chat client with MCP tool support, offering private conversation storage and connections to your own or third-party model APIs.