Raycast Ollama brings Ollama models into Raycast on macOS and Windows, for people who want AI chat and text assistance within their desktop launcher. It connects to Ollama on your own machine or a remote server you choose. The extension is open source under the MIT license, and local inference doesn't require an Ollama API key.
Saved conversations support multiple turns, with separate model choices for chat, image understanding and tool use. You can bring selected text or clipboard content into a conversation, or add the current browser tab through the Raycast browser extension. Vision-capable models can describe JPEG and PNG images and extract their text.
The focused commands cover grammar fixes, rewriting, translation, website summaries and code explanations. A single response can become an ongoing chat. Custom commands pair your own prompts with a chosen model and can include text selections, browser content or images.
Model management sits in Raycast too: you can download, update and delete models, inspect their capabilities, and load or unload them from memory. One list collects models across your configured Ollama servers.
For tasks that need external tools, chat supports MCP tools when the selected model supports tool calling. Optional web search and web fetch use Ollama's hosted services and require an Ollama account API key; the extension also exposes those tools to Raycast AI. Local model requests go to your local Ollama instance, while remote inference sends them to the selected server.
Claim this page and we'll verify you by hand. Raycast Ollama gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Raycast Ollama?Promote it
Something wrong or outdated on this page?
2KUpdated 6 months agoAGPL-3.0
macOS · Windows · Linux#Code execution#LM Studio integration#MCP
Witsy is an AGPL-3.0 desktop AI assistant for macOS, Windows and Linux that connects MCP tools to local and cloud models. It's for people who want document chat, writing help and voice features in one app, with a choice of where their models run.
boltai.comChat With Your Documents
macOS#Code execution#Human approval#LM Studio integration
kerlig.comChat With Your Documents
macOS#LM Studio integration#MCP#Multimodal input
mindmac.appDesktop Chat Apps
macOS#llama.cpp backend#LM Studio integration#MLX
37.3KUpdated 24 hours agoAGPL-3.0
macOS · Windows · Docker · Web#Batch processing#Hugging Face integration#MCP
796Updated 2 weeks agoMIT
macOS · Windows · Linux#llama.cpp backend#LM Studio integration#Multilingual
BoltAI is a native Mac app for people who want local LLMs and cloud AI services in the same workspace. It runs on Intel and Apple Silicon Macs and suits coding, writing, research and document analysis. The interface uses SwiftUI and AppKit.
Kerlig is a paid AI writing assistant for Mac that works with text in the apps you already use. It's aimed at people writing client emails, Slack replies and Jira tickets who want help editing and drafting without moving everything into a browser chat. It runs on Apple Silicon and Intel Macs with macOS 12 or later.
MindMac is a native macOS AI chat client for people who want to use local LLMs and cloud services in the same app. Its inline mode lets you ask questions or generate text inside Notes, Mail and browsers without switching to a chat window. It runs on Intel and Apple Silicon Macs with macOS 13 or newer.
PDFMathTranslate translates scientific PDFs while keeping their page layout, formulas, charts, contents pages and annotations. It's for researchers, students and others who need to read papers in another language without losing the relationship between the text and its figures. It produces both translated PDFs and bilingual documents for comparison with the original.
Interpreter reads Japanese text from game windows and displays English translations over your screen. It's built for people playing Japanese retro games, with MeikiOCR tuned for game text and pixel fonts. The default OCR and Sugoi V4 translation models run locally, so text stays on your computer and no internet connection is needed after setup. It's open source under the MIT license, with support for Windows, macOS and Linux.