workflowstacks
mcp-server

osaurus: Run AI Agents Offline

Own AI models with osaurus, for founders needing autonomous AI on macOS, with 6.0k+ GitHub stars
advancedโฑ 1-2 hours๐Ÿ’ต Free (self-hosted)
7,677 stars449 forksSwiftHealth Score 9/10Updated 8/23/2026100% free ยท open source
What it is

Run AI agents on your own computer without an internet connection.

What you can make with it

Your own custom AI automations, like sending welcome emails to new customers when they sign up on your website.

How it helps

It helps you keep your AI work independent of the cloud, and fully under your control.

Real use case example

"A founder wants to create a welcome email sequence when a new customer signs up on their website. They first write a function to listen for new signups, then use osaurus to interact with the AI to generate a personalized email. Finally, they use osaurus to send the email to the new customer."

If you're new

You're a good fit if you're new to AI development, and just want to understand how to use AI in small projects.

If you're senior

This skill is for senior engineers and founders who need a reliable, customizable way to run AI agents on macOS without cloud dependencies.

Common confusion cleared up

osaurus does not require an internet connection to run, but still uses online LLMs, which may introduce some latency.

Best inside these AI tools
Claude DesktopClaude Code
Pairs with
Claude DesktopClaude CodeStripe webhookNotion database
Why we list it on WorkflowStacks: It's a free and open-source option that fits well within the MCP-server category, allowing for maximum flexibility.
What it does

Osaurus allows founders to own and run autonomous AI models directly on their macOS, with persistent memory and cryptographic identity, all while being fully offline.

Install / run
git clone https://github.com/osaurus-ai/osaurus.git && cd osaurus
When to use it
  • โ€ขYou need to deploy AI models on macOS devices without relying on cloud services.
  • โ€ขYour application requires autonomous AI execution with persistent memory.
  • โ€ขYou want a fully offline, open-source solution for running AI agents on macOS.
Quick start
  1. 1Clone the osaurus repository and navigate into the cloned directory.
  2. 2Build the osaurus project using Swift, following the instructions in the README.
  3. 3Configure your AI model and its parameters according to your needs.
  4. 4Start the osaurus server to begin running your autonomous AI model.
  5. 5Use the osaurus CLI to interact with and manage your AI agents.
Ready-to-paste prompt
Run `osaurus start --model my_model` to start an autonomous AI model named 'my_model' with osaurus.
Heads up: Ensure you have Xcode and the Swift compiler installed on your macOS, as osaurus is built in Swift and requires these tools to build and run.
Saves to your device

Topics

anthropic
apple-foundation-models
apple-intelligence
apple-neural-engine
llm
mcp
mcp-server
mlx
openai
swift
What's inside โ€” free to inspect
No purchase needed

Read the entire source before you build โ€” unlike paid marketplaces that hide it behind a buy button.

10
top-level files
13
folders
93.4M
source size
MIT
license
Key files
AGENTS.md
README.md
File tree
.cursor/
.github/
App/
assets/
docs/
helpers/
osaurus.xcworkspace/
Packages/
reports/
results/
sample-knowledge/
sandbox/
scripts/
.gitattributes
.gitignore
.swift-format
.swiftlint.yml
AGENTS.md
COMMUNITY_EVALS.md
lefthook.yml
LICENSE
Makefile
README.md
Quick Actions
Details
Creator
osaurus-ai
Language
Swift
Category
mcp-server
Published
8/17/2025

Are you the creator of this tool? Claim your listing โ†’ and earn 85% of every sale.