osaurus-ai/osaurus

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 19 minutes ago
Added to GitGenius on September 8th, 2026
Created on August 17th, 2025
Open Issues & Pull Requests: 207 (+2)
GitHub issues: Enabled
Number of forks: 461
Total Stargazers: 7,814 (+0)
Total Subscribers: 35 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 8.2 hours
Mean response time: 5.9 days
90th percentile: 10.8 days
Tracked items: 385

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 28% of tracked open issues have had no activity in three months. Only 11% of issues opened in the past year have been closed. Three people close 87% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 73
New in 7 days: 19
Closed in 7 days: 11
Avg open age: 87 days
Stale 30+ days: 42
Stale 90+ days: 15

Recent activity

Opened in 7 days: 15
Closed in 7 days: 7
Comments in 7 days: 0
Events in 7 days: 9

Top labels

  • bug (225)
  • enhancement (135)
  • good first issue (8)

Detailed Description

Osaurus is a native macOS application that harnesses AI agents with persistent memory, autonomous execution, and cryptographic identity, built in Swift for Apple Silicon and fully offline-capable.

The tool addresses the problem of AI capabilities being fragmented across cloud services by consolidating the infrastructure layer—context, memory, tools, and identity—on the user's own machine. It sits between the user and any language model, whether local or cloud-based, providing continuity through agent memory and autonomous execution. The approach keeps user data local by default while remaining flexible enough to connect to cloud providers when additional computational power is needed. The application is built natively in Swift for Apple Silicon without relying on Electron, and it supports multiple model sources including OpenAI, Anthropic, Ollama, and Apple Foundation Models.

Developers should choose this tool if they want to build AI agents that maintain state and execute autonomously while keeping sensitive data and personal context on their own hardware. It suits projects where privacy and data ownership are priorities, or where offline capability is essential. The tool is particularly well-suited for macOS users with Apple Silicon who want to avoid cloud dependencies for their AI infrastructure. Those evaluating adoption should note that the project emphasizes the distinction between interchangeable inference models and the irreplaceable harness layer that provides memory and continuity—the core value proposition is owning the latter rather than relying on external services for it.

The project maintains an active development posture with regular engagement across multiple community channels and welcomes pull requests. The codebase is organized to support extensibility through a plugin registry for tools and models. Development activity shows responsiveness to the open-source community with documentation and model resources actively maintained alongside the core application.