# dinoki-ai/osaurus

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/dinoki-ai-osaurus).**

3,531 stars · 139 forks · Swift · mit

## Links

- GitHub: https://github.com/dinoki-ai/osaurus
- Homepage: https://osaurus.ai
- awesome-repositories: https://awesome-repositories.com/repository/dinoki-ai-osaurus.md

## Topics

`anthropic` `apple-foundation-models` `apple-intelligence` `apple-neural-engine` `llm` `mcp` `mcp-server` `mlx` `openai` `swift`

## Description

Osaurus is a local AI workflow engine and LLM agent orchestration framework designed for private execution on local hardware. It functions as a desktop application automator and a voice-controlled AI interface, enabling the development of autonomous agents that can write code, execute tools, and operate a computer without keyboard or mouse input.

The system is distinguished by its ability to control native desktop applications via accessibility APIs and manage web interactions through a headless browser automation tool. It supports a local-first execution model and on-premises deployment within private networks to ensure data privacy and offline functionality.

The project covers a broad range of automation capabilities, including codebase task automation, vision and image processing, and the programmatic generation of spreadsheets and presentations. It also includes integrations for web search, third-party messaging, and a plugin architecture to extend agent capabilities.

## Tags

### Artificial Intelligence & ML

- [Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-orchestration-frameworks.md) — Provides a framework for building autonomous agents that write code and use external tools for complex tasks.
- [Local AI Execution Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/local-ai-execution-environments.md) — Provides a local-first execution environment for AI agents and models to ensure data privacy and offline functionality. ([source](https://osaurus.ai/))
- [AI Agent Development](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-development.md) — Includes a system for creating and testing specialized AI assistants that evolve through user interaction. ([source](https://osaurus.ai/))
- [AI Workflow Automation](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-automation.md) — Runs AI models on private hardware to automate tasks and process data without cloud dependency.
- [Autonomous AI Agent Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-ai-agent-frameworks.md) — Provides a functional framework for building self-directed agents that can autonomously write code and execute tools. ([source](https://osaurus.ai))
- [Accessibility Tree Desktop Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/desktop-automation-agents/accessibility-tree-desktop-controllers.md) — Controls native desktop applications by querying platform accessibility APIs and injecting input events.
- [Local AI Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/local-ai-runtimes.md) — Ships a local runtime environment designed for running large language models and AI inference tasks on host hardware. ([source](https://osaurus.ai))
- [Local LLM Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-models/local-llm-execution.md) — Runs large language model inference on the host machine to ensure data privacy and offline availability.
- [Private AI Infrastructure](https://awesome-repositories.com/f/artificial-intelligence-ml/private-ai-infrastructure.md) — Provides platforms for hosting and managing AI models and agentic workflows on private servers.
- [Voice Controlled Computing](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-controlled-computing.md) — Enables execution of system-level operations and complex computer tasks via spoken natural language commands.
- [Voice Controlled Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-controlled-interfaces.md) — Provides a hands-free interaction layer for operating AI agents and software development tasks using voice.
- [Agent Plugin Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-plugin-frameworks.md) — Implements a modular architecture for integrating specialized skills and plugins into autonomous agent systems. ([source](https://osaurus.ai/))
- [Agent Capability Extensions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-capability-extensions.md) — Provides a plugin architecture to expand agent capabilities with external modules for file system and browser interactions.
- [Voice Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents.md) — Implements voice-based communication allowing users to operate the system and interact with agents hands-free. ([source](https://osaurus.ai/))
- [Presentation Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/automated-content-generation/presentation-generators.md) — Implements a system to programmatically create and modify presentation files containing structured content and custom themes. ([source](https://osaurus.ai/skills))
- [Image Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/image-processing.md) — Ships a system for analyzing images to detect text and faces or remove backgrounds. ([source](https://osaurus.ai/skills))

### Development Tools & Productivity

- [Headless Browser Automation](https://awesome-repositories.com/f/development-tools-productivity/headless-browser-automation.md) — Implements a controller for interacting with web browsers to perform actions and extract content. ([source](https://osaurus.ai/skills))
- [Automation Task Orchestration](https://awesome-repositories.com/f/development-tools-productivity/automation-task-orchestration.md) — Ships a system to monitor folders and run parallel jobs to automate software development tasks. ([source](https://osaurus.ai))

### DevOps & Infrastructure

- [On-Premise Deployment](https://awesome-repositories.com/f/devops-infrastructure/on-premise-deployment.md) — Supports running AI inference within private networks to ensure data never leaves the local organization. ([source](https://osaurus.ai/enterprise))

### Operating Systems & Systems Programming

- [Desktop Application Automation](https://awesome-repositories.com/f/operating-systems-systems-programming/desktop-environment-frameworks/desktop-environment-components/desktop-applications/desktop-application-automation.md) — Provides capabilities for controlling native desktop applications to manage events and communications via scripts. ([source](https://osaurus.ai/skills))
- [Desktop Automation](https://awesome-repositories.com/f/operating-systems-systems-programming/desktop-environment-frameworks/desktop-environment-components/desktop-automation.md) — Controls native desktop applications via accessibility APIs to automate repetitive user workflows.
- [Accessibility API Wrappers](https://awesome-repositories.com/f/operating-systems-systems-programming/platform-api-access/accessibility-api-wrappers.md) — Implements element-based interactions and smart filtering within the operating system using accessibility APIs. ([source](https://osaurus.ai/skills))

### Business & Productivity Software

- [Spreadsheet Manipulation Libraries](https://awesome-repositories.com/f/business-productivity-software/spreadsheet-manipulation-libraries.md) — Provides programmatic capabilities to read and modify spreadsheet files, including cell data and formulas. ([source](https://osaurus.ai/skills))

### Data & Databases

- [Web Search Grounding](https://awesome-repositories.com/f/data-databases/data-synchronization/real-time/ai-grounding-services/business-context-grounding/web-search-grounding.md) — Retrieves deduplicated web search results to provide real-time grounding data for automated AI tasks. ([source](https://osaurus.ai/skills))

### Programming Languages & Runtimes

- [Dynamic Agent Code Generation](https://awesome-repositories.com/f/programming-languages-runtimes/dynamic-agent-code-generation.md) — Allows agents to dynamically generate and execute code as tools to solve complex autonomous tasks.