accomplish-ai/openwork
Openwork
Openwork is an AI agent for desktop automation that uses large language models to execute browser tasks, manage local files, and automate desktop workflows. It operates on a local-first execution model, translating natural language prompts into sequences of tool calls to perform digital chores.
The system functions as a framework for defining and saving repeatable sequences of actions as reusable skills. It integrates large language models with third-party services and local APIs to synchronize data and share files.
The agent includes capabilities for headless browser automation to conduct research and complete online forms, as well as tools for sorting, renaming, and organizing local disk files based on content rules. To maintain data privacy, the system uses directory-based permission scoping to restrict file system access to a predefined list of allowed folders.
Users configure the intelligence of the agent by connecting to model providers via API keys or local hosting.
Features
- Desktop Automation - Automates repetitive digital chores and tasks directly within the local desktop operating system environment.
- Agent Skill Definitions - Allows the definition of reusable configurations that store successful action sequences as named skills.
- Agent Skill Orchestration - Manages and coordinates the invocation of modular tools and saved skill sequences within agentic workflows.
- AI Agent Tool Integrations - Connects AI models to external software and local APIs to execute functional tasks and synchronize data.
- AI Agent Skills - Provides a framework for defining reusable instructions and capabilities for autonomous agents to perform structured tasks.
- LLM Tooling Integrations - Provides connectors and interfaces that allow language models to access external data and execute software tools.
- Desktop AI Agents - An intelligent agent that interacts with local software, desktop environments, and system-level APIs to automate workflows.
- LLM Orchestration - Uses large language models to orchestrate the translation of natural language prompts into executable tool calls.
- Headless Browser Automation - Includes tools for programmatically controlling browser engines to perform web navigation and data extraction.
- Third-Party Service Integrations - Implements libraries for connecting the system to external APIs and cloud services for data synchronization.
- Skill Definitions - Provides a system for saving repeatable workflows as structured skill definitions to trigger specific action sequences.
- External Tool Integrations - Provides interfaces that connect the AI agent to third-party tools and data sources to automate external tasks.
- Local-First Architectures - Employs a local-first architecture to manage files and native operating system workflows directly on the user's desktop.
- Model Provider Configurations - Provides settings for managing external AI model providers, API keys, and local hosting connections.
- Automated File Organizers - Organizes and manipulates local files based on content rules while respecting directory-level privacy restrictions.
- Browser-Based Workflows - Automates web-based tasks such as conducting research and completing online forms via browser interaction.
- File System Permissions - Implements security controls that restrict file system access to a predefined list of allowed local folders.
- AI Agents - Multi-agent research team with trust-gated verification and collaboration.
