AgentDock is an open-source framework designed to simplify the development, orchestration, and deployment of AI agents capable of executing complex automated workflows. The platform provides a backend-first architecture that allows developers to create sophisticated agent systems while maintaining flexibility in model providers and infrastructure choices. It consists of two main components: a core framework that handles agent logic and orchestration, and a reference client application that demonstrates how agents can be deployed and interacted with through a web interface. Built primarily with TypeScript and modern web technologies, the framework emphasizes extensibility and predictable behavior through configurable determinism. AgentDock also supports integration with multiple large language model providers, enabling developers to combine reasoning models, APIs, and external tools within a unified automation pipeline.
Features
- Framework for building and deploying AI agents and workflows
- Provider-agnostic integration with multiple LLM services
- Modular architecture enabling extensible agent behavior
- Reference client application built with Next.js
- Configurable determinism for predictable agent execution
- Infrastructure for multi-agent orchestration and automation