Osprey Framework Documentation#

An agentic interface and safety harness for safety-critical control systems.

The Osprey Framework is an agentic interface and harness for scientific facilities managing complex technical infrastructure — particle accelerators, fusion experiments, beamlines, and large telescopes. It wraps a coding agent in an operator-facing safety policy, a hook-based approval chain, and an MCP-server multiplexer, so the agent layer, the underlying LLM, and the compute backend are each replaceable without changing what the operator sees. The current reference implementation is a browser-based operator workstation; other surfaces (control-room consoles, chat clients, headless services) are possible.

Osprey addresses control-specific challenges: semantic addressing across large channel namespaces, protocol-agnostic integration with control stacks (EPICS and Mock ship in-tree; LabVIEW, Tango, and other stacks are supported via custom connectors), intelligent logbook search across facility electronic logbooks, and mandatory human oversight for safety-critical operations.

Osprey system architecture — from operator to facility, with the safety gate and approval workflow in-line.

Osprey system architecture (for a detailed view, see Architecture).#

Documentation Structure#

Getting Started

Install Osprey, create your first project, and deploy a control assistant with a coding agent and MCP servers.

Getting Started
Architecture

Core concepts: agentic orchestration, MCP servers, connectors, human-in-the-loop safety, and the runtime API.

Architecture Overview
How-To Guides

Task-oriented recipes for adding connectors, configuring providers, deploying projects, and customising MCP servers.

How-To Guides
Contributing

Development setup, coding standards, testing guidelines, and the contribution workflow.

Contributing to Osprey
Citation

If you use the Osprey Framework in your research or projects, please cite our paper:

@article{10.1063/5.0306302,
      author = {Hellert, Thorsten and Montenegro, João and Sulc, Antonin},
      title = {Osprey: Production-ready agentic AI for safety-critical control systems},
      journal = {APL Machine Learning},
      volume = {4},
      number = {1},
      pages = {016103},
      year = {2026},
      month = {02},
      doi = {10.1063/5.0306302},
      url = {https://doi.org/10.1063/5.0306302},
}