Skip to main content
An agent in LabFrame is not a stateless chatbot. Each agent has:
  • A persistent cloud workspace — a full Linux VM with files, packages, and tools
  • Conversation history across multiple projects
  • A configurable system prompt that shapes its behavior
  • Model selection — choose which AI model powers it

​
Creating an agent

Click + New Agent in the sidebar. You will see a modal with two fields:
FieldDescription
Agent nameA display name (e.g., “Research Assistant”, “CSCI 564 Helper”)
Machine typeThe VM profile for the agent’s workspace
After you click Create, LabFrame provisions a dedicated cloud VM. The sidebar shows status updates while the VM starts. When the green dot appears, the agent is ready.

​
Projects

Each agent can have multiple projects — separate conversations, each with its own chat history and optional workspace scope. To create a new project, click the + icon next to the agent name in the sidebar. You can give the project a name, optionally upload starter files, and invite collaborators. Projects keep different tasks organized. A single “Research Assistant” agent might have one project for a literature review and another for data analysis, each with their own conversation thread.

​
Renaming and deleting

Hover over an agent in the sidebar and click the three-dot menu to rename or delete it. Only the agent owner can rename. Deleting an agent also deletes its workspace and all projects. You can also rename projects from the same three-dot menu on each project entry.

​
System prompts

The system prompt tells the agent how to behave. You can set it when creating the agent or edit it later. For example:
You are a research assistant for a materials science lab. When asked to review a paper, produce a structured summary with sections for methodology, key findings, limitations, and relevance to our lithium-ion battery degradation project.
Agents with clear, specific system prompts produce better results.

​
Models

Use the model picker at the bottom of the chat input to switch models. Available options include:
  • Opus 4.6 — most capable, best for complex multi-step tasks
  • Sonnet 4.6 — fast and capable, good for most tasks
  • GPT 5.4 — OpenAI model, strong at coding and structured output
You can switch models between messages. The agent keeps the same workspace and conversation regardless of which model you use.

​
Agent states

The colored dot next to the agent name in the sidebar indicates its current state:
IndicatorMeaning
Green dotSandbox ready — the agent can respond immediately
Yellow dotSandbox starting — the VM is booting
Gray dotAgent asleep — the VM is suspended to save resources
Red dotSandbox error — something went wrong with the VM
If your agent is asleep, it wakes automatically when you send a message. You can also click Wake Agent in the chat area to wake it manually.