xpander agent namespace covers the full agent lifecycle plus graph editing, agentic-tool discovery, and NeMo model-config sync. Most lifecycle commands also exist as top-level shortcuts (xpander deploy ≡ xpander agent deploy).
[agent] is omitted, most commands show an interactive selection list of your agents. Use --no-interactive to fail instead of prompting.
Discovery
xpander agent list
List all agents in your organization, sorted by creation date (newest first).
xpander agent list-json
Same as agent list --json, kept as a separate command for backwards compatibility.
xpander agent get <agent> (alias g)
Get details for a single agent.
xpander agent interactive
Drop into the interactive agent management TUI: list, pick, edit, delete, invoke without typing every command.
Control plane (CRUD)
xpander agent new (alias n)
Create a new agent in the xpander.ai cloud.
Without flags, the command runs an interactive wizard. Pass
--name, --framework, and --folder together to run non-interactively in CI.
xpander agent update
Update an existing agent’s metadata.
xpander agent edit [agent] (alias o) / xpander agent open [agent]
Open the agent’s configuration page in your browser. edit and open are equivalent.
xpander agent delete [agent] (alias del)
Permanently delete an agent.
Local development
xpander agent init [agent-id] (alias i)
Download the agent’s framework files into the current directory.
Files written:
Dockerfilerequirements.txtxpander_handler.py.env
xpander_config.json, agent_instructions.json, …).
The base templates can be inspected via xpander agent templates (below).
xpander agent templates
Manage and discover agent templates.
xpander agent dev [agent]
Run the agent locally for testing.
Starts the agent in your local Python environment using the
.env file in the working directory. Use this to iterate on xpander_handler.py without redeploying.
Cloud deployment
xpander agent deploy [agent] (alias d)
Build and deploy the agent’s Docker image to xpander.ai’s cloud.
What happens:
- Uploads your local agent code.
- Builds a Docker image.
- Deploys and runs the container.
- Increments the agent’s deployed version.
Dockerfilerequirements.txtxpander_handler.py.env
xpander agent logs [agent] (alias l)
Stream real-time logs from a deployed container.
Press
Ctrl+C to detach.
xpander agent restart [agent]
Restart the deployed container without rebuilding.
xpander agent stop [agent]
Stop a running container.
Invocation (testing)
xpander agent invoke [agent] [message...]
Test a deployed (or local) agent and print the response.
When run inside an agent directory with a
.env file, xpander agent invoke "hi" infers the agent from .env and treats "hi" as the message.
The CLI caches the agent list for 24 hours, so name lookups stay fast across invocations.
Graph
An agent’s operation graph is the directed graph of connector operations the agent is allowed to call, along with the allowed transitions between them. The platform uses it both to constrain tool selection during a run and to render the visual workflow shown in the dashboard. Most users edit graphs through the dashboard; the CLI commands here are useful for scripting and CI.xpander agent graph create
Create an operation graph for an agent.
xpander agent graph View
View the graph structure of an agent.
The
View subcommand is capitalized in the CLI: type it exactly as xpander agent graph View.Tools
The xpander platform organizes tools as interfaces (a connector or service: Slack, GitHub, Salesforce, etc.) and operations (the individual API calls each interface exposes:slack.send_message, github.create_issue, and so on). Use these commands to discover interface IDs and the operations they offer when you’re building agent configs by hand or scripting against the API.
xpander agent tools interfaces
List available agentic interfaces (categories of connectors and tools your agents can use).
xpander agent tools operations
List the operations exposed by a specific interface.
NeMo
NeMo support lives at the top level (not underagent), but it’s agent-config-related:
xpander nemo pull
Pull an agent’s model configuration into a local NeMo config file.
xpander nemo push
Push your local NeMo config changes back to the agent.
Common patterns
Deploy then test
Iterate locally before deploying
Non-interactive for CI
--confirm flag skips destructive-action prompts during deployment. Combine with --no-interactive (global) to fail fast if any prompt would otherwise appear.
