CLI command reference

Every command below is also in everruns --help, and an agent running on Everruns types the same words in its shell. Install the CLI and sign in first; see CLI.

Flags every command takes

Flag	Description
--reason <TEXT>	Why you are making this change. Recorded in the changed entity’s history; give one on every command that changes something.
--context-revision <N>	The revision of the entity’s manager notes you read (everruns context get). The change is refused if the notes changed since.
-o, --output <FORMAT>	text (default), json or yaml.
-q, --quiet	Print only the essential identifier, for capturing ids in scripts.

Session and account

Command	What it does
everruns chat	Send a message and stream the response
everruns login	Interactive login (localhost OAuth callback)
everruns logout	Remove stored credentials
everruns status	Show current user and org

Command groups

Group	What it manages
agents	Agent definitions and their configuration
budgets	Spending limits for sessions, agents, users and organizations.
capabilities	Capabilities agents can use, including declarative ones you define.
connections	Your LLM provider API keys
context	Notes managers keep about an entity, read by agents that manage it.
durable	Durable scheduled tasks and their executions.
evals	Evaluation cases, runs, results and scores.
files	Sync files between a local folder and a session
harnesses	Reusable base setups (prompt plus capabilities) agents build on.
health-issues	Operational problems detected in this installation.
history	Recorded changes to entities: list, compare, restore.
images	Uploaded images.
knowledge-bases	Curated collections of knowledge entries.
knowledge-indexes	Searchable indexes synced from external sources.
mcp-servers	Registered MCP servers available to agents and sessions.
memories	Workspace memories in the organization.
models	LLM models available to agents, and organization defaults.
notifications	Your in-app notifications.
observers	Online scoring of live traces.
orgs	Organizations you belong to, and which one is active
payments	Machine payments: wallets, spend policies and attempts.
plugin-marketplaces	Sources of installable plugins.
plugins	Plugins installed in this organization.
providers	LLM providers and their credentials.
reports	Usage and cost reporting: queries, saved reports, catalog.
sandbox-targets	Sandbox providers this deployment offers.
sandboxes	Sandboxes across providers: state, history, usage.
sessions	Running and archived sessions, their state and participants
skills	Skill packages and their content.
system	Server status.
tasks	Background tasks across every session in the organization.
user	Your own account settings.
users	People in the current organization.
virtual-users	Runtime accounts for consumers or services.
workspaces	Durable working areas holding the files agents work on.