CLI
The everruns CLI is a command-line client for the Everruns API. It covers the same surface as the SDK — agents, sessions, messages, capabilities — and is designed to compose well with shell pipelines.
This page covers installation, configuration, and the command surface. For scripting patterns and jq examples, see Automate with the CLI.
Install
Section titled “Install”Homebrew (macOS / Linux)
Section titled “Homebrew (macOS / Linux)”brew tap everruns/tapbrew install everrunsFrom the Git repository:
cargo install --git https://github.com/everruns/everruns everruns-cliOr clone and build:
git clone https://github.com/everruns/everruns.gitcd everrunscargo install --path crates/cliVerify
Section titled “Verify”everruns --versionConfigure
Section titled “Configure”The CLI defaults to the hosted API at https://app.everruns.com/api. Override for local or self-hosted deployments:
# Per commandeverruns --api-url http://localhost:9300/api agents list
# Per shellexport EVERRUNS_API_URL=http://localhost:9300/apiexport EVERRUNS_API_KEY=devCommand surface
Section titled “Command surface”| Group | Subcommands |
|---|---|
agents | create, list, get, update, delete |
sessions | create, list, get, cancel, delete |
capabilities | (list — no subcommand) |
chat | Send a message and stream the response |
Agents
Section titled “Agents”# Inlineeverruns agents create \ --name "my-agent" \ --system-prompt "You are a helpful assistant." \ --tag production
# From a file (TOML, YAML, JSON, or Markdown front matter)everruns agents create -f agent.tomleverruns agents create -f agent.yamleverruns agents create -f agent.mdIf ./agent.toml exists and you don’t pass inline flags, everruns agents create picks it up automatically. The file formats are documented in Define agents as files.
everruns agents listeverruns agents get agt_xxxeverruns agents delete agt_xxxSessions
Section titled “Sessions”everruns sessions create --agent agt_xxxeverruns sessions create --agent agt_xxx --title "Debug session"
# With session-level overrideseverruns sessions create \ --agent agt_xxx \ --harness generic \ --capability 'web_fetch={"timeout":10}' \ --hint setup_connection=true \ --network-allow api.example.com \ --max-iterations 8Also accepts: --locale, repeatable --tag, --system-prompt, --hints-json, repeatable --network-block, repeatable --secret KEY=VALUE, and budget flags.
everruns sessions listeverruns sessions get ses_xxxeverruns chat "Tell me a joke!" --session ses_xxxOptions: --timeout <seconds> (default 300), --no-stream to queue without waiting.
Output formats
Section titled “Output formats”Every command accepts -o / --output:
everruns agents list -o jsoneverruns agents list -o yaml--quiet suppresses headers and prints only the essential identifier — useful for capturing IDs in shell variables.
See also
Section titled “See also”- Automate with the CLI —
jq, quiet mode, scripting patterns. - Define agents as files — file formats for
-f. - SDK — the programmatic equivalent.
Agent composition
Section titled “Agent composition”Discover and manage the plugins, skills, and knowledge bases available to agents:
# Pluginseverruns plugins listeverruns plugins get <plugin-id>everruns plugins install <marketplace-id> <plugin-name>everruns plugins uninstall <plugin-id>
# Skillseverruns skills listeverruns skills get <skill-id>everruns skills create ./SKILL.mdeverruns skills delete <skill-id>
# Knowledge baseseverruns knowledge-bases listeverruns knowledge-bases get <knowledge-base-id>everruns knowledge-bases create "Product docs" --description "Published product documentation"everruns knowledge-bases delete <knowledge-base-id>Resource identifiers are URL-encoded before requests are sent. Use the global --output json or --output yaml option for machine-readable discovery output.
Skill creation reads the supplied Markdown file and sends its contents to Everruns. Knowledge document ingestion and assigning composition resources to an agent are not yet exposed by the CLI.