Skip to content

CLI Quickstart¶

This walkthrough uses the current Go CLI command set and output shape.

Step 1: Install¶

curl -fsSL https://runagents-releases.s3.amazonaws.com/cli/install.sh | sh
runagents version

Step 2: Configure¶

runagents config set endpoint https://your-workspace.try.runagents.io/api/v1
runagents config set api-key ra_ws_your_workspace_key
runagents config get

Step 3: Seed Starter Resources¶

runagents starter-kit

This creates starter resources (echo-tool, playground-llm) if missing.

Step 4: Create Agent File¶

Create agent.py:

def handler(request):
    message = request.get("message", "")
    return {"response": f"hello: {message}"}

Step 5: Deploy¶

runagents deploy \
  --name hello-world \
  --file agent.py \
  --tool echo-tool \
  --model openai/gpt-4o-mini

Notes:

runagents deploy maps to POST /deploy on your configured API base URL.
For tool-call authorization, bind policies via console deploy flow, API (policies field), or action plans.

Step 6: Verify Agent¶

runagents agents list
runagents agents get hello-world

Step 7: Inspect Runs¶

runagents runs list --agent hello-world
runagents runs get <run-id>
runagents runs events <run-id>

Step 8: Approvals (When Triggered)¶

If a policy rule returns approval_required, use:

runagents approvals list
runagents approvals approve <request-id>
# or
runagents approvals reject <request-id>

Useful Commands¶

runagents tools list
runagents tools get echo-tool
runagents models list
runagents context export -o json

Next Steps¶