AI product

OpenHands Agent Canvas

OpenHands Agent Canvas is a workflow and runtime interface for running coding agents across different execution environments. It can use Claude Code, Codex, or the OpenHands harness and move agent work between local execution, Docker containers, remote virtual machines, and Kubernetes, supporting both interactive development and event-triggered background workflows.

Visit site Mentioned in 1 video ↓

Overview

The OpenHands platform connects triggers from sources such as GitHub, Slack, Jira, Linear, and schedules to agent workflows that plan, execute, validate, ship, and monitor engineering changes. The page presents Agent Canvas as a preview within OpenHands, with automations for tasks such as pull-request review, issue triage, CI-failure remediation, security work, and documentation updates.

What OpenHands Agent Canvas is used for

1 use taken from transcripts — each links to the moment in the video.

  • A tool for choosing the right sandbox environment for a coding agent. It can run with Claude Code, CodeX, or the OpenHands harness, and with a quick toggle it moves the agent between running locally with skipped permissions, in Docker containers, in a remote VM, or in Kubernetes — supporting both quick local iterative development and autonomous background runs triggered by events.

Videos mentioning OpenHands Agent Canvas

1 in the library.