OpenHands

In this catalog it is the Coding Agents option when you need to edit repositories and ship engineering changes. Keep OpenHands on the observe/propose side of the loop: useful signals and drafts, with human or policy authority still required before anything irreversible runs.

OpenHands is an autonomous SWE agent operating a sandboxed computer (shell, browser, editor) toward engineering goals.

1. Launch a sandboxed workspace for the task.
2. Agent plans and uses shell/browser/editor tools.
3. Iterate on failures inside the sandbox.
4. Hand back patches, PRs, or artifacts.

Related: swe-agent · e2b · topics/06-self-coding

• Use when: OpenHands (formerly OpenDevin) is an open-core autonomous software engineering agent that operates a sandboxed computer — shell, browser, editor — aiming to complete engineering tasks end-to-end matches the bottleneck and you specifically need to edit repositories and ship engineering changes.
• Skip when: another pack already covers the need with less ops surface, or OpenHands would become a second place people retype truth.
• Prefer instead: compare SWE-agent, e2b before locking the cell.

• Ops: confirm license, hosting, and release cadence for OpenHands (OpenHands/OpenHands) before relying on it in a live corridor.
• Integration: bad credentials, scopes, or schema drift produce empty retrievals or runaway tool/model spend without an obvious UI alarm.
• Scope: Coding Agents components support agents; they are not the company ledger or the approval authority.