Generalist AI software developer operating in a sandboxed execution environment.
Documents the primary agent in OpenHands (arXiv 2407.16741, accepted ICLR 2025; formerly OpenDevin). A generalist agent that interacts with a sandboxed environment using tools for file editing, web browsing, and code execution. Open-source, 188+ contributors. The platform supports multiple runtimes: local Docker, cloud, and modal. Evaluated on SWE-Bench and WebArena task suites. Source: arXiv paper (ICLR 2025 accepted).
Performance is measured where the work happens — at the team level. OpenHands Agent runs inside 🙌 OpenHands (OpenDevin), whose windowed metrics are the honest unit of account.
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this agent.
Sign in