Skip to main content
This domain is for sale. Contact Snagged to learn more.
OP

OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored by Agentic.ai on our published 36-point rubric. Rubric and rules by David Kooi, Skylark Creations. See full rubric → Last re-evaluated 8 November 2026.

See pricing ↓

Visit OpenHands

Is this your tool? Claim this listing to manage your content and analytics.

How it decides

What it decides by itself, and when it asks you

Mapped from the code in OpenHands/software-agent-sdk.

This card covers the OpenHands agent SDK, the library that the OpenHands command-line tool and OpenHands Cloud are built on, and not the OpenHands app or its screens. On its default settings the SDK never stops to ask for your approval, even after an app gives the agent tools to run commands and edit files. An app built on it can turn approvals on, but deciding when the work is done and what to remember stays with plain code and AI models.

Read the full map: the judgments it shows and who holds each one

Three problems the map found

  1. A new message can count as approval

    Fix proposed

    When the approval policy calls for it, the agent pauses before an action until the app approves or rejects it. If you send a new message instead, and the app then runs the conversation again without rejecting, the waiting action is attempted as if you had approved it. A message saying "wait, not that" does not by itself cancel the action.

  2. The goal judge can read "false" as done

    Fix proposed

    With the goal feature, a judge model is asked for a short structured reply that includes a "complete" field. The code turns that field into yes or no with a Python conversion (bool) that counts any non-empty text as yes, including the word "false". So if the judge writes "false" as text in that field, the goal is marked complete.

  3. A secret inside a tool request is recorded unmasked

    Reported

    You can register secrets, such as service access keys, so they are masked in text replies that contain no request to use a tool. When the model puts a registered secret into a request to use a tool, such as a shell command, the details of that request are written to the conversation record without masking, and when the model gives no summary of the request, the automatic summary repeats them. Anyone who can read that record can read the key.

Read the full map

Not checked: This card was taken from the published map of the OpenHands agent SDK at one commit; it did not look at the OpenHands app or its screens, at the hosted services the SDK can call, or at code outside the map's folders, and no OpenHands code was run to make it.

Mapped by agent-ops-patterns (open source) from OpenHands/software-agent-sdk at commit aae9c43. Mapped Oct 6, 2026. Last updated Nov 10, 2026.

Recent activity

What's happened with OpenHands lately

  • Evaluated
    Initial agenticness evaluation: 18/32

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about OpenHands

Get answers based on OpenHands's actual documentation

Try asking:

About

About

OpenHands is an open-source autonomous coding agent led by Robert Brennan, Xingyao Wang, and the OpenHands community. The agent plans, generates Python actions via the CodeAct pattern, executes them across browser, terminal, and file tools, and...

Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Nov 8, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Open Source: Free
  • Teams: $500/month, 10 users included (+$50/month per seat)
  • Enterprise: Custom pricing

Checked 2026-11-19 on the vendor's pricing page.

Details
AddedMay 22, 2026
RefreshedNovember 17, 2026
Quick Facts
Open sourceYes
Pricing modelPlatform fee + usage
Sources
Last updated November 20, 2026
Newsletter

Join the Agentic AI Insider.

I use AI for:
Similar tools

Related Tools