AgentsModelsSkillsMemoryEvaluationsGuidesSubmit a resource
Agents open-source 71,464 stars

OpenHands

Open-source AI software development agent for coding tasks, repositories, and developer workflows.

OpenHands is an open-source AI-driven development project for letting agents work on software tasks, inspect repositories, modify code, and support developer workflows.

terminal
$ git clone https://github.com/OpenHands/OpenHands.git
# Start with the official repository and follow the docs for the current Docker or runtime setup.
Open repository Read docs View sources
Decision signals
Open sourceSelf-hostedDocker
Tags
workflow orchestrationtool callingopen sourceself hosteddockerself hosted aideveloper workflow

Action profile

What can OpenHands actually do?

Agent profiles are most useful when they explain the surfaces an agent can act on, how those actions are supervised, and what a safe first workflow looks like.

OpenHands is a practical open-source reference point for the coding-agent category. It is not just a chat interface for code explanations; it is aimed at agents that work inside software development workflows.

OpenHands is an open agent resource to evaluate by action surface: what software it can operate, which tools or browser steps it touches, and how much supervision it needs before it can run real work.

Fit check

Where it fits in an agent workflow

Good fit if

  • Developers evaluating open-source coding agents
  • Teams that want an inspectable alternative to closed coding-agent products
  • Researchers studying repository-level task automation and software engineering agents

Not a fit if

  • Non-technical users looking for a general personal assistant
  • Teams unwilling to review sandboxing and repository permissions before using coding agents

Action surface

What to inspect before using it

Action surface

Browser, terminal, code, tools, APIs, files, or workflow steps it can operate.

This defines the risk boundary.
Supervision

Logs, review points, approvals, and whether a human can pause or replay actions.

Action agents need auditability.
Failure mode

What happens when a page changes, a tool fails, or the agent reaches uncertainty.

Recovery behavior matters more than demos.

First test

How to evaluate it before committing

Run one narrow action in a sandbox, then inspect permissions, logs, recovery behavior, and every tool or browser step.

Keep the first test small enough that you can inspect the source, understand the permissions, and compare the result with nearby OpenAgent resources.

Workflows

Best workflows to test first

Issue triage and code changes

Use OpenHands as a candidate when an agent needs to inspect a repository and propose implementation changes.

Coding-agent research

Study how an open coding agent handles tasks, tools, sandboxing, and developer feedback.

Self-hosted developer automation

Evaluate whether parts of your coding workflow can run in an inspectable open-source environment.

Compare

Compare by action boundary

Choose OpenHands for software development workflows vs browser automation agents

browser-use and OpenClaw are stronger for web workflows. OpenHands is more directly focused on repositories, code tasks, and software engineering.

Resource Category License Stars
OpenAI Agents SDK Agents MIT 26,833
Aider Agents Apache-2.0 45,400
AutoGen Agents CC-BY-4.0 58,400

FAQ

Adoption questions

What should I check before using OpenHands?

Start with one safe workflow for OpenHands. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

Is OpenHands open source?

OpenHands is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Who should evaluate OpenHands?

OpenHands is most worth evaluating for developers evaluating open-source coding agents.

Is OpenHands only for developers?

Yes, its clearest fit is software development and repository workflows.

Should I use OpenHands on production code immediately?

No. Start with a sandbox repository and review every change before moving to important code.

Related

More agents to compare