# OpenHands — Open-source software engineering agent with GUI, CLI, SDK and an enterprise control plane.

> Source: The Agents Index — https://theagentsindex.com/openhands (structured, researched, re-verified)
> Facts last verified: 2026-09-21

OpenHands is an open-source platform for software engineering agents, offering a browser canvas, terminal CLI, Python SDK and agent server. It runs locally, on OpenHands Cloud, or self-hosted in a customer's own Kubernetes cluster.

| Fact | Value |
| --- | --- |
| Website | https://www.openhands.dev |
| Price | from $0.10/1m input tokens pay-as-you-go |
| Free tier | Yes |

Two standing free plans. Open Source is free and local with your own LLM key. The hosted Individual plan is free for 1 user and capped at 10 Max Daily Conversations, with model tokens billed pay-as-you-go at provider cost unless you bring your own key. Enterprise additionally offers a 30-day trial.

## What it does

**Writes code** · Yes — Core purpose: the agent authors code from a natural-language task across GUI, CLI and SDK surfaces, including scripted headless runs.

> Build AI agents that write software. A clean, modular SDK with production-ready tools.
> — https://docs.openhands.dev/llms.txt · Software Agent SDK section, 'Software Agent SDK' entry description

**Debugs and fixes** · Yes — Documented for CI failure remediation and incident work: it investigates failures, finds likely causes and implements the fix.

> Investigate failed builds and tests, identify likely causes, and propose or implement fixes.
> — https://www.openhands.dev/services · One platform for the agentic SDLC section, 'CI failure remediation' card

**Writes tests** · Yes — Test generation and coverage maintenance is named as a supported workflow, not only code authoring, on the services page.

> Generate tests, expand coverage, and keep test suites aligned as the codebase changes.
> — https://www.openhands.dev/services · One platform for the agentic SDLC section, 'Test generation and maintenance' card

**Reviews code** · Yes — A dedicated PR review workflow reads someone else's diff and posts inline comments on the pull request within minutes.

> The OpenHands PR Review workflow is a GitHub Actions workflow that: Triggers automatically when PRs are opened or when you request a review
> — https://docs.openhands.dev/openhands/usage/use-cases/code-review.md · Overview section, bullet list describing the workflow

**Whole-codebase work** · Partly — Repository-wide migrations are documented as prompts the agent handles, but the Large Codebase SDK that targets big repos is an Enterprise-only line on the pricing table.

> Large Codebase SDK
> — https://www.openhands.dev/pricing · Compare plans table, Integrations group, 'Large Codebase SDK' row (Enterprise column only)

**Ships it** · Partly — It ends at a pull request rather than a deploy: the documented automation loop opens a PR and leaves the merge and release to you.

> When the trigger fires, the agent runs in an isolated cloud container, does the work, and opens a pull request. You review the output.
> — https://www.openhands.dev/enterprise · Automations section, 'Agents that run themselves, on your terms.' paragraph

**Done-for-you service** · Partly — Software you run yourself, but the vendor also sells advisory and implementation engagements that deploy agents alongside your team.

> We work alongside your team to design and deploy production-ready agents that are integrated with your environment and workflows, on an OpenHands foundation you can extend and own.
> — https://www.openhands.dev/services · Implementation section, 'Move from roadmap to production'

## How much it does unattended

**Runs autonomously** · Yes — Event-triggered runs complete the task with nobody in the loop, and headless CLI mode forcibly approves every action.

> Headless mode always runs in `always-approve` mode. The agent will execute all actions without any confirmation. This cannot be changed
> — https://docs.openhands.dev/openhands/usage/cli/headless.md · Requirements section, warning box

**Multi-agent** · Partly — A parent agent can delegate to sub-agents, but the documented TaskToolSet runs them sequentially and blocks, so it is delegation rather than parallel coordination.

> The TaskToolSet lets a parent agent launch sub-agents that handle complex, multi-step tasks autonomously. Each sub-agent runs synchronously - the parent blocks until the sub-agent finishes
> — https://docs.openhands.dev/sdk/guides/task-tool-set.md · Overview section, first paragraph

**Agent permissions** · Yes — Three confirmation policies ship in the SDK, from approving every action to only risky ones judged by a security analyzer.

> AlwaysConfirm() - Require approval for all actions; NeverConfirm() - Execute all actions without approval; ConfirmRisky() - Only require approval for risky actions
> — https://docs.openhands.dev/sdk/guides/security.md · Confirmation Policy section, 'Available policies' list

## Which models it runs on

**Claude** · Yes — Claude Sonnet, Opus and Haiku are all sold through the vendor's own LLM proxy, and can equally be reached with your own Anthropic key.

> claude-sonnet-4-5-20250929 | $3.00 | $0.30 | $15.00 | 200,000 | 64,000
> — https://docs.openhands.dev/openhands/usage/llms/openhands-llms.md · Pricing table, claude-sonnet-4-5 row

**GPT** · Yes — GPT-5 and GPT-5 Codex appear in the vendor's own model price list, and Azure OpenAI is a documented provider route too.

> gpt-5-codex | $1.25 | $0.125 | $10.00 | 272,000 | 128,000
> — https://docs.openhands.dev/openhands/usage/llms/openhands-llms.md · Pricing table, gpt-5-codex row

**Open models** · Yes — Open-weight models are supported first-class: a recommended local model plus documented LM Studio, Ollama, vLLM and SGLang serving paths.

> We now recommend Qwen3.6-35B-A3B as the first local model to try with OpenHands. It is an open-weight MoE model built for agentic coding
> — https://docs.openhands.dev/openhands/usage/llms/local-llms.md · News section, 2026/05/21 entry

**Model choice** · Yes — You choose the model on every tier; the vendor lists model agnosticism as a feature of the free local plan itself.

> Model agnostic
> — https://www.openhands.dev/pricing · Local / Open Source plan card, Includes list, final bullet

## Where you use it

**In your editor** · Partly — Zed, JetBrains and a community VS Code extension connect over ACP, but the vendor itself labels the IDE integration experimental.

> IDE integration via ACP is experimental and may have limitations.
> — https://docs.openhands.dev/openhands/usage/cli/ide/overview.md · Top-of-page warning box, above 'What is the Agent Client Protocol'

**On the command line** · Yes — A terminal CLI is included on every plan including the free local one, with headless and JSON output modes for scripting.

> OpenHands CLI
> — https://www.openhands.dev/pricing · Compare plans table, Key Capabilities group, 'OpenHands CLI' row (ticked in all three columns)

**In your pipeline** · Yes — Ships as GitHub Actions plugins for PR review and QA, and headless mode is documented specifically for CI/CD pipelines.

> Headless mode runs OpenHands without the interactive terminal UI, making it ideal for: CI/CD pipelines
> — https://docs.openhands.dev/openhands/usage/cli/headless.md · Overview section, intro sentence and bullet list

**In a browser** · Yes — A web GUI is on every tier, hosted on OpenHands Cloud for the SaaS plans and run locally on the open-source one.

> Hosted cloud access from desktop and mobile
> — https://www.openhands.dev/pricing · SaaS / Individual plan card, 'Everything in Free, plus:' list

## Whose machine it runs on

**Self-hosted** · Yes — Two self-host routes: the free open-source stack on your own machine, and Enterprise deployed into your own Kubernetes VPC.

> Deploy on your own Kubernetes infrastructure. Your code never leaves your environment. No shared tenancy.
> — https://www.openhands.dev/enterprise · Built for teams running agents at scale section, 'Self-hosted in your VPC' card

**Open source** · Partly — The core is MIT-licensed open source, but the Enterprise control plane is described only as source-available under a commercial licence.

> OpenHands Open Source is a full, MIT licensed version of OpenHands that is designed for a single user and can run locally on your machine with your own LLM key.
> — https://www.openhands.dev/pricing · FAQs, 'What are the main differences between OpenHands open source, and OpenHands Cloud?' answer

## What it costs to run

**How it meters** · Yes — Not seats: you pay for model tokens, either with your own key or through the vendor's proxy billed per million tokens at provider rates.

> Pricing follows official API provider rates. Below are the current pricing details for OpenHands models:
> — https://docs.openhands.dev/openhands/usage/llms/openhands-llms.md · Pricing section, sentence above the per-1M-token table

**Free tier** · Yes — Two standing free plans with no sales call: the local open-source build, and a free hosted Individual tier on the cloud.

> Bring your own key or use our providers at-cost
> — https://www.openhands.dev/pricing · SaaS / Individual plan card, price row reading 'Free' with this subtitle

**API access** · Yes — A documented REST API starts and polls conversations with a bearer key, and the pricing table ticks Cloud APIs on all three plans.

> OpenHands Cloud provides a REST API that allows you to programmatically interact with OpenHands.
> — https://docs.openhands.dev/openhands/usage/cloud/cloud-api.md · Cloud API Overview, opening paragraph

**MCP server** · Yes — MCP is fully supported on CLI, SDK, local GUI and Cloud, letting the agent consume external tool servers over SSE, SHTTP or stdio.

> Model Context Protocol (MCP) is an open standard that allows OpenHands to communicate with external tool servers, extending the agent's capabilities with custom tools
> — https://docs.openhands.dev/overview/model-context-protocol.md · Intro paragraph above the MCP Support Matrix

**Bring your own key** · Yes — Bring-your-own-key works on every plan, and Enterprise additionally runs on your own infrastructure with your existing provider agreements.

> Yes! OpenHands Open Source and OpenHands Cloud plans offer support to bring your own LLM keys.
> — https://www.openhands.dev/pricing · FAQs, 'Can I bring my own model keys?' answer

## Buying it for a team

**A company can buy it** · Yes — Organisations buy the Enterprise plan on a custom contract, with multi-user orgs, shared credits and centralised team billing.

> Centralized team billing
> — https://www.openhands.dev/pricing · Compare plans table, Key Capabilities group, 'Centralized team billing' row (Enterprise column only)

**Seat model** · Partly — No published per-seat rate at all: the two free plans are single-user, Enterprise is unlimited users and is explicitly sold without seat licensing.

> Use your own compute resources and LLM API keys. No per-seat licensing.
> — https://docs.openhands.dev/enterprise.md · What is OpenHands Enterprise, 'Cost Control' card

**Pooled budget** · Yes — Organisation members draw on one shared credit pool, with an org-wide monthly cap plus per-user budgets admins can override.

> Create conversations - Start new conversations using the organization's shared credits.
> — https://docs.openhands.dev/openhands/usage/cloud/organizations/roles-permissions.md · Role Descriptions, Member bullet list

**Admin controls** · Yes — Admins constrain the agent's reach: which secrets, tools and domains it may touch, plus enforced default LLMs and spending caps.

> Define exactly which secrets, tools, and domains each agent can reach. Detect prompt injection. Halt risky actions for human review.
> — https://www.openhands.dev/enterprise · Security section, 'Agents get access to what they need. Nothing more.'

**Audit log** · Partly — Full per-action audit logging is claimed for the Enterprise control plane; the free and Individual tiers carry no such published logging.

> Complete audit logs for every agent action
> — https://www.openhands.dev/enterprise · Security section, third bullet

**Single sign-on** · Partly — SAML SSO exists only on self-hosted Enterprise; the comparison table shows it absent from Cloud and from both free tiers.

> This guide explains how to let users sign in to an OpenHands Enterprise installation with your corporate identity provider (for example Okta, Microsoft Entra ID, Google Workspace, or ADFS) over SAML.
> — https://docs.openhands.dev/enterprise/integrations/saml-sso.md · SAML SSO page, opening paragraph

## What happens to your code

**Opt out of training** · Partly — Running it locally or self-hosted keeps code out of vendor hands entirely, but the cloud privacy policy reserves model training on your content with no opt-out published.

> we may use content and feedback from your use of the Services to train and tune our AI models to improve the capabilities of our Services
> — https://www.openhands.dev/privacy · How we use personal information, 'To develop and improve the Site and Services'

**Data residency** · Partly — Enterprise puts code and conversations in your own infrastructure, but no region or jurisdiction is published for the hosted cloud tiers.

> All code and conversations stay on your infrastructure. Nothing leaves your environment.
> — https://docs.openhands.dev/enterprise.md · What is OpenHands Enterprise, 'Complete Data Control' card

**Getting out** · Partly — You can manage and delete stored content, and deletion is by email request; no bulk data export or credit-expiry terms are published.

> If you require your data to be deleted, please email contact@all-hands.dev.
> — https://www.openhands.dev/privacy · Retention section

_Not established: Certifications_

## Platform record (as of 2026-08-30)

Reported by the code-hosting platform, not by the vendor.

| Fact | Value |
| --- | --- |
| Licence | MIT |
| Stars | 85613 |
| Forks | 11214 |
| Last push | 2026-08-30 |

## Provenance

1 of 37 sources behind the facts above are independent of the vendor.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| all-hands.dev | Independent source | 2026-07-17 |
| vpsranking.com | Independent source | 2026-07-17 |

## What changed

- 2026-09-21 — Capabilities · Commercial terms · Free tier
- 2026-09-02 — Capabilities · Commercial terms · Free tier · Price
- 2026-08-31 — Capabilities · Commercial terms · Free tier
- 2026-08-23 — Alternatives · One-liner · Repository · Summary
- 2026-07-17 — One-liner · Summary

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent OpenHands, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.