AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Mar 27, 2026·Updated Aug 17, 2026
Independently verified against live vendor data on Aug 6, 2026.

Open-source autonomous coding agent that writes code, runs commands and closes GitHub issues end-to-end. Free self-hosted under MIT, free cloud tier with bring-your-own-key, Enterprise quote-only.

How we scored it

Autonomy

5/5

Integrations

5/5

Pricing clarity

4/5

Evidence

4/5

Setup

4/5

The facts

OpenHands is an open-source platform for autonomous AI software agents, built by All Hands AI. It lets an agent act as a full software engineer: writing code, running terminal commands, browsing documentation, calling APIs and opening pull requests. Given a GitHub issue or a task description, OpenHands plans and executes the whole solution without per-step direction. It has 84.3k GitHub stars and is MIT licensed. The agent runs in a sandboxed Docker environment with a terminal, code editor, browser and file system. It installs dependencies, runs test suites, debugs failures and iterates until the task completes. Verified integrations are GitHub, GitLab and Bitbucket for source control, Jira for issue tracking, Slack for notification, Linear for planning, and PagerDuty as a workflow trigger. MCP support ships on every plan, and it is client-side: OpenHands connects out to external MCP servers and uses their tools automatically, rather than publishing an endpoint other agents connect into. The primary surface is Agent Canvas, a browser-based UI and backend server that replaced the legacy CLI and Local GUI as the default. All Hands AI publishes the OpenHands Index, a public benchmark that is unusually strong evidence for this category. It scores model and SDK combinations across five categories of real software engineering work: Issue Resolution, Greenfield, Frontend, Testing and Information Gathering. Issue Resolution aggregates SWE-bench and SWE-bench-multimodal. The leaderboard publishes per-category score, dollar cost and runtime for 33 model configurations, 17 open and 16 closed, with downloadable logs for each run. There are three tiers. Two of them are free and clearly published, and only Enterprise is quote-only. Local Open Source is free and self-hosted with unlimited conversations, a web GUI, terminal UI and CLI, and any model via bring-your-own-key. SaaS Individual is free with hosted access, bring-your-own-key or at-cost model providers, and Git integrations. Enterprise is contact-sales and is the only route to multi-user RBAC, SAML and SSO, centralized billing, the Agent Control Plane, the Large Codebase SDK and VPC self-hosting. What free does not buy is any of those governance features, and on the hosted tiers it does not buy model inference either, which is billed to your own provider key. Two things a buyer should weigh before adopting the hosted product. All Hands AI states in its privacy policy that it may use content and feedback from your use of the Services to train and tune its AI models, and publishes no mechanism to opt out of that. Self-hosting the MIT build avoids it entirely, because nothing leaves your environment. Separately, the company runs a Vanta trust center that publishes a controls framework and subprocessors but names no certification at all, and lists an engagement letter rather than a completed attestation. OpenHands is not the right fit for unsupervised production deployment without strong code review. It can return incorrect or partial solutions on ambiguous requirements, and is best treated as a capable junior engineer whose work is reviewed before merging. Devin at $20/mo and GitHub Copilot at $10/mo are commercial alternatives with managed infrastructure and support commitments. Teams unwilling to manage model API spend or Docker infrastructure will find the self-hosted path more demanding. Current state Q3 2026.

Pricing

free

View pricing ↗

Segment

b2b

Setup

moderate

Verified

Aug 6, 2026

Transparency

Mostly Public

Contract

Data training

Trained

Human in loop

Optional

Capabilities

agentic-codingterminal-agentautonomousopen-sourcebyokweb-search

Pros & Limitations

Editorial assessment

Pros

  • Runs the full autonomous software engineering loop: reads an issue, writes code, runs tests, debugs failures and submits a pull request without per-step human direction.
  • Open source under MIT with bring-your-own-key model support, so it self-hosts on your own infrastructure with your choice of model and carries no vendor lock-in. It has 84.3k GitHub stars.
  • All Hands AI publishes the OpenHands Index, a public leaderboard scoring 33 model configurations across five categories of real engineering work, with per-category cost, runtime and downloadable logs. Very few commercial coding agents publish comparable evidence.

Limitations

  • The privacy policy states that All Hands AI may use content and feedback from your use of the hosted Services to train and tune its AI models, and no opt-out mechanism is published. Self-hosting the MIT build avoids this because nothing leaves your environment.
  • The Vanta trust center publishes a controls framework and subprocessors but names no certification of any kind, and lists an engagement letter rather than a completed attestation. There is no SOC 2, ISO 27001 or equivalent to point at.
  • Enterprise is the only route to multi-user RBAC, SAML and SSO, centralized billing, the Agent Control Plane and the Large Codebase SDK, and its price is not published on any surface.

Technical Details

Deployment
cloudself-hostedwebcli
Model architectureMulti-model (model agnostic, bring-your-own-key)
Autonomous rateOpenHands autonomously completes software engineering tasks end-to-end: it writes code, runs tests, debugs failures and submits pull requests without per-step human approval once the issue or task is assigned. The agent iterates until completion or until it reaches a defined stopping condition.
Integrations
GitHubGitLabBitbucketJiraSlackLinearPagerDuty

Similar agents

Rating

4.6/ 5

Editorial score

How we score this →

Recognition

Rated 4.6 ★Listed 2026
Embed these on your site →

Industries

DevToolsOpen Source

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature OpenHands.

Compare

Related Content

Is this your tool?

Claim this listing free to get your embeddable badges, a review collection link, and the Verified checkmark.

Claim listing →

Free · Every Two Weeks

AI Agent Price & Rating Tracker

Price changes, new agent launches, acquisitions, and rating updates across the AI agent market. Verified against live vendor data, not vendor marketing.

No spam. Unsubscribe anytime. We never share your email.