AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Mar 27, 2026·Updated Oct 1, 2026
Independently verified against live vendor data on Sep 7, 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 89.7k 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 and Linear for planning, with Azure DevOps available on the Enterprise tier. 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 product now ships as a set of components. Agent Canvas is the browser client and control center, the Software Agent SDK and Agent Server run the agent, an Automation Server runs scheduled and event-driven automations, and the CLI remains a supported terminal interface. The earlier Docker-based Local GUI is deprecated in favor of Agent Canvas. 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, Git, Jira and Slack integrations, and a cap of 10 conversations per day. 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, Azure DevOps and VPC self-hosting. What free does not buy is any of those governance features, or unlimited daily conversations on the hosted tier. On the hosted tiers it also does not buy model inference, which is billed to your own provider key or at cost. 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. No mechanism to opt out of that is published on the free tiers. Its Enterprise Security FAQ states that for customers with an Enterprise Customer Agreement, customer data is not used to train or test its AI systems, and self-hosting the MIT build avoids the question entirely because nothing leaves your environment. Separately, the company runs a Vanta trust center that publishes a controls framework, three subprocessors and an engagement letter, and its Security FAQ records SOC 2 Type II as in progress and ISO 27001 as not yet held. OpenHands suits teams that want to delegate whole engineering tasks to an agent they can inspect, self-host and run on their own model keys, and that have code review in place for the pull requests it opens. Devin at $20/mo and GitHub Copilot at $10/mo are commercial alternatives with managed infrastructure and support commitments, for teams that would rather not run model API spend or Docker infrastructure themselves. Current state Q4 2026: the product ships as Agent Canvas, the Software Agent SDK and Agent Server, an Automation Server and a maintained CLI, with the old Local GUI deprecated. Individual and Open Source are free, Enterprise is quote-only, and SOC 2 Type II is in progress with a third-party penetration test completed in June 2026. A September 2026 Enterprise release added organization-wide secrets, a budget dashboard showing each member's usage, sign-in to MCP servers with the user's own identity through OAuth, including a catalog with GitLab and Atlassian Rovo, organization-wide visibility of automations, and Git Sync for managing automations through a Git repository.

Pricing

free

View pricing ↗

Segment

b2b

Setup

moderate

Verified

Sep 7, 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 89.7k 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.
  • ✓Jira, Slack and Git provider integrations, MCP support and the Cloud Agent SDK are included on every tier, including the two free ones, and scheduled and event-driven automations can open pull requests without a developer at the keyboard.

Limitations

  • –Training depends on the tier. On the free hosted Individual tier the privacy policy states that All Hands AI may use content and feedback from your use of the Services to train and tune its AI models, with no opt-out published. Under an Enterprise Customer Agreement customer data is not used for training, and the self-hosted Open Source build sends nothing to the vendor.
  • –The Vanta trust center names no certification. The vendor's Security FAQ dated July 2026 records SOC 2 Type II as in progress and ISO 27001 as not yet held, so there is no completed attestation to point at.
  • –Enterprise is the only route to multi-user RBAC, SAML and SSO, centralized billing, the Agent Control Plane, the Large Codebase SDK and Azure DevOps, and its price is not published. The free hosted Individual tier is capped at 10 conversations per day.

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
GitHubGitLabBitbucketAzure DevOpsJiraSlackLinear

Similar agents

Rating

4.6/ 5
★★★★★

Editorial score

How we score this →

Recognition

Rated 4.6 ★Listed 2026
Embed these on your site →

Built for

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 Claimed badge on your listing.

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.