Feature Comparison
The table below highlights the key differences between the OpenHands Agent Canvas and OpenHands Enterprise offerings:| Feature | Agent Canvas | OpenHands Enterprise |
|---|---|---|
| Full breadth of agent functionality (sub-agents, MCP, skills, model agnosticism) | ✅ | ✅ |
| Where does the agent run? | Locally or on a custom backend | Scalable, Kubernetes runtimes |
| Automations Create scheduled and event-based workflows | ✅ | ✅ |
| ‘@OpenHands’ in Slack and Jira Important for real-time resolution of bugs and feedback | Requires custom Automation | Native integration |
| ’@OpenHands’ in GitHub, GitLab, Bitbucket Important for real-time resolution of PR comments and failing tests | Requires custom Automation | Native integration |
| Share conversations Unlock collaboration use cases | ❌ | ✅ |
| Multi-user Organizations and RBAC Roll out to several users and teams | ❌ | ✅ |
| User and Organization Budgets Monitor and control costs | ❌ | ✅ |
| Agent Observability Integrations Centralized logging of conversations | ❌ | ✅ Uses Laminar |
| Private Plugin Marketplace Publish reusable plugins for teams to use | ❌ | ✅ |
| SAML | ❌ | ✅ |
| REST APIs | ❌ | ✅ |
When to Choose Each Option
OpenHands Agent Canvas
The OpenHands Agent Canvas is ideal for:- Individual developers exploring AI-assisted coding
- Small teams with basic requirements
- Self-hosted environments where you manage your own infrastructure
- Running OpenHands locally on your own machine using the Agent Canvas
OpenHands Enterprise
OpenHands Enterprise is the right choice when you need:- Multi-use RBAC — Manage multiple users from a single platform
- Platform integrations — Invoke OpenHands directly from Slack, Jira, GitHub, GitLab, or Bitbucket
- Scalability — Run unlimited parallel agent conversations without local resource constraints
- Enterprise security — SAML authentication, RBAC, and centralized audit logs
- Usage Monitoring — Track and enforce budgets; monitor usage across all users
Kubernetes vs. VM Install — Feature Comparison
OpenHands Enterprise is available in two self-hosted deployment modes:- Kubernetes (Helm) install — deploys into your existing Kubernetes cluster using Helm charts
- VM (Embedded Cluster) install — runs an embedded Kubernetes cluster on a dedicated VM via the Replicated installer
| Feature | Kubernetes Install | VM Install |
|---|---|---|
| Access to LLM Gateway + Budgeting Access to LiteLLM for model routing and per-user/org cost controls | ✅ | ✅ |
| Agent Observability Laminar integration for LLM conversation tracing and analytics | ✅ Opt-in | ✅ Opt-in |
| Automations Scheduled and event-driven agent workflows | ✅ Opt-in | ✅ Opt-in |
| Plugin Marketplace Private plugin directory for team-published plugins | ✅ | ⚠️ Experimental |
| Organizations + RBAC Multi-user organizations with role-based access control | ✅ via Keycloak | ✅ via Keycloak |
Automations and Agent Observability (Laminar) are disabled by default in both deployment modes and must be
explicitly enabled — via Helm values in the Kubernetes install, or via the Replicated Admin Console in the VM install.Plugin Marketplace is available in the VM install but is currently listed as an Experimental feature and
disabled by default.
Getting Started
Try Agent Canvas
Get started with OpenHands on your local machine using Docker or the CLI launcher.
Contact Enterprise Sales
Discuss your organization’s requirements and get a customized deployment plan for OpenHands Enterprise.