All Hands AI

OpenHands is a platform for building and running AI coding agents across the software development lifecycle. Teams can start with agents on a laptop, then move successful workflows into shared automations that run in the cloud or inside a controlled environment.

The platform is aimed at engineering teams that want agents to handle repetitive, high-volume work such as reviewing pull requests, fixing failed CI checks, triaging issues and drafting incident retrospectives. Engineers stay in control of review, approval and merge.

Automations start from events in the engineering stack. The page lists triggers from GitHub, Slack, Jira, Linear, CI and schedules, with MCP available to connect internal tools, APIs and data sources. Each workflow can plan, execute, validate and ship a change, and monitor each step.

OpenHands does not tie teams to one agent or model. The page says it can run Claude Code, Codex, Gemini CLI or OpenHands itself, and can use closed models as well as open-weight models such as Kimi, DeepSeek and Qwen. Runs can happen on a local machine, in a cloud sandbox or inside an enterprise VPC.

The Agent Canvas plan is free and open source under the MIT licence, and can be self-hosted on a laptop or shared VM. It supports a single user or shared identity, bring-your-own LLM key, and any agent. The Teams plan costs $500 per month for up to 10 users, with extra seats at $50 per month each, and includes a 30-day trial. It adds multi-user identity and role-based access, built-in integrations, budgeting controls and SSO. The Teams plan is capped at 5,000 sessions per month.

The Enterprise plan is priced on request and adds deployment in a VPC, isolated sandboxes, audit logs, usage budgets and an enterprise agreement with SLA-based support and a customer success manager.

The OpenHands SDK and the open-source repository on GitHub are also available for developers who want to build their own agents.