Openhands

Open-source AI agents that code, debug, and deploy software.

Openhands is an open-source AI software development agent platform that enables autonomous coding agents to interact with a full development environment — writing code, running commands, browsing documentation, and debugging — to complete software engineering tasks from end to end. Built under an MIT license and developed out of research at Boston’s AI Lab (formerly OpenDevin), it is designed to be accessible to both individual developers and enterprise teams, with a self-hosted option for those who want full control and a managed cloud offering for those who prefer convenience. Openhands differentiates itself primarily through its open-source nature, which allows teams to inspect, modify, and extend the platform, and its support for multiple LLM providers as the underlying model powering agents.

Compliance

SOC 2

Visit Openhands

Key Features

Full development environment access: Agents interact with a real shell, file system, browser, and code editor rather than generating text in isolation, enabling them to run code, install packages, and observe actual execution results.
Autonomous task execution: Takes a natural language task description and works through it end-to-end, handling planning, implementation, testing, and iteration without requiring human input at each step.
Multi-model support: Works with a range of LLM providers, giving teams flexibility to use the model that best fits their capability, cost, and data residency requirements.
Open-source MIT license: The full platform is freely available and modifiable, allowing teams to self-host, customize, and contribute without licensing restrictions.
Cloud and self-hosted options: Available as a managed cloud service for ease of use or self-hosted for teams that need data control or want to integrate Openhands into their own infrastructure.
Enterprise support: Custom enterprise arrangements are available for organizations that need SLAs, dedicated support, or additional compliance guarantees beyond what the open-source deployment provides.

Use Cases

For developers wanting a self-hosted autonomous coding agent: An engineer who wants to run AI coding agents on their own infrastructure — for cost control, data privacy, or customization — deploys Openhands self-hosted using their preferred LLM provider.
For research and AI teams experimenting with agent architectures: A team building or evaluating AI agent systems uses Openhands as an open-source foundation they can inspect and modify, rather than building a full agent execution environment from scratch.
For SMBs wanting autonomous engineering capacity without enterprise pricing: A small software company uses Openhands’ cloud tier on a usage-based model to handle self-contained coding tasks without committing to the fixed costs of enterprise-only autonomous coding tools.

Pricing MODELS

Open-source free

Pricing Summary

The core Openhands platform is free and open source (MIT license) and can be self-hosted at no licensing cost. A managed cloud version is available on a usage-based pricing model. Custom enterprise pricing is available for organizations with additional support or compliance needs.