OpenHands Software Agent SDK

What is OpenHands Software Agent SDK?

The OpenHands Software Agent SDK offers developers Python, TypeScript and REST interfaces for building agents that write and edit code. You define an LLM, give the agent tools such as a terminal, file editor and task tracker, then open a conversation with a workspace and send it a task. Typical uses include one-off jobs like writing a README, routine upkeep like updating dependencies, and larger multi-agent work such as refactors and rewrites. Agents can work directly on your local machine, or run in throwaway workspaces on Docker or Kubernetes via the Agent Server. The same SDK is the engine behind the OpenHands CLI and OpenHands Cloud, so you build with the parts the main product uses. The repository documents agents, tools, conversations, workspaces and events, plus examples for GitHub workflows, skills and plugins. It is an open-source repository with no paid plans listed, and costs come from the LLM provider you connect.

Use cases

• Build a custom coding agent in Python
• Automate dependency updates across repositories
• Run multi-agent refactors and rewrites
• Run agents in Docker or Kubernetes workspaces
• Add coding agents to GitHub workflows
• Create a new developer experience on an agent engine

Who it's for

• Agent developers
• Software engineers
• Platform teams

Why use OpenHands Software Agent SDK

• Build on the same engine that runs the OpenHands CLI and Cloud instead of writing an agent loop from scratch.
• Pick where agents run, from your own machine to isolated Docker or Kubernetes workspaces.
• Python, TypeScript and REST access let different parts of a stack talk to the same agents.
• Reusable skills and custom tools let you adapt agents to your repositories and package tooling.
• Open-source code and worked examples make it easier to inspect behavior before adopting it.

OpenHands Software Agent SDK features

• Python SDK for agents, tools and conversations
• TypeScript client that works in the browser
• REST and WebSocket API through the Agent Server
• Built-in terminal, file editor and task tracker tools
• Local workspaces or ephemeral Docker and Kubernetes workspaces
• Support for custom tools and MCP
• Skills loaded through AgentContext, including public skills from a marketplace
• Examples for standalone use, remote servers, GitHub workflows and plugins
• Powers the OpenHands CLI and OpenHands Cloud

OpenHands Software Agent SDK integrations

• GitHub
• Docker
• Kubernetes
• MCP
• OpenHands CLI
• OpenHands Cloud

How to get started with OpenHands Software Agent SDK

1. Install the SDK following the Getting Started guide.
2. Create an LLM object with a model name and API key, then an Agent with the tools it may use.
3. Open a Conversation with a workspace, either a local directory or a remote Agent Server.
4. Send a message and call run so the agent edits files and runs commands to complete the task.
5. Add skills, MCP servers or automation to extend what the agent does.

OpenHands Software Agent SDK limitations

• It is a developer toolkit, so you write code to use it rather than getting a ready-made app
• You supply your own LLM API key and pay your provider directly

OpenHands Software Agent SDK pricing

OpenHands Software Agent SDK is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

OpenHands Software Agent SDK alternatives

The main OpenHands Software Agent SDK alternatives listed on Debuly are Claude Agent SDK, OpenAI Agents SDK, LangGraph, CrewAI, AutoGen and Pi. The table compares pricing and platforms; order is A–Z.

1. 

   AutoGen

   Microsoft's MIT-licensed Python and .NET framework for multi-agent AI apps, now archived; new projects are pointed to Microsoft Agent Framework.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit AutoGen (official site)
2. 

   Claude Agent SDK

   Anthropic's Python SDK for building agents on the Claude Code runtime, with built-in tools, custom tools, hooks and MCP servers.

   Developer platformsAutomation and agentsCoding
   Visit Claude Agent SDK (official site)
3. 

   CrewAI

   Multi-agent framework and platform for building AI agent crews in Python or a visual editor, then deploying and monitoring them.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit CrewAI (official site)
4. 

   LangGraph

   Low-level open-source orchestration framework and runtime for building stateful, long-running AI agents as graphs.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit LangGraph (official site)
5. 

   OpenAI Agents SDK

   Open-source Python framework for building multi-agent workflows with tools, handoffs, guardrails, tracing, sandboxes and voice agents.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit OpenAI Agents SDK (official site)
6. 

   Pi

   Open-source, MIT-licensed terminal coding agent and TypeScript toolkit you extend with skills, extensions, prompt templates and themes.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Pi (official site)

OpenHands Software Agent SDK FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.