OpenHands/software-agent-sdk

A clean, modular SDK for building AI agents with OpenHands V1.

What it solves

It provides a standardized way to build AI agents specifically designed to interact with code and software development environments. It simplifies the creation of agents that can perform tasks ranging from simple documentation updates to complex codebase refactors and routine maintenance.

How it works

The SDK offers Python, TypeScript, and REST APIs that allow developers to define agents, equip them with tools (such as terminal access, file editors, and task trackers), and manage conversations within a workspace. These agents can operate on a local machine or within isolated, ephemeral environments like Docker or Kubernetes via an Agent Server.

Who it’s for

Software engineers and developers who want to build custom AI-powered developer tools, automated maintenance bots, or complex multi-agent software engineering workflows.

Highlights

  • Multi-language Support: APIs available in Python, TypeScript, and REST.
  • Flexible Workspaces: Supports both local execution and remote, ephemeral workspaces (Docker/Kubernetes).
  • Extensible Tooling: Includes built-in tools for terminal and file editing, with support for custom tools and MCP.
  • Skill Integration: Can automatically load package-management skills (e.g., for uv or deno) based on project markers.

Related

  • Project
    codeany-ai/open-agent-sdk-typescript

    An open-source TypeScript SDK for running autonomous AI agents in-process, featuring a vast library of built-in tools and support for multiple LLM providers.

  • Project
    strands-agents/harness-sdk

    An open-source SDK for building and running AI agents in Python and TypeScript, providing a model-agnostic framework for managing agent loops, tools, and memory.

  • Project
    CopilotKit/CopilotKit

    An SDK for building agent-native applications that allows a single agent backend to power generative UI and shared state across web, mobile, and chat platforms.

  • Project
    Agenta-AI/agenta

    Agenta is an open‑source, self‑hostable workspace for building AI agents that can be chatted with, shared with a team, and run in the background. It supports many LLM providers, integrates with thousands of SaaS tools, offers permission controls, tracing, and scheduling, and provides a web UI plus a rich developer ecosystem.

  • Dispatch
    OpenAI Agents API Launch – Managed Harness for Durable Cloud Agents

    OpenAI introduced the Agents API, a managed Codex harness that lets developers run durable, tool‑enabled agents in hosted or self‑hosted sandboxes, with session persistence and multi‑agent support.