OpenHands/OpenHands

🙌 OpenHands: AI-Driven Development

What it solves

OpenHands Agent Canvas provides a centralized, self-hosted control center for managing coding agents. It eliminates the need to switch between fragmented tools by allowing developers to run multiple agents—such as OpenHands, Claude Code, or Gemini—across various environments (local, remote, or cloud) from a single interface. It also solves the problem of manual repetitive tasks by enabling the creation of automated workflows that trigger agents based on schedules or external events.

How it works

Agent Canvas acts as a frontend orchestration layer that connects to one or more "Agent Servers." These servers run the actual agents and provide a REST API for communication. The system can be deployed in several ways: running directly on a local machine, within Docker containers for sandboxing, or on cloud VMs. For automation, it pairs with an Automation Server that handles scheduling and webhooks to trigger agent actions across third-party integrations like GitHub, Slack, and Linear.

Who it’s for

It is designed for software engineers and development teams who want to maintain control over their agent infrastructure, use a variety of different LLM-powered coding agents, and automate engineering workflows without relying solely on proprietary cloud platforms.

Highlights

  • Multi-Backend Support: Switch between local, remote, and cloud agent backends without losing context.
  • Agent Agnostic: Compatible with OpenHands and any agent using the Agent-Client Protocol (ACP), including Claude Code and Codex.
  • Workflow Automation: Create automations that integrate with Slack, GitHub, Notion, and Linear to handle tasks like issue decomposition or report generation.
  • Flexible Deployment: Supports self-hosting via npm, Docker, or source installation, with options for sandboxed environments.

Related

  • Project
    BennyKok/omg.dev

    An open-source parallel coding agent harness that provides a single web portal to run and control multiple AI coding agents simultaneously.

  • Project
    openchamber/openchamber

    An open-source workspace for running, supervising, and reviewing AI coding agent work across desktop, browser, editor, and mobile devices.

  • Project
    777genius/agent-teams-ai

    A desktop orchestration layer for AI agent teams that allows users to coordinate multiple autonomous agents from different providers to handle coding and project tasks via a Kanban board.

  • Project
    omnigent-ai/omnigent

    Omnigent is an open‑source meta‑harness that unifies many LLM coding agents (Claude Code, Codex, Cursor, etc.) under one CLI and web UI, letting you run, combine, and govern them across devices and cloud sandboxes, with built‑in collaboration and policy features.

  • Project
    ColeMurray/background-agents

    An open-source background coding agent system that executes software engineering tasks in isolated sandboxes and submits results as Pull Requests.