OpenHands/OpenHands

🙌 OpenHands: AI-Driven Development

What it solves

OpenHands Agent Canvas provides a self-hosted developer control center to manage and automate coding agents. It eliminates the need to switch between fragmented tools by allowing developers to run multiple agents (like OpenHands, Claude Code, or Gemini) across various backends—local, remote, or cloud—from a single interface.

How it works

The system uses a frontend (Agent Canvas) that connects to one or more Agent Servers via a REST API. These servers can be hosted on a laptop, VM, or cloud infrastructure. For automation, it pairs with an Automation Server to trigger agents based on schedules or webhook events (e.g., from GitHub or Slack). It supports the Agent-Client Protocol (ACP) to remain compatible with various third-party agents and allows users to bring their own LLM models.

Who it’s for

Software engineers and development teams who want a centralized, self-hosted environment to orchestrate coding agents and automate repetitive engineering tasks.

Highlights

  • Multi-Backend Support: Switch between local, remote, and cloud agent environments without losing context.
  • Agent Agnostic: Works with OpenHands, Claude Code, Codex, Gemini, Pi, and any ACP-compatible agent.
  • Workflow Automation: Integrates with Slack, GitHub, Linear, and Notion to automate tasks like report generation or issue decomposition.
  • Flexible Deployment: Can be run without a sandbox, within a single Docker container, or with multiple isolated Docker sandboxes for concurrent conversations.

Related

  • Project
    Agenta-AI/agenta

    An open-source, collaborative workspace for building and deploying autonomous AI agents that can be accessed via chat platforms like Slack and Telegram.

  • Project
    openchamber/openchamber

    OpenChamber is an open‑source, cross‑platform workspace that lets developers run AI coding agents, set automated goals, compare multiple model runs, review changes with guided walkthroughs, and ship code—all from desktop, web, VS Code, or mobile.

  • Project
    SirAllap/agentglass

    A desktop workspace that consolidates terminals, pull requests, and agent interactions into one window, allowing you to manage multiple AI coding agents without switching between apps.

  • Project
    autonomous-ai/openharness

    OpenHarness is an open‑source native desktop hub that runs multiple LLM coding agents (Claude Code, Codex, etc.) in real tmux terminals, links laptops, servers and GPU boxes via end‑to‑end‑encrypted WebRTC/relay, and lets you add domain‑specific “harnesses” (Blender, CircuitJS, MuJoCo, etc.) with live viewers. A optional ESP32‑S3 round device shows agent status and accepts voice/tap input.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, self‑hosted AI assistant that plans tasks, runs tools, keeps a personal knowledge base, and can operate as a team of cooperating agents. It supports many LLM providers, multimodal input, dozens of chat channels (Telegram, Slack, WeChat, etc.), a plug‑in skill system, and a three‑tier memory with nightly “Deep Dream” distillation. Install via a one‑line script or Docker, manage everything through a web console, and extend the system through the public Skill Hub or custom tool integrations.