Mininglamp-OSS/octo-web

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

What it solves

OCTO Web provides a unified user interface for the OCTO messaging platform, allowing humans to collaborate with AI agents (referred to as "Lobsters"). It eliminates the need for separate codebases for web and desktop applications by using a single React codebase that targets both the browser and a PC client via Electron.

How it works

Built with TypeScript and React, the client communicates with an octo-server backend using REST and WebSockets. The architecture is split into route-level views, a shared UI kit, a client-side state store, and an API layer. For the PC version, a thin Electron shell wraps the React application to provide native OS capabilities like notifications and file drops.

Who it’s for

Users and developers who want a cross-platform workplace environment where AI agents handle execution and thinking tasks while humans provide direction and taste.

Highlights

  • Cross-platform delivery: A single codebase ships as both a web app and a desktop application.
  • Agent-optimized UI: Includes specialized surfaces for AI interactions, such as streaming replies, tool-call previews, and agent identity chips.
  • Bilingual support: Native English and Simplified Chinese localization built-in.
  • Local-first philosophy: Designed to support a workflow where data and agents can run on the user's own hardware.

Related

  • Project
    Mininglamp-OSS/octo-server

    OCTO Server is a Go‑based backend that provides REST/WebSocket APIs, orchestrates OpenClaw‑powered "Lobster" AI agents, and controls real‑time messaging via WuKongIM. It serves as the central hub for OCTO’s web, mobile, and admin clients, handling authentication, RBAC, storage, and extensible adapters.

  • Project
    pipecat-ai/pipecat-client-web

    A web client SDK and React library for connecting to and interacting with voice and multimodal AI applications built with the Pipecat framework.

  • Project
    agent0ai/agent-zero

    Agent Zero is an open‑source Docker‑based framework that gives an LLM‑driven AI agent a full Linux desktop, a browser with DOM‑annotation, live document editors, and a plugin ecosystem. Agents can run GUI apps (e.g., Blender, LibreOffice), edit files, browse and annotate web pages, and even spawn sub‑agents, all while you watch and intervene through a web UI. Installation is via a cross‑platform launcher or a one‑line script, and the system supports project‑scoped workspaces, host‑machine bridging, time‑travel snapshots, and extensive community plugins.

  • Project
    inkeep/agents

    A platform for building AI agents featuring a no-code visual builder and a TypeScript SDK with full two-way synchronization for collaborative agent management.

  • Project
    assistant-ui/assistant-ui

    assistant‑ui is a TypeScript/React library that provides composable, production‑ready chat UI components for AI assistants. It works with many LLM backends via typed runtimes, handles streaming, markdown, tool‑call rendering, and offers a CLI to scaffold or inject the UI into Next.js projects. MIT‑licensed and backed by Y Combinator.