peters/horizon

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

What it solves

Horizon replaces traditional tabbed or tiled terminal managers with an infinite 2D canvas. It solves the problem of "tab fatigue" by allowing developers to visually organize terminals, coding agents, browsers, and remote desktops in a spatial layout that persists across sessions.

How it works

Horizon functions as a GPU-accelerated terminal board. You place "panels" (shells, agents, browsers, etc.) onto an infinite surface, which can be grouped into color-coded "workspaces." It uses a command palette for navigation and supports preset templates to quickly spawn complex layouts. The application maintains state, meaning your entire board layout, zoom level, and terminal history are restored exactly as you left them when you reopen the app.

Who it’s for

It is designed for software developers and engineers who manage multiple concurrent tasks—such as coding, monitoring logs, browsing documentation, and interacting with AI agents—and want a more intuitive, spatial way to manage their workspace.

Highlights

  • Infinite Canvas: Pan and zoom across a 2D surface to manage your workflow, with a minimap for quick navigation.
  • AI Agent Integration: First-class support for coding agents like Grok, Claude Code, and Gemini, with live token usage tracking.
  • Integrated Tools: Includes built-in browser panels, markdown editors, Git status views, and VNC support for remote desktop monitoring.
  • Persistent Sessions: Automatically saves your entire board layout, including terminal history and panel positions.
  • Remote Connectivity: Seamlessly integrates with SSH and Tailscale to manage remote hosts, including the ability to open remote shells or VNC sessions.

Related

  • Project
    RizRiyz/luvus

    Luvus is a cross‑platform terminal UI that lets you launch, monitor, and orchestrate AI coding agents (Claude, Codex, Grok, etc.) alongside shells, editors, and Git tools. It provides persistent workspaces, pane management, agent‑aware status panels, Git/GitHub integration, remote‑machine support, a read‑only web view, and an extensible module system. Install via a script, Homebrew, or PowerShell, then use `luvus` to start a session, `luvus doctor` to verify setup, and `luvus update` for upgrades.

  • Project
    Runfusion/Fusion

    Fusion is an open‑source AI‑powered software factory that turns plain‑language task descriptions into fully reviewed, merge‑ready code. It coordinates a fleet of LLM‑driven agents, runs each task in its own Git worktree, and presents the whole process on a visual dashboard with configurable workflows and human oversight.

  • Project
    kaanozhan/Frame

    Frame is an Electron‑based desktop IDE that adds a persistent, git‑tracked “project memory” for AI coding assistants (Claude Code, Codex, Gemini). It creates a `.frame/` folder with rules, architecture maps, task lists and a spec‑driven workflow, injects this context into each AI session, and anchors updates to git commits via pre‑commit hooks. Features include a multi‑terminal grid, task/spec panels, GitHub integration, fast file lookup, and multi‑AI switching. Intended for developers who want reliable, shareable context when working with LLM‑powered agents.

  • Project
    NanmiCoder/cc-haha

    cc‑haha is a cross‑platform desktop workbench for Claude Code and other LLMs. It provides multi‑session chat, Git branch launching, diff review, built‑in browser preview, permission controls, model selection, image generation, visual sub‑agent and team management, dynamic workflow orchestration, request tracing, and macOS‑only “Computer Use” that lets agents control other apps without hijacking your mouse/keyboard. The app is built with Electron, React, TypeScript, and runs on the Bun runtime, supporting many model providers (Claude, ChatGPT, Grok, local Ollama, etc.) and integrates with IM platforms (Telegram, Slack, WeChat, etc.). Users download a binary for macOS/Windows/Linux, configure API keys, and can also run the underlying CLI for deeper customization.

  • Project
    preset-io/agor

    Agor is a self‑hosted (or cloud) web workspace that lets software teams collaborate with coding agents (Claude Code, Codex, Gemini, etc.). Work is organized on Git branches, each with its own dev environment and chat history, and displayed on a live 2‑D board where teammates see live cursors, comments, and artefacts. Persistent AI teammates have searchable knowledge, skills, and scheduled tasks, and can be accessed via Slack or GitHub. The system includes RBAC, token‑cost accounting, and supports any LLM provider via their SDKs. Install with `npm i -g agor-live`, run `agor init && agor daemon start && agor open`.