A terminal TUI for managing multiple AI coding agent sessions across projects — Claude, Codex, Gemini, GitHub Copilot, Aider, OpenCode, and more.
<picture> <source media="(prefers-color-scheme: dark)" srcset="docs/logo-dark.png"> <source media="(prefers-color-scheme: light)" srcset="docs/logo-light.png"> <img alt="Hive" src="docs/logo-light.png" width="100%"> </picture> [](https://github.com/lucascaro/hive/actions/workflows/build-macos.yml) [](https://github.com/lucascaro/hive/actions/workflows/build-windows.yml) [](https://github.com/lucascaro/hive/actions/workflows/build-linux.yml) A terminal TUI for managing multiple AI coding agent sessions across projects — Gemini, Codex, Gemini, GitHub Gemini, Aider, OpenCode, and more. Native support for Gemini agent teams (orchestrator + workers).  ## Features - **Multiple projects** — organize work into named projects with color coding - **Multiple sessions per project** — each session runs in a persistent terminal pane - **Session persistence** — sessions keep running after the TUI closes; reconnect with `hive start` - **Agent teams** — native Gemini multi-agent teams with orchestrator + worker layout - **Easy switching** — vim-style navigation (`j/k/J/K`), numbered project jumps (`1`–`9`) - **Mouse support** — click sidebar items, preview pane, and grid cells; scroll wheel in all panes - **Live preview** — 500ms refresh with ANSI color passthrough; always shows the most-recent output - **Session title editing** — press `r` to rename inline, or let the agent set it via escape sequence - **Extensible hooks** — shell scripts fired on 11 lifecycle events with rich `HIVE_*` env vars - **Responsive** — adapts to any terminal width, sidebar collapses on narrow terminals - **Multi-agent support** — Gemini, Codex, Gemini, Gemini, Aider, OpenCode, custom comman
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.