0x0funky

0x0funky / TermHive

Public

Human-driven multi-agent dashboard for Claude Code, Codex, Gemini & OpenCode. Web UI, project wiki, shared content, and MCP-based agent messaging — see every agent, coordinate manually, intervene instantly.

ai-coding claude-code codex gemini-cli multi-agent
37
3
100% credibility
Found Apr 19, 2026 at 37 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

TermHive is a browser-based dashboard for coordinating multiple AI coding agents with live terminal views, shared files, project wiki, and direct messaging between agents.

How It Works

1
🔍 Discover TermHive

You hear about TermHive, a simple dashboard that lets you watch and guide multiple AI coding helpers working together on your projects.

2
🚀 Launch the dashboard

Download and start it on your computer, then open your web browser to see the welcoming screen.

3
📁 Create your project

Name your project and pick its main folder so everything stays organized.

4
🤖 Add your AI helpers

Choose names and roles for your AI team, like frontend or backend expert.

5
🖥️ Watch them all at once

Start your helpers and arrange their screens in splits, grids, or free-form layouts – drag, resize, and jump between them easily.

6
📝 Share files and chat

Drop notes or code into shared folders, send quick messages between helpers, and build a growing project notebook.

🎉 Your project thrives

Your AI team collaborates smoothly under your watch, building exactly what you need without surprises.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 37 to 37 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is TermHive?

TermHive is a human-driven multi-agent dashboard for running Claude Code, Codex, Gemini, and OpenCode CLIs in parallel via a web UI. It streams live terminals from multiple agents, lets you coordinate manually across layouts like tmux-style grids or freeform canvases, and enables instant intervention without tab overload. Built in TypeScript with WebSocket PTYs, it adds shared content folders, project wikis, and MCP-based agent messaging—all stored in simple JSON files, no database needed.

Why is it gaining traction?

Unlike autonomous agent platforms that drift and burn tokens unchecked, TermHive keeps you in control: watch every agent's screen, batch start/stop, and message them directly (e.g., "tell backend API is ready"). The command palette (Cmd+K), mobile responsiveness, and usage trackers for Claude/Codex rate limits make coordinating complex projects feel precise and lightweight. Developers dig the persistent layouts and real-time activity feed that surfaces file changes and messages.

Who should use this?

Backend teams splitting frontend/backend tasks across specialized agents, or solo devs prototyping with Claude Code + Gemini in sync. Ideal for anyone juggling multiple AI coding CLIs on the same codebase, tired of copy-pasting context or losing oversight in separate terminals. Skip if you're on single-agent workflows or prefer fully hands-off automation.

Verdict

Grab it for multi-agent coding if you run Claude/Codex—quick npm install, dev server in seconds, solid docs. At 37 stars and 1.0% credibility, it's early but stable for prototypes; watch for broader Gemini/OpenCode polish.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.