Stop juggling terminals. One workspace where AI agents and dev tools actually work together. Config-driven, with process monitoring built in.
Add a project folder. HiveTerm detects your stack automatically.
Add agents and commands. Configure in the UI or write a hive.yml.
Run hv swarm. Agents coordinate via MCP, notify you when they need you.
8 MCP tools. Claude spawns a test runner. Codex reads its output. The build agent pings you when it's done. They figure it out.
Claude finds a failing test, spins up a dedicated fixer agent, and keeps working on its own task.
One agent checks your dev server logs, spots an error, writes a fix, and restarts the process. You didn't have to ask.
Long build running? The agent sends a native desktop notification when it's done. You keep working on something else.
Press a key, say what you want, and the text shows up in the agent's input. Useful when you've got an idea but don't feel like typing two paragraphs.
Agents, dev servers, watchers, tests. Split panes, tab switching, all running in real terminals with full PTY support.
Define your bees in hive.yml. Commit it. Your teammate clones the repo, runs hv swarm, and gets the exact same setup.
Agents talk to each other through a local MCP server. They spawn sub-agents, read each other's output, send you desktop notifications.
Processes auto-restart on crash. CPU and memory usage per process. Output buffering so you can check what a headless agent did while you were away.
| Feature | HiveTerm | Terminal + tmux |
|---|---|---|
| AI Agent Workspace | ||
| Config-driven setup (hive.yml) | ||
| Built-in MCP Server | ||
| Sub-agent spawning | ||
| Process monitoring & auto-restart | ||
| Split panes | ||
| Desktop notifications from agents | ||
| Cross-platform (Mac/Win/Linux) | ||
| Team config sharing |
No limits. Run as many projects, bees, and sub-agents as you want.
Download, write a hive.yml, run hv swarm. You'll know in 60 seconds if this is for you.