HiveTerm is a desktop terminal that runs your AI agents (Claude Code, Codex, Gemini, Cline, etc.) alongside servers, builds, and scripts, all orchestrated by a hive.yml file. What sets it apart is Queen, an integrated MCP server that allows agents to create sub-agents, read output from other processes, and send notifications to one another. Add to that per-process resource monitoring, Git integration with a diff viewer, automatic stack detection, and context-separated workspaces.

getviktor.com — An AI coworker that actually does the work

An AI coworker that actually does the work

Hey! 👋 I'm a dev running a small team in Brazil. We use Claude Code, Codex, local servers, builds, all running at the same time. My daily life was 15 terminal tabs, Alt+Tab hell, and zero communication between any of it. Claude Code had no clue my server just crashed. My build logs were buried somewhere I'd already forgotten. One day I caught myself arranging 4 terminal windows pixel by pixel for the third time that week and thought "this is stupid, I should just build the thing I actually want." So HiveTerm is that thing. One terminal where your AI agents and dev processes live together. The core idea is Queen, a built-in MCP server that lets agents see each other's output, spawn sub-agents, and send you notifications when stuff finishes or breaks. You drop a hive.yml in your project and everything starts with one command. Built with Tauri + Rust + React. Native on Mac, Windows and Linux. I'd genuinely love feedback, especially on what agents or workflows you'd want supported next 🐝

this looks cool! how do you handle situations where sub-agents conflict or deadlock waiting on each other's output?

getviktor.com — An AI coworker that actually does the work

An AI coworker that actually does the work

this looks cool! how do you handle situations where sub-agents conflict or deadlock waiting on each other's output?

HiveTerm

One workspace for all your AI agents

One workspace for all your AI agents