Show HN: Bohay – Mission control for your AI coding agents

bohay: mission control for your AI coding agents

Everything your agents need, in one place

One terminal that watches every agent, keeps your work safe, and ships your code without switching windows.

◉

See every agent at a glance

One sidebar shows what each agent is doing right now: waiting on you, working, finished, or resting. Status you can trust, too: an agent only counts as working when it really is, so a starting CLI or your own typing never reads as busy. An optional retro chime tells you the moment one finishes or needs you.

claude · waiting codex · working copilot · done opencode · resting

See the agent view

⌘

See what an agent is really running

Agents shorten long commands on screen. Click a pane's title for the real one, in full, straight from the system.

Inspect a pane

∞

Pick up where you left off

Close the terminal and nothing stops. Open it again and every pane, tab, and layout is right where you left it.

How sessions work

↺

Your agents remember too

After a restart, each agent reloads its own chat history by itself. You never paste a session flag or lose the thread.

About resume

◇

Run a whole team at once

Put many agents on one project together without stepping on each other. Every agent works in its own copy, claims the files it touches, and only merges once your tests pass.

OAuth moduledone API layerrunning Integration testsqueued

Meet the task board

⎇

Git without leaving

Browse commits, branches, pull requests, and issues in a built in tab. Open a pull request or merge it right there, without touching another app.

Explore the git tab

⇄

Work on any machine

Drive a session running on another computer straight from your laptop over plain SSH. No port forwarding to set up, and it still feels instant as you type.

Set up remote

Several agents. One repo. Zero conflicts.

Add tasks with dependencies to the ◇ orch board. Each started task gets an isolated git worktree and its own pane; path leases stop overlapping edits from even being assigned; a quality gate (your test command) must pass before a task counts as done; and finished branches merge through a dedicated worktree,your checkout is never touched.

Read the orchestration guide →

◇ orch 1 done 2 running 1 queued

t1doneOAuth token modulegate ✓

t2runningAPI layerbohay/t2

t3runningDocs + examplesbohay/t3

t4queuedIntegration tests⟶ t2 t3

LEASES L1 src/api/ L2 docs/

Your agent team, in the notch

bohay-notch mirrors every agent into a native macOS panel that drops from the MacBook notch. Monitor them, approve a request or answer a question, and jump straight to any pane, all without breaking flow.

claude · ~/sudos

Agents

4

AGENTS4

2 running 1 done 1 idle $3.99total

✋claudesudos⧉

Claude wants to run a command

Run cargo test in sudos?

brew install --cask --no-quarantine RizRiyz/bohay/bohay-notch macOS 15+ · Apple silicon · or download the .dmg

Works with the agents you already use

Claude Code

Copilot

Codex

opencode

Cursor

Pi

Kimi

Amp

Grok

Qwen

…plus Gemini, Aider, Droid, and any agent bohay recognizes on screen. Live status for all, zero setup. The ● agents also resume your sessions after a restart, and most report precise events through the optional hook. Full matrix →

Open source · AGPL-3.0 licensed

If bohay saves you time, give it a star

bohay is free and fully open source. A star helps more people running AI agents find it, and you are welcome to read the code, open an issue, or send a pull request any time.

Star on GitHub

Browse the code

github.com/RizRiyz/bohay Open an issue · Read the docs · crates.io