Austin SpragginsandClaude Opus 5.5 1b55d3cb00 feat(agents): one key jumps to the agent that has waited on you longest (#1164)
With several agents running across tabs and windows, finding the one
blocked on a permission prompt meant scanning tab dots or opening the tray
menu. Go to Next Agent Needing Attention (cmd-shift-U, and ctrl-shift-U off
macOS; FocusNextAgentNeedingAttention to rebind, also in Search Everywhere)
reveals it directly: waiting agents first, the longest wait at the head,
then finished turns nobody has read. Pressing again from one of them moves
to the next and wraps; from anywhere else it starts at the head. It searches
the tabs of every open window, the same agents the tray menu lists, and
reveals a pane in another window the way a tray pick does; a workspace no
window is showing is not searched. With nothing to attend to it says so
("No agent in your open windows needs you") instead of doing nothing
silently. The ordering is a pure function over the tray's agent rows, with
tests.

Ordering by age needs to know when a status began, so AgentSessionState
carries since_ms: the daemon stamps it whenever a hook event, an assumed
interrupt or a stale-turn sweep moves the status. Hook events are stamped
one at a time, so a status that leaves and comes back within one batch
(Done, a new prompt, Done again) starts a fresh age. It is wall-clock time,
not an Instant, because it crosses the socket and survives a handoff; ages
across machines therefore follow each machine's clock. An older daemon
simply leaves it out and those rows queue behind stamped ones.
The tray menu now reads "needs input · waiting 3m", the workspace switcher
shows the same age beside the tab (computed the same way, on the same
clock), and `tty7 agents` gains a FOR column. Ages are in whole minutes in
the GUI so the tray snapshot, and with it the menu, changes at most once a
minute.


Claude-Session: https://claude.ai/code/session_017RJFBHCC4dbUua21a2TedQ

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 12:18:18 +08:00
2026-10-07 22:50:59 +08:00

tty7

tty7

A terminal workbench: persistent sessions, remote work, agents.

Pure Rust · GPU rendering on Zed's gpui · VT core from Alacritty


CI Version Platforms License Discord

English · 简体中文


One-minute tour of tty7: agents across repos, one agent driving another through the CLI, the prompt editor, diffs, dragging panes, and sessions that survive quitting the app

▶ Watch in full quality

Why

A background server owns your shells and panes — not the window. Everything below follows from that.

  • Performance — ~2× the throughput of Alacritty, Ghostty, or Kitty (benchmarks)
  • Persistent sessions — quit the app and your shells keep running; after a reboot, layout, screen, and supported agent conversations come back. No tmux
  • Agent-aware — Claude Code, Codex & co.: status, notifications, and git context for every repo at once
  • Scriptable by agents — one agent opens a pane for another, hands off a task, waits, and reads the result, with or without the GUI running
  • Editor-grade input — suggestions, completion, highlighting, history search, with no plugin to install
  • Remote development — files, repos, panes, and git data stay on the remote machine, over a native SSH stack

Install

Native builds for macOS, Windows, and Linux on Releases:

macOS …-macos-arm64.dmg · …-x86_64.dmg drag into Applications
Windows …-setup.exe · portable ….zip
Linux …-x86_64.AppImage chmod +x and run — X11/Wayland libraries bundled

What's inside

Agent-aware per-pane detection (28 CLIs) · status dot · notifications · branch + diff · tray icon when input is needed · resume after reboot · reopen any past session from Search Everywhere · one-key launch · tab sidebar grouped by repository, with pinned groups
CLI + Skills bundled tty7 CLI · agent skill · run streams a command and exits with its code · split · send · wait --until free · capture
Editor-grade input ghost suggestions from history · explained tab completion · syntax highlighting · multi-line editing · click places the caret · ⌃ R fuzzy history
Window tabs & splits · ⌘ P Search Everywhere · ⌘ F scrollback search · hibernate a tab to free its memory · IME
Side panel ⌘ J · process tree and listening ports · file tree · changes and diffs · find in files · GitHub issues and pull requests, read-only, signed in through gh
Shell integration injected when a pane starts, nothing to install · prompt marks · working directory · exit codes · command-finished notifications · zsh, bash, fish, PowerShell, WSL, remote panes
Remote workspaces remote files, repos, changes, diffs, worktrees, tabs, and panes · reconnect from any client and continue where you left off
SSH native russh stack: profiles with keychain secrets · SFTP panel · port forwarding · jump hosts · one-time, unprivileged tty7-server install

Supported agents

Detection is free: brand avatar, branch + diff, tab title. Status takes one click under Settings → Integrations to install that agent's hook, and brings the status dot, notifications, the tray icon, tty7 wait, and resume after a reboot. Fork needs both — the agent's own fork command, and the hook that tells tty7 which session to fork. Past sessions are read from the agent's own history files and listed in Search Everywhere, where ⏎ resumes one.

The full support matrix, all twenty-eight
Agent Detected Status · resume Fork Past sessions
Claude Code ✓ ✓ ✓ ✓
Codex ✓ ✓ ✓ ✓
TraeCode ✓ ✓ ✓
Grok ✓ ✓ ✓
OpenCode ✓ ✓ ✓ ✓
Oh My Pi ✓ ✓ ✓ ✓
Prime Agent ✓ ✓ ✓
Droid ✓ ✓ ✓ ✓
Qwen Code ✓ ✓ ✓ ✓
Goose ✓ ✓ ✓
Qoder CLI ✓ ✓ ✓ ✓
Qoder CN CLI ✓ ✓ ✓ ✓
CodeBuddy ✓ ✓ ✓ ✓
Gemini ✓ ✓ ✓
Copilot ✓ ✓ ✓
Kimi Code ✓ ✓ ✓
Pi ✓ ✓ ✓
Crush ✓ ✓
Antigravity ✓ ✓
Cursor ✓ ✓ ✓
Empryo ✓ ✓
Muse Code ✓ ✓
jcode ✓ ✓
Aider ✓
Amp ✓
Auggie ✓
Hermes ✓
Vibe ✓

None of them are wrapped or proxied — the agent you start is the agent you get, in a normal PTY, with its own interface. An agent launched through a wrapper script can be mapped to one by name with agent_commands in config.json. Every agent on your PATH is also a row in Search Everywhere (Agent: Claude Code, …) that opens it in a new tab, and the New Tab menu names the ones you have actually run. agent_launch sets the command line it starts with.

Documentation

Full documentation lives in docs/ — keyboard shortcuts · config.json · CLI reference. The agent-facing CLI interface is also documented in skills/tty7/SKILL.md.

Install the skill with:

npx skills add l0ng-ai/tty7    # install
npx skills update tty7         # update later

Benchmarks

Same machine, same day, same 155×40 grid — Apple M1 Pro, macOS 26.3.1, five-run averages (2026-07-04):

tty7 Alacritty Ghostty Kitty
Plaintext I/O — 11 MB cat (lower = better) 95 ms 239 ms 179 ms 185 ms
DOOM-fire frame rate (higher = better) 888 fps 485 fps 552 fps 617 fps
Cold-launch memory 116 MB¹ 105 MB 128 MB 130 MB

¹ GUI 105 MB + the persistent server 11 MB.

Methodology and one-command reproduction: scripts/bench/.


S
Description
A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui, VT core from Alacritty.
Readme Apache-2.0
48 MiB
Languages
Rust 97.4%
TypeScript 1.4%
Shell 0.4%
CSS 0.4%
PowerShell 0.2%
Other 0.1%