mirror of
https://github.com/l0ng-ai/tty7.git
synced 2026-11-06 16:15:41 +00:00
l0ng-ai
63f97f51d1
Every agent whose launch program is on PATH becomes a palette command, "Agent: <name>", ordered by frecency and bindable as LaunchAgent:<slug>. "New Agent Tab" (Cmd+Shift+A on macOS; unbound elsewhere, where Ctrl+Shift+A is select-all) launches the most recently used one, and the New Tab menu gains a single "Launch Agent..." row that opens the palette pre-filtered to them. A launch always opens a new pane (a tab in the active tab's cwd, or a split when picked from the palette with Alt held) and types the command into that pane's shell once it exists - immediately for a local pane, on landing for a remote one via PendingSpawn::run_on_land - never into a pane that was already there. Detection, status and resume then work as for a hand-typed agent. The command is the agent's bare binary unless the new `agent_launch` config map overrides it. A wrapper named there is detected as its agent without an `agent_commands` entry: the daemon folds the programs `agent_launch` runs into its alias map (interpreters, shells and real agent names excepted), reloaded when config.json changes instead of once per process, and a mapped script run under its interpreter (`bash ~/bin/cc`, `node cc.js`) is now recognised too. A running agent's pane menu gets "Set Current Launch Args as Default", which writes its launch argv - minus session flags and positional prompts, joined with the settings' quoting - into `agent_launch`. Remote workspaces cannot be asked for their PATH through the Host trait, so they offer the agents previously seen running in that workspace (WindowView::seen_agents).
148 lines
5.1 KiB
Plaintext
148 lines
5.1 KiB
Plaintext
---
|
|
title: "Coding agents"
|
|
description: "What tty7 does around Claude Code, Codex, TraeCode, and 20 others — without ever wrapping them."
|
|
---
|
|
|
|
tty7 recognises coding agents running in a pane and builds around them. It does
|
|
not wrap them, proxy them, or replace their interface: the agent you start is
|
|
the agent you get, running in a normal PTY, with its own UI. tty7 adds the
|
|
things a terminal is in a position to add — who is running where, what they
|
|
need, and what changed.
|
|
|
|
<Frame caption="Agent sessions across several repos, each with its avatar, status dot, branch, and diff">
|
|
<img src="/images/agents-overview.webp" alt="Agent sessions in the tty7 sidebar" />
|
|
</Frame>
|
|
|
|
## Which agents
|
|
|
|
Twenty-three CLIs are recognised on sight, by the command running in the pane:
|
|
|
|
| Agent | Command |
|
|
|---|---|
|
|
| Claude Code | `claude`, `claude-code` |
|
|
| Codex | `codex`, `codex-cli` |
|
|
| TraeCode | `traecli`, `traex` |
|
|
| Gemini | `gemini`, `gemini-cli` |
|
|
| Copilot | `copilot` |
|
|
| Cursor | `cursor-agent` |
|
|
| Amp | `amp` |
|
|
| OpenCode | `opencode` |
|
|
| Aider | `aider`, `aider-chat` |
|
|
| Goose | `goose` |
|
|
| Droid | `droid` |
|
|
| Grok | `grok` |
|
|
| Qwen Code | `qwen`, `qwen-code` |
|
|
| Kimi Code | `kimi`, `kimi-code` |
|
|
| Qoder CLI | `qoder`, `qodercli` |
|
|
| Crush | `crush` |
|
|
| CodeBuddy | `codebuddy`, `codebuddy-code`, `cbc` |
|
|
| Auggie | `auggie` |
|
|
| Hermes | `hermes` |
|
|
| Vibe | `vibe`, `vibe-acp` |
|
|
| Antigravity | `agy`, `antigravity` |
|
|
| Pi | `pi` |
|
|
| Oh My Pi | `omp` |
|
|
|
|
Detection sees through the usual disguises: a full path, a `.cmd` or `.exe` on
|
|
Windows, leading environment assignments, and an interpreter in front
|
|
(`node .../claude/cli.js`).
|
|
|
|
### Your own wrapper
|
|
|
|
If you launch agents through a wrapper script, map its name to an agent in
|
|
`config.json`:
|
|
|
|
```json
|
|
{
|
|
"agent_commands": {
|
|
"cc": "claude",
|
|
"work": "codex"
|
|
}
|
|
}
|
|
```
|
|
|
|
The key is your command's name; the value is one of the slugs above (`claude`,
|
|
`codex`, `traecli`, `gemini`, `aider`, `amp`, `opencode`, `copilot`, `cursor`, `goose`,
|
|
`droid`, `pi`, `auggie`, `hermes`, `vibe`, `antigravity`, `grok`, `qwen`,
|
|
`omp`, `kimi`, `qodercli`, `crush`, `codebuddy`).
|
|
|
|
## Quick launch
|
|
|
|
Every agent tty7 finds on your `PATH` is one palette command away: **Agent:
|
|
Claude Code**, **Agent: Codex**, and so on, most-used first. The New Tab menu's
|
|
**Launch Agent…** row opens the palette on that list, and **New Agent Tab**
|
|
(<kbd>⌘ ⇧ A</kbd> on macOS, unbound elsewhere) starts whichever agent you used
|
|
last.
|
|
|
|
A launch always opens a new tab in the current tab's directory and types the
|
|
agent's command into its shell, so the agent is detected, tracked and resumed
|
|
exactly as if you had typed it — and quitting it leaves you at the prompt. Each
|
|
`Agent: …` command is bindable too, as `LaunchAgent:<slug>`.
|
|
|
|
By default an agent launches as its bare binary (`claude`, `codex`,
|
|
`cursor-agent`, …). Give it a command line of its own with `agent_launch`:
|
|
|
|
```json
|
|
{
|
|
"agent_launch": {
|
|
"claude": "claude --dangerously-skip-permissions",
|
|
"codex": "cx --profile work"
|
|
}
|
|
}
|
|
```
|
|
|
|
A wrapper named there (`cx` above) is recognised as that agent without an
|
|
`agent_commands` entry. To keep the flags a running agent was started with,
|
|
right-click its pane and choose **Set Current Launch Args as Default**; tty7
|
|
writes them into `agent_launch`, minus the session they resumed and any prompt.
|
|
|
|
In a remote workspace tty7 cannot read the far machine's `PATH`, so it offers
|
|
the agents it has already seen running there: start one by hand once and it
|
|
joins the list. A wrapper named in your local `agent_launch` is only recognised
|
|
over there if the remote `config.json` names it too.
|
|
|
|
## What you get for free
|
|
|
|
Just by running an agent in a pane:
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Brand avatars" icon="id-badge">
|
|
The tab chip and sidebar row show which agent runs where, so ten tabs stay
|
|
legible.
|
|
</Card>
|
|
<Card title="Git context" icon="code-branch">
|
|
The branch and working-tree diff on the row, refreshed as the agent works.
|
|
</Card>
|
|
<Card title="Session resume" icon="rotate-left">
|
|
A pane lost to a reboot relaunches the conversation, carrying its original
|
|
flags. [More →](/agents/sessions)
|
|
</Card>
|
|
<Card title="Context feed" icon="paper-plane">
|
|
Palette commands that hand the current selection or the repo's `git diff` to
|
|
the running agent as a prompt.
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
## What needs a hook
|
|
|
|
Live status — **working**, **needs your input**, **done** — comes from the agent
|
|
itself, over a channel tty7 installs into that agent's configuration. It powers
|
|
the status dots, the notifications, the tray icon, and `tty7 wait`.
|
|
|
|
Installing takes one click per agent under **Settings → Integrations**.
|
|
[Status and notifications →](/agents/status)
|
|
|
|
## Where to go next
|
|
|
|
<CardGroup cols={3}>
|
|
<Card title="Status and notifications" icon="circle-dot" href="/agents/status">
|
|
Hooks, status dots, the tray icon.
|
|
</Card>
|
|
<Card title="Sessions" icon="code-branch" href="/agents/sessions">
|
|
Resume, fork, and copying a session id.
|
|
</Card>
|
|
<Card title="Orchestration" icon="diagram-project" href="/agents/orchestration">
|
|
One agent driving another with `tty7 wait`.
|
|
</Card>
|
|
</CardGroup>
|