2026-10-17 12:08:30 -05:00
|
|
|
---
|
|
|
|
|
title: "Recipes"
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
summary: "Extensions put together: Asana, subagents, a classifier guard, Herdr, your phone, and a local model."
|
2026-10-17 12:08:30 -05:00
|
|
|
order: 8
|
|
|
|
|
group: "Extend"
|
|
|
|
|
---
|
|
|
|
|
|
|
|
|
|
## Asana
|
|
|
|
|
|
|
|
|
|
Two ways to bring Asana in, and they work together: its MCP server, so the agent can read and update
|
|
|
|
|
tasks, and a mention source, so you can point at one task with `@`.
|
|
|
|
|
|
|
|
|
|
### The MCP server
|
|
|
|
|
|
|
|
|
|
Asana registers each app, so each person makes one of their own.
|
|
|
|
|
|
|
|
|
|
1. **Register an MCP app** in Asana's developer console (**My apps**). Set its redirect URL to
|
|
|
|
|
`http://127.0.0.1:8765/callback`, and leave **This is a native or command-line app** unchecked.
|
|
|
|
|
Share it with your workspace. Your organization may need an admin to approve it.
|
|
|
|
|
2. **Keep the secret in your environment.** In `~/.zshrc` or `~/.bashrc`, then open a new
|
|
|
|
|
terminal:
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
export ASANA_MCP_CLIENT_SECRET='…'
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
3. **Add the server**, with your app's client ID, and hide the tools Asana marks as internal:
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/mcp.json"
|
|
|
|
|
{
|
|
|
|
|
"mcpServers": {
|
|
|
|
|
"asana": {
|
|
|
|
|
"url": "https://mcp.asana.com/v2/mcp",
|
|
|
|
|
"auth": {
|
|
|
|
|
"kind": "oauth",
|
|
|
|
|
"client_id": "1209…",
|
|
|
|
|
"client_secret": "${ASANA_MCP_CLIENT_SECRET}",
|
|
|
|
|
"redirect_uri": "http://127.0.0.1:8765/callback"
|
|
|
|
|
},
|
|
|
|
|
"exclude_tools": [
|
|
|
|
|
"get_project_internal", "search_objects_internal", "log_widget_event",
|
|
|
|
|
"create_task_confirm", "save_task_changes_confirm", "create_project_confirm",
|
|
|
|
|
"create_project_confirm_populate", "save_project_changes_confirm"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
4. **Sign in** and check what you can use:
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
luxe mcp login --id asana
|
|
|
|
|
luxe mcp tools
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
5. **Decide what the agent may do.** Task names and comments go to your model provider when a tool
|
|
|
|
|
returns them. To let reads through and ask before anything changes:
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/permissions.json"
|
|
|
|
|
{
|
|
|
|
|
"permission": {
|
|
|
|
|
"mcp": {
|
|
|
|
|
"asana/create_*": "ask",
|
|
|
|
|
"asana/update_*": "ask",
|
|
|
|
|
"asana/delete_*": "ask",
|
|
|
|
|
"asana/add_*": "ask"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
If Asana's data may only go to a provider your organization approves, use
|
|
|
|
|
`"asana/*": "deny"` until you are on one. In a headless or loop run, make the writes `deny`:
|
|
|
|
|
nobody is there to answer an `ask`.
|
|
|
|
|
|
|
|
|
|
6. **Use it:** *@[mcp:asana] what is due this week?*
|
|
|
|
|
|
|
|
|
|
### Your tasks in the `@` picker
|
|
|
|
|
|
|
|
|
|
This needs a personal access token (**My apps → Personal access tokens**), since the MCP sign-in's
|
|
|
|
|
token works only for the MCP server. Your workspace's ID is in
|
|
|
|
|
`https://app.asana.com/api/1.0/workspaces`, read with the same token.
|
|
|
|
|
|
|
|
|
|
```bash title="~/bin/asana-mentions"
|
|
|
|
|
#!/bin/sh
|
|
|
|
|
curl -sSf -H "Authorization: Bearer $ASANA_PAT" -G https://app.asana.com/api/1.0/tasks \
|
|
|
|
|
--data-urlencode assignee=me --data-urlencode "workspace=$ASANA_WORKSPACE" \
|
|
|
|
|
--data-urlencode completed_since=now --data-urlencode limit=100 \
|
|
|
|
|
--data-urlencode opt_fields=name,due_on,permalink_url |
|
|
|
|
|
jq -c '.data[] | (if .due_on then "due \(.due_on)" else "no due date" end) as $due | {
|
|
|
|
|
id: .gid,
|
|
|
|
|
label: .name,
|
|
|
|
|
detail: $due,
|
|
|
|
|
text: "Asana task \"\(.name)\" (\($due)) \(.permalink_url)"
|
|
|
|
|
}'
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/config.json"
|
|
|
|
|
{ "mentions": [{ "name": "Asana", "command": "asana-mentions" }] }
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
A task you pick goes in as `@[asana:1209…]` and reaches the agent as its name, due date and link,
|
|
|
|
|
and the agent can look it up through the MCP server. See [Mention sources](mention-sources.md).
|
|
|
|
|
|
|
|
|
|
## Subagents
|
|
|
|
|
|
|
|
|
|
A subagent is a separate context that does one job and returns a summary, which is what a headless
|
2026-10-20 13:51:34 -05:00
|
|
|
luxe run is:
|
2026-10-17 12:08:30 -05:00
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
luxe --headless --read-only --model openai/gpt-5.6 --format json \
|
|
|
|
|
-p "review src/parser.rs for edge cases" |
|
|
|
|
|
jq -rs 'map(select(.type == "message" and .text != "")) | last.text'
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
`--read-only` keeps the subagent from changing anything, and `--model` lets it be a different model
|
|
|
|
|
from the one doing the work. The `jq` filter keeps the last message with text in it, which is the
|
|
|
|
|
summary. For a review of your own uncommitted work, [`/review`](agent.md#a-second-opinion) does
|
|
|
|
|
this without the wrapper.
|
|
|
|
|
|
|
|
|
|
To let the agent start one itself, wrap that command in an MCP server with a
|
|
|
|
|
`delegate(task, model)` tool. Then:
|
|
|
|
|
|
|
|
|
|
- Rule it like any tool: `"mcp": { "delegate/*": "ask" }` in `permissions.json` puts each one in
|
|
|
|
|
front of you.
|
|
|
|
|
- Give the server a `timeout_secs` longer than a review takes. A call gets 60 seconds by default,
|
|
|
|
|
and one that runs out stops the subagent.
|
|
|
|
|
- Return the subagent's stderr when it fails, so the agent sees why.
|
|
|
|
|
- Give a subagent that writes its own worktree, with `git worktree add`, so it stays out of yours.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
luxe refuses to nest more than two levels deep, since an agent that starts two subagents per turn
|
2026-10-17 12:08:30 -05:00
|
|
|
would multiply fast. `LUXE_MAX_DEPTH` raises the limit.
|
|
|
|
|
|
|
|
|
|
## A guard that asks a model
|
|
|
|
|
|
|
|
|
|
A `BeforeToolUse` [hook](hooks.md) can ask a small classifier model whether a command is
|
|
|
|
|
destructive, and ask you when it might be. This one calls a typed decision model running on your
|
|
|
|
|
own machine, and the request follows that model's API; any model that returns a probability works.
|
|
|
|
|
|
|
|
|
|
```bash title="~/.config/luxe/hooks/risk-gate.sh"
|
|
|
|
|
#!/usr/bin/env bash
|
|
|
|
|
set -euo pipefail
|
|
|
|
|
command=$(jq -r '.ToolUse.args.command')
|
|
|
|
|
|
|
|
|
|
risk=$(jq -n --arg c "$command" '{
|
|
|
|
|
state: { command: $c },
|
|
|
|
|
questions: { destructive: { type: "noul",
|
|
|
|
|
instructions: "Would running this command cause irreversible data loss?" } }
|
|
|
|
|
}' |
|
|
|
|
|
curl -sS --max-time 2 "${DECISION_URL:-http://localhost:8000}/v1/systemone" \
|
|
|
|
|
-H 'Content-Type: application/json' --data @- |
|
|
|
|
|
jq -r '.answers.destructive.noul')
|
|
|
|
|
|
|
|
|
|
if awk "BEGIN{exit !($risk > 0.8)}"; then
|
|
|
|
|
jq -n --arg r "scored $risk for irreversible data loss" '{decision:"ask", reason:$r}'
|
|
|
|
|
else
|
|
|
|
|
echo '{"decision":"allow"}'
|
|
|
|
|
fi
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/hooks.json"
|
|
|
|
|
{
|
|
|
|
|
"BeforeToolUse": [
|
|
|
|
|
{
|
|
|
|
|
"matcher": "bash",
|
|
|
|
|
"command": ["/home/you/.config/luxe/hooks/risk-gate.sh"],
|
|
|
|
|
"timeout_ms": 2500,
|
|
|
|
|
"on_timeout": "ask"
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
- **It asks rather than blocks.** A hook can only make a call harder, so the worst a wrong answer
|
|
|
|
|
costs is a prompt.
|
|
|
|
|
- **It adds to your rules, not replaces them.** Keep what must always hold in
|
|
|
|
|
[`permissions.json`](security.md).
|
|
|
|
|
- **It runs before every matching call.** The `matcher` keeps it off `read` and `grep`; narrow it
|
|
|
|
|
further, such as `{ "bash": "rm *" }`, to cost less.
|
|
|
|
|
- **`on_timeout: "ask"`** puts the question to you if the classifier is down.
|
|
|
|
|
- **Nobody answers in a headless run**, so its `ask` is allowed there. Use `--on-ask deny`, or
|
|
|
|
|
`"hook_ask": "deny"` in `permissions.json`, to make it hold.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
## Run luxe in Herdr
|
2026-10-17 12:08:30 -05:00
|
|
|
|
|
|
|
|
[Herdr](https://herdr.dev) keeps coding agents in panes and shows which ones are working, waiting
|
2026-10-20 13:51:34 -05:00
|
|
|
on you, or done. luxe reports its state to Herdr on its own when it runs in a Herdr pane:
|
2026-10-17 12:08:30 -05:00
|
|
|
**working** during a turn, **blocked** when it needs you, and **done** when the turn ends.
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
curl -fsSL https://herdr.dev/install.sh | sh
|
|
|
|
|
herdr
|
|
|
|
|
luxe # in a pane
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
To let the agent drive Herdr, such as splitting panes or starting other agents, add Herdr's skill:
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
mkdir -p ~/.config/luxe/skills/herdr
|
|
|
|
|
curl -fsSL https://raw.githubusercontent.com/ogulcancelik/herdr/master/SKILL.md \
|
|
|
|
|
-o ~/.config/luxe/skills/herdr/SKILL.md
|
|
|
|
|
```
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
`LUXE_HERDR=0` or `{ "herdr": false }` in luxe's config turns the reporting off.
|
2026-10-17 12:08:30 -05:00
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
### luxe colors in Herdr
|
2026-10-17 12:08:30 -05:00
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
Herdr has no theme files — it takes a built-in theme plus per-token overrides. This is luxe's
|
2026-10-17 12:08:30 -05:00
|
|
|
own palette in those tokens, so the pane and the multiplexer around it read as one program:
|
|
|
|
|
|
|
|
|
|
```toml title="~/.config/herdr/config.toml"
|
|
|
|
|
[theme]
|
|
|
|
|
name = "vesper" # the closest built-in; every token below is overridden anyway
|
|
|
|
|
|
|
|
|
|
[theme.custom]
|
2026-10-20 13:51:34 -05:00
|
|
|
accent = "#ddc084" # champagne, the one color luxe leads with
|
2026-10-17 12:08:30 -05:00
|
|
|
text = "#e4dfd6"
|
|
|
|
|
subtext0 = "#97938c"
|
|
|
|
|
overlay0 = "#4d4a45"
|
|
|
|
|
overlay1 = "#97938c"
|
2026-10-20 13:51:34 -05:00
|
|
|
sidebar_bg = "#12100e" # the base surface, same as luxe's background
|
2026-10-17 12:08:30 -05:00
|
|
|
panel_bg = "#12100e" # the tab bar sits on it too, so the chrome is one field
|
|
|
|
|
surface0 = "#201e1a"
|
|
|
|
|
surface1 = "#2e2b27"
|
|
|
|
|
surface_dim = "#201e1a"
|
|
|
|
|
active_row_bg = "#201e1a" # the current space, at rest
|
|
|
|
|
selection_bg = "#2e2b27" # the Navigate cursor, which should be the brighter of the two
|
|
|
|
|
mauve = "#d2a5cd" # branch names
|
|
|
|
|
yellow = "#ddc084" # working — an agent at work glows in the accent
|
|
|
|
|
green = "#81caa0" # idle / done
|
|
|
|
|
red = "#e68485" # blocked, needs you
|
|
|
|
|
peach = "#faaa51" # interrupted
|
2026-10-20 13:51:34 -05:00
|
|
|
blue = "#85c7d7" # luxe has one cool hue, so blue and teal share it
|
2026-10-17 12:08:30 -05:00
|
|
|
teal = "#85c7d7"
|
|
|
|
|
|
|
|
|
|
[ui]
|
|
|
|
|
accent = "#ddc084" # borders and navigation chrome, which read off their own key
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
Reload it in place with `prefix+shift+r`, or `herdr server reload-config`. For any of the other
|
2026-10-20 13:51:34 -05:00
|
|
|
[themes](appearance.md) luxe ships, the hexes are in its theme file and the token names above do
|
2026-10-17 12:08:30 -05:00
|
|
|
not change.
|
|
|
|
|
|
|
|
|
|
The one token worth a second thought is `panel_bg`: Herdr draws the active tab as `panel_bg` text
|
|
|
|
|
on an `accent` fill, so it has to stay dark enough to read there. Lifting it to `#201e1a` gives the
|
|
|
|
|
tab bar a surface of its own if you prefer the chrome delineated.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
## luxe from your phone
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
|
|
|
|
|
Your sessions keep running on your computer, and your phone or tablet reaches them over
|
|
|
|
|
[Tailscale](https://tailscale.com), a private network between your own devices. Nothing is opened to
|
2026-10-20 13:51:34 -05:00
|
|
|
the internet. This is the terminal over SSH; [luxe on your phone](remote.md) is luxe's own way in.
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
|
|
|
|
|
1. Install Tailscale on the computer and on the phone, and sign in to the same account on both.
|
|
|
|
|
2. On the computer, turn on SSH. On Linux and macOS, Tailscale can do it for you:
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
sudo tailscale up --ssh
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
On Windows, turn on the OpenSSH Server in Settings, under Optional features.
|
2026-10-20 13:51:34 -05:00
|
|
|
3. Run luxe in [Herdr](#run-luxe-in-herdr), so your sessions outlive the terminal you started
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
them in.
|
|
|
|
|
4. On the phone, connect with an SSH app such as Blink Shell or Termius, using the computer's
|
2026-10-20 13:51:34 -05:00
|
|
|
Tailscale name, and run `herdr`. It attaches to the panes you left, with luxe where it was.
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
mosh you@desk -- herdr
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
[Mosh](https://mosh.org) keeps the connection through a locked screen or a switch from Wi-Fi to
|
|
|
|
|
cellular. It needs `mosh` installed on the computer too, which Linux and macOS have and Windows
|
|
|
|
|
does not; plain `ssh` works everywhere.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
On an iPad with a keyboard, this is luxe as you know it. On a phone, luxe fits a narrow screen,
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
and Herdr marks which session is waiting on you.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
### A notification when luxe needs you
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
[luxe on your phone](remote.md#notifications) has notifications built in. Without it, a
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
[hook](hooks.md) can post to [ntfy](https://ntfy.sh), whose app shows it on your phone:
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/hooks.json"
|
|
|
|
|
{
|
|
|
|
|
"PermissionRequested": [
|
2026-10-20 13:51:34 -05:00
|
|
|
{ "command": ["curl", "-s", "-d", "luxe is waiting for an approval", "https://ntfy.sh/your-topic"] }
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
],
|
|
|
|
|
"BeforeToolUse": [
|
2026-10-20 13:51:34 -05:00
|
|
|
{ "matcher": "question", "command": ["curl", "-s", "-d", "luxe has a question", "https://ntfy.sh/your-topic"] }
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
],
|
|
|
|
|
"AgentEnd": [
|
2026-10-20 13:51:34 -05:00
|
|
|
{ "command": ["curl", "-s", "-d", "luxe finished", "https://ntfy.sh/your-topic"] }
|
Luxe 0.1.3: your sessions on your phone, joinable sessions, and nested AGENTS.md
- luxe remote puts the sessions on your computer in reach of your own phone or tablet over
Tailscale: write, steer, answer prompts, send photos, browse files, diffs and GitHub, with a
paired device and your own Tailscale login.
- luxe join lets another program on the same machine join a running session over the RPC protocol.
- An AGENTS.md in a subfolder reaches the model the first time it works there.
- Long sessions stay fast: no stall before each model call, lighter memory, cheaper drawing.
- A session is open in one Luxe at a time, web_search shares results across its phrasings, and a
grep glob starting with ! excludes.
The CHANGELOG has the full list.
2026-10-20 02:40:13 -05:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
- **Anyone who knows an ntfy.sh topic can read it**, so pick a long random name, or run ntfy
|
|
|
|
|
yourself on your Tailscale network. The messages above say only that something is waiting, never
|
|
|
|
|
the command.
|
|
|
|
|
- **`AgentEnd` fires after every turn**, at your desk too. Leave it out if that is too many.
|
|
|
|
|
|
2026-10-17 12:08:30 -05:00
|
|
|
## A local model in LM Studio
|
|
|
|
|
|
|
|
|
|
1. Load a model in LM Studio and start its server.
|
2026-10-20 13:51:34 -05:00
|
|
|
2. In luxe, open **Configuration** and choose **Connect a local or custom model**, then
|
2026-10-17 12:08:30 -05:00
|
|
|
**LM Studio**. Leave the endpoint blank for the default.
|
|
|
|
|
3. Choose the model in the picker that opens.
|
|
|
|
|
|
2026-10-20 13:51:34 -05:00
|
|
|
LM Studio ignores the chat-template settings luxe sends a local server by default, so for
|
2026-10-17 12:08:30 -05:00
|
|
|
thinking levels to reach the model, send them as `reasoning_effort`, and start each session at a
|
|
|
|
|
sensible level. Connecting already wrote an `lmstudio` provider to `models.json`, so add these keys
|
|
|
|
|
to it rather than replacing the file:
|
|
|
|
|
|
|
|
|
|
```json title="~/.config/luxe/models.json"
|
|
|
|
|
{
|
|
|
|
|
"providers": {
|
|
|
|
|
"lmstudio": { "compat": { "thinking_format": "openai" } }
|
|
|
|
|
},
|
|
|
|
|
"models": {
|
|
|
|
|
"lmstudio/qwen3.8-27b": { "reasoning": true, "thinking": "medium" }
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
[Custom providers](custom-providers.md) covers samplers and request formats.
|