pitupitu
Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents run in herdr.
Install / Use
npx skills add klarluft/pitupituInstalls into whichever agent you are using.
Other
Other agent config
Quality Score
Category
OtherSupported Platforms
Our assessment of pitupitu
pitupitu scores 88/100 on our quality scale, 115th of 294 Other skills we index (top 40%).
Its Other is 18 KB long, well organised into 9 sections with 7 code examples: a thorough specification that gives an agent plenty to work with.
It has 95 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated 2 days ago, so pitupitu is actively maintained.
- It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
pitupitu compared with similar skills
All 4 of these similar skills score higher than pitupitu; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| pitupitu (this skill)by klarluft | 88 | 95 | 2d ago | Other |
| LocalAIby mudler | 100 | 50.0k | today | MCP Server |
| constraint-driven-developmentby addyosmani | 100 | 108.2k | 12d ago | SKILL.md |
| content-research-writerby ComposioHQ | 100 | 77.4k | 38d ago | SKILL.md |
| developer-growth-analysisby ComposioHQ | 100 | 77.4k | 38d ago | SKILL.md |
Frequently asked questions
- How do I install pitupitu?
- Run
npx skills add klarluft/pitupitu. The install tabs above show the steps for each supported agent. - Which AI agents does pitupitu work with?
- It is written for Claude Code and OpenAI Codex, as a Other file. Other agents that read the same format can often use it too.
- Is pitupitu safe to use?
- It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is pitupitu still maintained?
- The repository was last updated 2 days ago, so pitupitu is actively maintained.
Skill content
View source on GitHubYou say what you want done and where. pitupitu starts the agent session on that machine, keeps an eye on it, answers what it can, and tells you when it is done or needs you. In the car, on a walk, at the desk: the same sessions, from your phone or any browser.
pitupitu runs your agents in herdr, a terminal workspace manager for coding agents. Open herdr on that machine and you see exactly what your phone sees: the same sessions, live, to watch or type into at the desk. If herdr is not installed, pitupitu installs it.
This repository is the part that runs on each of your machines: a small Rust agent that links the machine to pitupitu cloud over one outbound WebSocket. The conversation, the voice and the page at pitupitu.chat are the hosted service.
<table> <tr> <td width="33%"><img src="assets/talk-phone.png" alt="The Talk screen on a phone: a conversation with pitupitu, and the line above the microphone naming the session that needs you"></td> <td width="33%"><img src="assets/work-phone.png" alt="The Work screen on a phone: what needs you first, then what runs, on every machine"></td> <td width="33%"><img src="assets/session-phone.png" alt="A session that asks: the question at the top, the answers as buttons, the terminal under it"></td> </tr> <tr> <td><b>Talk.</b> Say it; it starts. The line above the microphone names what needs you.</td> <td><b>Work.</b> What needs you first, then what runs, on every machine.</td> <td><b>A session that asks.</b> The question at the top, the answers as buttons, the terminal under it.</td> </tr> </table> <p align="center"> <img src="assets/talk-desk.png" alt="pitupitu on a wide screen: the work beside the conversation" width="100%"> <br><sub><b>On a wide screen.</b> The work beside the conversation; open <code>herdr</code> on the machine for the same sessions in your terminal.</sub> </p>Quick start
curl -fsSL https://pitupitu.chat/install | sh # or: brew install klarluft/tap/pitupitu
pitupitu setup # sign in with a code, pick a folder, start the service
Then open pitupitu.chat/app on your phone and say what you want done. You need claude and/or codex (or another agent herdr knows) installed and signed in on that machine; pitupitu never touches their logins.
How it works
phone / browser ──▶ pitupitu.chat (cloud) ◀── box link (outbound WebSocket) ── pitupitu ──▶ herdr ──▶ your agents
▲
you, at the desk: `herdr` ─┘
- The box agent dials out to
wss://api.pitupitu.chat/v1/box. Nothing connects in: no open port, no VPN, no certificate on your machine. - The cloud can ask for a fixed set of operations only, served through herdr: list, open and close workspaces and tabs, stop a session you asked it to stop, start an agent in a pane, send it a prompt or keys, read its screen, wait for it; and update this agent or herdr when you say so. There is no shell and no arbitrary command. The full list is in docs/box-link.md and in
calls.rs. - Your agents run as they always do, your own unmodified
claudeandcodex(or any agent herdr supports) signed in by you, on your own subscriptions or keys, in your own permission mode. pitupitu never reads, sees or uses their credentials. - herdr's server: the box agent starts
herdr serverwhen none is running (at its own start, and whenever herdr stops answering) and never stops it. It runs on its own, so restarting or updating the box agent leaves your sessions running. Openherdrand you attach to that same server; if you openedherdrfirst, pitupitu uses yours. - Where sessions go: a project gets a herdr workspace labelled after it, as you would make one; quick work in the pitupitu home folder (a lookup, a question) goes into tabs of one
pitupituworkspace, so yours are not littered with them. - From your files, only
skills/*/SKILL.mdin the pitupitu home folder are sent, plus what the box reports about itself: its version and herdr's (and whether newer ones exist), which agent CLIs are installed (with their versions), and the folders your agents worked in recently (only the folder paths and when, read from the agents' own session history; nothing else from those files). With history on, which it is unless you switch it off, more of that history is sent: see History.
Install
curl -fsSL https://pitupitu.chat/install | sh
or with Homebrew (macOS and Linux):
brew install klarluft/tap/pitupitu
pitupitu setup
or build from source with a recent stable Rust:
cargo install --git https://github.com/klarluft/pitupitu pitupitu
Release binaries are built for Linux (x86_64, arm64, static musl) and macOS (Intel, Apple silicon) and come with SHA-256 checksums on the releases page.
The install script and pitupitu setup install herdr with its own installer when it is not on your PATH. A herdr you installed with Homebrew, mise or Nix is used as it is. You need claude and/or codex (or another agent herdr knows) installed and signed in.
Set up
pitupitu setup
It asks a few plain questions; pressing Enter takes the suggested answer.
- Sign in: it shows a code; approve it on any screen at pitupitu.chat. To sign in from your phone, scan the QR code setup shows with its camera (
--no-qrleaves it out). The box gets its own key, stored in~/.config/pitupitu/pitupitu.toml(readable only by you). An account can have many boxes, each named (the hostname by default,--boxto choose); setting up the same box again replaces its old key. - pitupitu's folder (the home folder):
~/pitupituby default. Requests that belong to no project run there, andskills/<name>/SKILL.mdholds routines you name by voice. What pitupitu should know about you ("client work goes on the work laptop", "I use Codex for reviews") is your preferences, kept in your account:pitupitu prefs edit, the page, or just tell pitupitu "remember that …". (APITUPITU.mdfrom 0.1 is no longer read; copy anything useful intopitupitu prefs.) - Your agents can change pitupitu's settings (asked once, yes by default): installs a skill that teaches Claude Code and Codex how, so you can ask your own agent to do it. pitupitu keeps its copies up to date as it updates.
- History (not asked, on by default): setup says in one line that pitupitu keeps track of your projects by reading what your agents did on this machine, and where to switch it off. See History.
- herdr, the small program your agents run inside: installed if missing (said in one line, not asked). Then, for the agents it finds, their sessions are set to come back after herdr restarts (
herdr integration install claudeandcodex). - Starting by itself: pitupitu starts now and whenever you log in (a user service running
pitupitu connect: systemd on Linux, launchd on macOS). On Linux, setup asks once whether to keep it running while you are logged out, so your phone still reaches the machine and it comes back by itself after a restart; yes by default (loginctl enable-linger).--linger/--no-lingeranswer for a script.
Then open pitupitu.chat/app.
Commands
| | |
|---|---|
| pitupitu setup | sign in, pitupitu's folder, herdr, starting by itself (--home, --relink, --box, --no-service, --no-browser, --no-qr, --linger, --no-linger) |
| pitupitu connect | hold the link open in the foreground (what the service runs) |
| pitupitu status | account, home folder, herdr (version, server, newer release), agents found, service and version as this box sees them |
| pitupitu settings | your preferences, default box, agent and models, updates, voice, and every box with its note, on/off, agent and history |
| pitupitu prefs | show your preferences; prefs edit, prefs set <file> (- for stdin), prefs clear |
| pitupitu box note <text> | one line about this box ("client work, Acme"); --clear |
| pitupitu box rename <name> | what you call this machine when you talk; also on the talk page (tap the machine) |
| pitupitu box history on / off | let pitupitu read what your agents did on this machine, or stop it (History); on by default |
| pitupitu box on / box off | off: stays linked, but pitupitu starts nothing here and ignores its sessions until on again |
| pitupitu default <box> | the box used when you don't say which; --clear and pitupitu asks |
| pitupitu updates mine\|all\|quiet | what pitupitu brings up between turns unasked: the sessions you follow (default; its own tasks are followed from the start, yours once you pitupitu follow them), every session, or nothing unless asked |
| pitupitu agent claude\|codex\|auto | the agent a session gets when you don't say (auto: what the machine has, Claude first); pitupitu box agent … for this machine only |
| pitupitu model <agent> <model> | the model that agent runs on when you don't say (pitupitu model claude opus); --clear for its own default |
| pitupitu follow [<session>] | follow a session: pitupitu tells you when it finishes or needs you. Run it in a session in herdr, or name one by its title or id; --off or pitupitu unfollow to stop. pitupitu sessions lists this machine's sessions and which are followed |
| pitupitu place add <name> <path> | a folder on this machine with a name you say ("in acme, run the tests"); place rm <name>, pitupitu places lists them all |
| pitupitu todo | your list: todo add <text> (--here for this repository, --project), pitupitu idea <text>, todo done\|drop\|reopen\|rm <id or words>; pitupitu todo lists the open items (--all, --done, --ideas, --here, words) |
| pitupitu remind <when> <text> | a reminder, the t
Truncated for display — read the full file on GitHub.
Related Skills
LocalAI
50.0kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
constraint-driven-development
108.2kEstablishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-i…
content-research-writer
77.4kAssists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
developer-growth-analysis
77.4kAnalyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
