Infinite Haiku

Observability that stays in your network.

Metrics, logs and traces on one timeline, stored in your own cluster and read by your browser directly. Your telemetry never passes through our servers.

Write to us See our servers live →
OpenTelemetry in · Kubernetes · read-only MCP for your agents
Our own Poet, live

drag to zoom · double-click back

Reading our own Poet…

Your data stays home.

The datastore runs in your Kubernetes cluster or on your Linux machines. We sign you in and introduce your browser to it; the data goes straight to you over an encrypted channel. No egress bill to ship telemetry out, and nothing at our end to leak.

Walk into the timeline.

Every series of a service at once, drawn on your GPU. Zoom in and the detail follows; open a request and see its log lines and the change behind it. Missing data is shown as missing, never as zero.

Your agents investigate.

A read-only door (MCP) lets the coding agent you already use search, follow a request and read the same numbers as your charts. No vendor AI, no per-investigation fee.

How it works

  1. 1A Poet in your cluster. Our datastore runs where your services run and takes their OpenTelemetry. Read-only, one namespace.
  2. 2You sign in at infinitehaiku.com. Our web service checks who you are and introduces your browser to your Poet. That is all it sees.
  3. 3Your browser talks to your Poet directly. An encrypted peer-to-peer channel (WebRTC). The numbers never pass through our servers.
Your browser signs in at infinitehaiku.com, which introduces it to the Poet in your network; the data then goes directly between the Poet and your browser. Your network Your services OpenTelemetry Poet your datastore Your browser dashboards, AGS infinitehaiku.com sign-in, introduction your telemetry, encrypted, direct never through our servers
Infinite Haiku in one minute · plays from YouTube (youtube-nocookie.com)

Proof, not promises

Measured: 500,000 tasks from 200 workers over five hours, drawn at 1.1 ms of CPU per frame.

This site's own requests, live: the same public view you can give your customers.

This site's own requests, live · open it full size

Who is behind it

An independent team. You talk to the people who build it.

No sales layer between your questions and the answers.

Built since April 2024. Bootstrapped: no venture capital, no board, no hyperscaler lock-in. About us

  • Alerts in your network. Evaluated inside your own Poets.
  • Public status pages. Share a live dashboard without sharing access.
  • Kernel faults on the timeline. Memory errors, silent out-of-memory kills and disk errors, per node.
  • Flat CHF 5 per user account and month. Nothing per gigabyte, host or event.
  • Don't trust us: watch it yourself. Your Poet shows every connection and its bytes, peer to peer or to us. See how

Join the free pilot.

Expert help on your systems. Leave anytime: delete the Poet, one command. Once we open to the public: two months free, then a flat CHF 5 per user account and month. How the pilot works · Security

Write to us

Docs

Install it, send it your telemetry, and use what it shows.

Start

What Infinite Haiku is, how to send it data and how your AI agent reads it.

  • What is Infinite Haiku

    An observability product whose datastore runs in your infrastructure and whose views reach your browser directly.

  • Connect your AI agent

    Let Claude Code, Codex or any MCP client read your Infinite Haiku through ih-mcp, a read-only program on your own machine.

Install

A Poet where your data should live, and Muses or OpenTelemetry senders that feed it. Your browser reads it over a direct, encrypted WebRTC connection.

  • Install on Kubernetes

    One Helm command, filled in for you on our site. The cluster turns Connected as soon as the pod starts; your browser then reads it over a direct, encrypted WebRTC connection.

  • Install on a Mac or Linux machine

    One line installs the Poet and its Muse as services, from our signed downloads. A Mac needs no administrator rights.

  • Install on NixOS

    A NixOS server or VM: the Poet and the Linux Muse as systemd services through our NixOS module. Other distributions use the one-line installer.

  • Install with plain YAML

    No Helm in the cluster, or a policy review first: render the chart once, read it, apply it with kubectl.

  • Install examples

    Recipes for relay-only networks, mirrors, pull secrets, storage, deleting data on uninstall, Flux, upgrades and several clusters.

Features

What you can do with it.

  • Public dashboards

    Show chosen panels to people who do not sign in, for a demo or a public status page, without opening anything else.

  • How long your data is kept

    Logs and traces are kept a week, metrics for good at a coarser step, and a Poet never fills its disk: the oldest data goes first.

  • Observe your AI coding agents

    See how fast your Claude subscription quota goes, and what each Claude Code session and subagent spends, on which model, with which tools, from Claude Code's own telemetry.

  • Watch every connection yourself

    Who is connected to your Poet, over which path, and how many bytes went where: peer to peer, or to infinitehaiku.com. Measured by your Poet and stored with your other data.