Your team’s playbooks,
in every AI tool

Write how your team does the work once. Space serves it, with what your company knows, to Claude, ChatGPT, Codex and every AI tool your people use.

Space hosted stopped taking new accounts on 5 November 2026. Existing accounts keep working, and the open-source edition stays free to self-host.

Works with
  • Claude Code
  • Codex
  • ChatGPT
  • Claude
  • Cursor
  • Gemini
  • Cline
  • Hermes
The Ideal City of Urbino, a Renaissance panel of a perfectly ordered square, in green dots.
Città ideale · Urbino · c. 1480

The problem

Every AI tool does the work its own way.

Your people use Claude, ChatGPT and Codex side by side. Ask each for the same client report and you get three structures, three sets of checks and three levels of quality.

  • Can’t follow your template
  • Can’t see the client’s history
  • Can’t keep your checks

01 · Instructions

Each tool has its own rulebook

Claude Code reads CLAUDE.md, Codex reads AGENTS.md, ChatGPT keeps custom instructions. Each copy drifts on its own.

Space serves one playbook to every tool.

02 · Context

Each tool sees a different picture

One has last year’s report, another last month’s notes, a third nothing at all. Each fills the gaps its own way.

Space gives every tool the same knowledge.

03 · Format

Each run invents the format

Without one template and one checklist, the structure, the order and the checks change from one run to the next.

Space applies your template and your checks.

See it work

Same brief. Same report.
Whatever the tool.

01 Pick a tool

02 Give it your playbook

03 Add what your team knows

04 Change the playbook once

Claude CodeIts own instructions

Audit report, Dupont Industries

Language
English
Sources
None
  • Summary
  • Findings
  • Recommendations
  • Next steps

No checklist applied

Brief: write the audit report for Dupont Industries4 tools · 4 structures

Illustrative example. Models still vary; the playbook removes the differences that come from instructions, context and format.

A page of Leonardo da Vinci’s notebook, handwriting and diagrams, in green dots.

Leonardo da Vinci · Codex Leicester · c. 1510

How it works

Write it once.
Every agent follows it.

  1. #1 Write

    Your playbook, as a skill

    One kind of work: the steps, the template and the checklist your best people use.

    • SKILL.md
    • report-template.md
    • quality-checklist.md
  2. #2 Offer

    Every agent offers it

    When someone asks Claude, ChatGPT or Codex for that work, the agent offers your skill and applies it once they agree.

    Your Space has client-audit for this. Use it?

  3. #3 Update

    Change it in one place

    Edit the skill in Space. Every agent that reads it uses the new version on its next run.

Systems

Playbooks that learn.
Agents get only what is proven.

A system is work your team repeats, such as posting, outreach, SEO or a development lane, with a goal metric, a target and a review cadence. Its lab is where new ideas are tried.

01 · Lab

Try ideas in the lab

Your people and their agents add hypotheses and lessons to a system’s lab. Lab entries are never recalled, so an untested idea never reaches an agent as a rule.

Untested ideas stay in the lab.

02 · Verdict

Promote what proved itself

An entry becomes a verdict, Works or Does not work, only with measured evidence or the owner’s call, and a source. Demote it and it leaves recall at once, with its history kept.

Only verdicts reach your agents.

03 · Reuse

See which lessons get used

Agents record each use of a verdict. Each system shows its health, its goal and its reuse share: how many of its verdicts were used within 30 days of promotion.

Reuse share, per system.

Illustrative example. The entries and systems shown are sample content.

What a Space holds

What your team knows.
In every agent.

#1 Memory

Decisions, with their source

What was decided and why, linked to where it came from. Read, correct or delete any memory from the web app.

#2 Documents and data

Past work, kept

Briefs, reports and templates with every revision, and client records as tables your agents can read and update.

#3 Every AI tool

Each person keeps their tool

Claude, ChatGPT, Codex, Cursor, Gemini and more connect over MCP. Nothing to migrate, nobody to retrain.

Under your control

  • Only the owner edits playbooks
  • Read or write access, per tool
  • Revoke a tool anytime
  • Memory text encrypted at rest
Privacy & data

Questions

Asked before every pilot.

What is a skill?

A playbook for one kind of work, saved in your Space: the steps to follow, plus files such as a template and a checklist. When someone asks a connected agent for that work, the agent offers the skill and applies it once the person agrees. Skills come with the Teams plan.

Which AI tools work with Space?

Claude Code, Codex, Claude, ChatGPT, Cursor, Gemini, Cline and Hermes have each been tested with Space. They connect over MCP, the standard way AI tools reach outside knowledge.

Who can change a playbook?

Only the Space owner. Agents read a skill and offer it; nobody’s agent can rewrite it for everyone.

Is our knowledge private?

You choose which tools connect and whether each can read or write. Memory text is encrypted before it is stored, and search ranks an index of it, so finding a memory never decrypts your whole Space.

Couldn’t we build this ourselves?

You could. The hard parts are serving the same instructions to every tool, keeping each team’s knowledge separate, and searching it without decrypting it. That is the part Space runs for you.

What does a pilot look like?

Pilots are closed. Space hosted stopped taking new accounts on 5 November 2026, and the open-source edition is the way to run it today.

Guides

How AI tools remember.

All articles

Pricing

No new plans.
The code is open.

5 November 2026

Hosted Space is closed to new accounts

Space hosted stopped taking new accounts on 5 November 2026. Existing accounts keep working, and the open-source edition stays free to self-host.

  • Existing accounts keep their work and their access
  • Nothing to cancel if you never paid
  • The self-hosted edition is free, under AGPL-3.0
Self-host it on GitHub

Same task. Same standard.
Whatever the model.

Run it yourself from the open-source repository.