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.
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.
Works with
Claude Code
Codex
ChatGPT
Claude
Cursor
Gemini
Cline
Hermes
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
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 instructionsAudit 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.
Leonardo da Vinci · Codex Leicester · c. 1510
How it works
Write it once.
Every agent follows it.
#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 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 Update
Change it in one place
Edit the skill in Space. Every agent that reads it uses the new version on its next run.
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
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.
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?
We pick one deliverable your team produces often, write its playbook with you, connect the tools your people already use, and compare real tasks with and without Space.
- Claude memory and Claude Code memory, explainedWhat the Claude apps and Claude Code remember between sessions, and what they forget.
- Codex memory: native memories, AGENTS.md or a workspaceThe three places Codex can keep context, and how to choose between them.
- How to evaluate an MCP memory serverWhat an MCP memory server does, and a 30 minute test before you trust one.
- Agent skills for teams in Claude, ChatGPT and CodexWhere each tool reads SKILL.md, and how a team shares one skill across them.
- Agent memory explained: context, retrieval and learningHow agent memory differs from a context window and from model training.
Pricing
Start with a pilot.
On your own work.
Teams · after the pilot
For your team
€9.99 excluding VAT per seat a month
- A pilot on one playbook, written with you
- Your team’s tools connected, nothing to migrate
- Real tasks compared with and without Space
- Then the Teams plan, from 2 seats
Starter · Pro · Ultra
On your own
from €1.29 excluding VAT a month
- Skills, documents, databases and memory
- For one person and the AI tools they use
- Starter’s first month is free
Prices exclude VAT, which is added at checkout.
Same task. Same standard.
Whatever the model.
Tell us which work you want every AI tool to get right.