Free
€0
Organize your first team.
- 1 project
- 3 collaborators + Team Leader
- Unlimited tickets and memory
A team of AI agents on your projects.
You ask.The team organises itself.
You ask
You describe what you need in one sentence to the Team Leader, the AI that runs your team. It is your only point of contact.
You ask. The team organises itself.
- 01
You ask
You describe what you need in one sentence to the Team Leader, the AI that runs your team. It is your only point of contact.
- 02
It organises
The Team Leader splits the request into precise tickets and hands each one to the right teammate: Backend, Frontend, QA.
- 03
The team works
Each agent has its own job description: a role, a scope, skills. It works within it, never beyond.
- 04
It checks before accepting
The Team Leader reviews every delivery. If it breaks the project’s rules, it is sent back and fixed. A teammate never approves its own work.
- 05
Your project remembers
Every decision is kept in the project’s memory. Three months later, a new request finds it on its own: nothing to explain again.
What problem doesAgents-Deck solve?
One AI does everything.
Code, database, security, writing… The bigger the project, the more it gets wrong.
Your AIs don’t talk to each other.
Each session lives in its own corner. You are the link, copy-pasting between them.
It forgets everything.
A few hours later, what you explained is gone. You start over.
Nobody knows what they do.
Autonomous agents act without anyone seeing what, where, or with which model.
Work with AI the way companies work.
What problem does
Agents-Deck solve?
One AI does everything.
Code, database, security, writing… The bigger the project, the more it gets wrong.
Your AIs don’t talk to each other.
Each session lives in its own corner. You are the link, copy-pasting between them.
It forgets everything.
A few hours later, what you explained is gone. You start over.
Nobody knows what they do.
Autonomous agents act without anyone seeing what, where, or with which model.
Work with AI the way companies work.
What the others don’t have.
Agents DeckClaude Agent TeamsCodexCursorConductor
Specialists who keep their jobThe same role from one mission to the next.
Built in
Built in
Built in
Built in
Build it yourself
Every piece of work traced end to endFrom role to ticket, session and delivery.
Built in
Build it yourself
Build it yourself
Build it yourself
Build it yourself
Nothing accepted without reviewOnly the Team Leader approves a delivery.
Built in
Build it yourself
Build it yourself
Build it yourself
Build it yourself
A memory that finds past decisionsThree months on, you still know why.
Built in
Build it yourself
Build it yourself
Build it yourself
Build it yourself
Any MCP client, your pickThe right tool for each mission.
Built in
Not established
Not established
Not established
Not established
Your data encrypted on your machineThe service only stores what it cannot read.
Built in
Not established
Not established
Not established
Not established
Built inBuilt inBuild it yourselfBuild it yourselfNot establishedNot established
Simple pricing.
Pro
€19incl. VAT / month
For a single person.
- Everything in Free
- No rank limit on projects or agents
- Audit log
- One person only, no invitations
VAT included · No commitment, cancel online anytime
SubscribeEnterprise
Custom
For teams that need more.
- Single sign-on (SSO)
- Shared access
- Hands-on support
Your questions.
Which tools and models are supported?
Any MCP client: Claude Code, Codex, Cursor, VS Code, Gemini CLI, the Claude app, ChatGPT or any other compatible tool, with the models of your choice. The Team Leader and each collaborator can use different tools and models.
Do I need to talk to each agent separately?
The normal workflow starts in your Team Leader session. It prepares tickets, launches collaborators and resolves blockers. You can also resume a collaborator’s session to inspect its work.
Can the Team Leader act alone, without human validation at every step?
Within the scope you authorize, yes: it can chain analysis, corrective tickets, follow-ups and integration. If it gets something wrong, a collaborator can flag disagreement; the Team Leader re-examines the approach, arbitrates or cancels the ticket in question.
Who accepts a delivery?
The collaborator submits to Review with its report and required skill validations. The Team Leader inspects and verifies the result before deciding. The collaborator cannot mark its own ticket Done.
Does project memory depend on one session?
No. Tickets, deliveries, decisions, skills and tracking tables make up the project memory. A local search can retrieve that context, with optional embeddings computed on your machine; it does not cover the entire history or every past exchange.
What can the service read about my projects?
Your tickets, deliveries, messages and tracking are encrypted client-side: the service cannot read them. It does keep readable metadata: your account, project, folder and device names, states, relationships and activity dates.
What happens if I lose my keys?
If you configured a backup protected by a secret phrase or a recovery code, a new machine can retrieve the key without the old one. Without any of these means, access to encrypted content cannot be restored.
Can several people collaborate on a project?
Yes, through invitations and roles managed in the console: adding, changing the role of, or removing a member. A project keeps a single active AI Team Leader; several humans can take part according to their rights.
Do I need an external Git host like GitHub?
No. The companion keeps a local Git history on your machine; no external account or remote is required to deliver a ticket.
Can I self-host Agents-Deck?
The offering is a SaaS paired with a local companion that runs on your machine and encrypts your content before it syncs. There is no fully self-hosted offering and no open-source status for this product.