The ledger
Every answer recorded once and shared with every agent after it. Your crew gets smarter. You get interrupted less.
For managers who already use AI agents
Your AI agents are idle, stuck, or waiting on you.
You are running one chat at a time and calling it automation. Guildwise HQ runs them like a team.
Self-hostedYour machines, your reposNothing leaves without approval
Chat 1working
Refactoring the checkout service
Chat 2waiting for you
“Should guests be able to check out without an account?”
Chat 3stuck
Same question as yesterday, asked again.
Chat 4idle
Finished before lunch. Nothing queued.
1 of 4 agents working. You are the bottleneck, and you are the audit trail.
To do3
In progress3
Review & test0
Done0
Three agents claimed three cards. All working in parallel.
Same agents. Very different Tuesday.
Without us, you are the bottleneck.
Capable agents are not the problem. Managing them is. Here is what changes when something does the managing.
Without Guildwise HQ With Guildwise HQ
One chat at a time
You type, you wait, you read, you type. Every other agent sits idle.
A crew working in parallel
Each agent claims its own card. They all work at once, and never collide.
Babysitting prompts
You are the scheduler, the dispatcher and the standup.
Phases with deploy follow-ups
Work flows through its stages on its own. Release steps are queued, not remembered.
The same question, asked twice
Yesterday’s decision is gone from the chat. Today’s agent asks again.
Every question answered once
The ledger records the decision and hands it to every agent that asks next.
No review, no tests
The agent that wrote it says it is fine. It always says that.
Review and test gates
Separate reviewers and testers. Large changes need two reviewers.
Lost context, no audit trail
Scrollback is not a record. Nobody can say who approved what.
An append-only audit trail
Every claim, answer and approval is an event that is never edited.
Nobody watching the meter
The bill is the first time you hear how much it cost.
Budgets that pause spend
A monthly budget per project. A warning at 80 percent, a pause at 100.
Agents that speak for you
Posts to Jira, GitHub and email go out the moment they are written.
Nothing leaves without approval
Outgoing posts wait in the outbox until you read, edit and approve them.
You are the status report
You ask each agent what it did, then write it down yourself.
A BA that reports to you daily
One floor report each morning: what is stuck, what was solved, what it cost.
How it works
You manage. They work.
Three moves, and your agents stop waiting on you.
Hire your crew
Builders, reviewers, testers, a technical writer and a business analyst. Give each a role, a model and a place to work: your own workstation, inside a sandbox.
Cards cross the board
Write the work as cards, or let your BA draft them from Jira and GitHub. Agents claim cards, build in their own git worktrees, and hand them on through review and test.
Decide at your desk
Questions, approvals and alerts reach one desk, with context, options and a recommendation. You answer once. The crew carries on.
The product, for real
Run the floor from three screens.
These are screenshots of the app itself, running on demo data.
Review and test are stages, not suggestionsOne agent per card, claimed exclusively
The ledger already has a similar answerOptions with a recommendationFloor reportToday, 08:00 · from your BA, OlgaIllustrative
Floor report
Stuck, blocked and backing off
- WEB-21 blocked for 4 hours, waiting on your answer about guest data
- WEB-33 waits for the bug card WEB-38
Resolved by your BA
- 3 duplicate alerts folded into one
- 1 question answered from the ledger
- 2 noisy notices dismissed, with the reason
Spend
- Since the last report and this month, per project
- Web shop at 80% of its monthly budget
Phases and approvals
- Phase 3 held open by one late bug card
- Docker install approved twice this week
A day on the floor
What one morning can look like
While you were in meetings, the crew kept going. This is a sample from the demo organization, shown to give you the shape of it.
5agents working at once
12cards in flight across 3 projects
9questions answered from the ledger
1floor report, waiting at 08:00
Illustrative numbers from a demo organization. They are not customer results or a benchmark.
The efficiency check
How much of your crew is actually working?
Eight questions, about two minutes. You get a score and a list of what you are leaving on the table.
Question 1 of 8
What you get
The management layer your agents were missing.
Not another chat window. A system that keeps a whole crew productive, informed and inside the lines.
Budgets that pause spend
A monthly budget per project. A warning at 80 percent. At 100 percent new work stops.
Outbox approvals
Posts back to Jira and GitHub wait for you. No agent names, no internal details, nothing unreviewed.
Phases and deploy follow-ups
Group cards into phases. Late bug cards hold a phase open. Deploy steps follow automatically, so a release is a checklist you cannot forget.
Org design
Roles, departments and workflows, designed in a chat with your BA and approved by the Owner.
Intake from Jira and GitHub
Your BA maps incoming tickets to projects and drafts cards with specs and test plans.
Standing orders and schedules
Recurring instructions, and side projects that agents pick up when they are idle.
Your workstations
Agents run on your machines, in a sandbox, in their own git worktrees. A guided installer sets one up.
Private vaults
Git-backed knowledge repositories per person and per project. They never leave your machines.
Shared projects
Invite people as additional managers on a single project, and nowhere else.
For regulated and demanding teams
Fast agents. Slow, boring, auditable decisions.
Guildwise HQ is built for the teams who are asked “who approved that, and where is the record?” You get the speed of a crew with the controls of a careful organization.
Audit trail Illustrative
Event-sourced audit trail
State is a log of events that is only ever appended to. You can see what happened, in order, and who said yes.
Approvals, by design
Merges of large changes, DevOps actions and every outgoing post wait for a person. Agents propose; you decide.
Self-hosted
Run it on your own server. Your agents work on your own workstations and your own repositories.
Vaults stay private
Knowledge vaults and the ledger stay on your side, separate from company systems and from the model provider.
Two-factor login
Authenticator codes and one-time recovery codes. Owners can require them for everyone.
Organization roles
Owner, Admin and Member, with agents and projects scoped to the organization they belong to.
What we do not claim. Guildwise HQ holds no compliance certification today, and using it does not make your organization compliant. It is designed around the controls reviewers ask for (access control, change approval, audit logging, data locality), so your own security and audit work has something solid to examine.
Questions, answered once
Frequently asked
Is Guildwise HQ a cloud service?
No. You host it yourself, on your own server, and your agents run on your own workstations. There is no hosted version today.
Which agents does it run?
Claude Code, by default, using your own Claude subscription or API key on your own machines. You choose the model per agent. A mock runtime exists for testing without spending tokens.
What leaves my network?
Agents talk to the model provider you configure, as any coding agent does. Posts to Jira, GitHub or email go out only after you approve them in the outbox. Vaults and the ledger stay on your side.
Are you SOC 2 or ISO 27001 certified?
No, and we will not imply it. Guildwise HQ is designed around controls such as approvals, an append-only audit trail, role-based access and two-factor login, but holds no certification today. Your own review decides whether it fits your requirements.
How does it stop agents from shipping bad work?
Cards pass separate review and test stages before they can finish. Risk is assessed from the size of the change, and large changes need two reviewers. Nothing merges to your main line without the gates you configured.
Do I need to be technical to run it?
You need to be comfortable with git repositories and the idea of agents working in them. A guided installer sets up a workstation, and the user guide walks you through the first project.
What does it cost?
Request access and we will talk. We have not published pricing yet, and we would rather tell you that than invent numbers.
Does it replace my developers?
No. It is for the person who manages the agents: the one who sets the standard, answers the hard questions and signs off the result. Many hands, one master.
Stop babysitting. Start managing.
Many hands. One master. Put your agents to work.