checking…
Select a project or create a new one.
Create a project in the Projects tab first — cards run against a project folder.
Create a plan to soundboard an idea.

Apps

Build, sign, archive and send every branded mobile app to its store from one place.

Google Play connections

Service-account keys stay on DevHub and are never written into the repository.

Android apps

One profile per branded MAUI project. Builds run sequentially on each project’s assigned agent.

Release history

Google review status refreshes automatically every two minutes.

AppVersionTrackStatusCreatedArtifact

Agents

PCs running the ClaudeLauncher agent app — projects are assigned to an agent, which runs the selected local AI CLI.
StatusNameCompanyMachineVersionClaude CLICodex CLIGemini CLIRunway JobsMax jobsWeightVoice operatorUsage (month / 5h)Last seen
Select or create a preset.
Loading dashboard…

Dashboard

Jobs, AI time, tokens & cost — per day, per project, per agent.

Tokens per day

All projects — hover a bar for the in/out/cost breakdown.

Jobs completed per day

Board cards finished — hover for AI time spent.

Projects

Jobs, tasks and AI time from the board · tokens & estimated cost from transcripts.
Project Jobs done Active Tasks AI time Tokens Tokens (all time) Est. cost

Agents

Card runs attributed to each agent PC.
Agent Jobs done Running now AI time Tokens in Tokens out Est. cost

Settings

Model lists per engine — these fill the model dropdowns on projects and cards. Neither CLI lists its own models, so you maintain them here.

Branding

Used on the dev hub, page titles, and platform emails.

Models

Use Ask agents to import any model IDs local CLIs can enumerate.

Claude models

Model IDLabel

Codex models

Model IDLabel

Gemini models

Model IDLabel
What each model is best for

AI fallbacks

When an AI/model is in cooldown on an agent, follow these rules until a usable model is found.
AIModelFallback AIFallback model

AssemblyAI transcription

AssemblyAI can transcribe one person as plain text or separate a multi-person recording into ordered Speaker A/B turns. Audio is sent only after you stop and confirm.
No key set — AssemblyAI transcription is unavailable.
Once AssemblyAI creates a transcript, the hub asks it to delete the transcript and uploaded audio immediately, including when transcription later fails.
Recent transcriptions: none since the hub started.

Duplicate detection

Optional. Add an Anthropic API key and an AI compares each new card against similar existing ones and flags genuine duplicates before they run. No key = duplicate detection is off (nothing gets flagged).
No key set — duplicate detection is off.
Usage & results
Every duplicate check this key ran — its reasoning and result.

Email (SMTP)

Outgoing mail server used for platform emails and developer invites. Admin only. No host set = outgoing email is off.
No host set — outgoing email is off.
Send a test email
Sends using the saved settings above — Save first if you just changed them.

Single sign-on (SSO)

Microsoft / Google sign-in for hub accounts. Configure a provider and its buttons appear on sign-in and registration; leave it blank and they stay hidden. Admin only.

Microsoft

Google

API endpoints

Enterprise LLM APIs. Anthropic-compatible = full Claude CLI on agents (chat + cards, enterprise billing). OpenAI-compatible = chat only, called by the hub.
NameTypeBase URLDefault modelKey

Container registries

Docker/OCI registries for container publishes. Connect one here (host + credentials, stored centrally), then pick it in a project's Container publish config. 🚀 Publish builds & pushes the image using these — no repo .pubxml needed.
NameHostUsernamePassword

Credentials

Store reusable secrets here, then assign them to cards. Keep names and descriptions free of secrets.

NameEnvironment variableDescriptionUpdated

Documents

Reference docs & protocols. Assign a doc to projects so the AI can consult it, or attach one to a card as the source of truth for that task.
TitleProjectsSizeUpdated
QUALITY CONTROL

Continuous testing

Every project. Every spare agent. A continuous cycle of testing, evidence and improvement.

Loading

Coordinator settings

Select a test project

Choose a project to view settings, findings, submissions and live activity.

PRODUCT DISCOVERY

Opportunities

Spare agents research the market, investigate useful ideas and prepare plans for your approval.

Loading

Research pool & review queue

Give agents product direction, then review their sources and proposed plans.

Security

NuGet and npm dependencies are checked after implementation runs and every Sunday at 03:00 (server time). Manual and weekly scans use the latest default branch. Failed or incomplete scans retain known findings.

Build feedback

Every round of a Chicane build feedback loop: what arrived, what was asked of the assistant, what it replied and what was answered. The correlation id matches the one on Chicane's Integrations tab. Kept for 90 days.

System users

Developers who use the hub. Until the first user is registered the hub is open; after that, sign-in is required. Each user is scoped to projects and granted action permissions.

NameEmailCompanyRoleProjectsPermissionsStatusLast login