What is Infa
Infa Chrome Extension
How to use and install our Chrome Extension
Community
Browse community design systems
Release Notes
Featuring the latest changes to keep you up-to-date
Research Program
Participate in shaping the future of Infa
SOC 2 Type II Compliance Badge
Enterprise Ready
SOC 2 Type II certified for enterprise-level security and compliance
EventsLearnPricing
Sign up for free

Feedback

Share your feedback

Close
Anonymous submissions are auto-posted to #feedback channel. You can also share directly in Slack.

Need help?

Reach out to contact@infa.ai or see docs

Navigation
Search...
⌘ K
Focus sentinel
Close

Search Documentation

PressESCto close
Focus sentinel
Infa Documentation
  • General Information
    • Boards
    • Components
      • Main Components Vs Component Views
      • Component Tagging
      • Component Anatomy
    • Labels
    • Teams
    • Authentication
    • Permissions
      • Inviting People to Teams
      • Inviting People to Boards
    • Billing & Subscription
      • Managing Subscription
      • Promo Code Activation
    • Data Import, Export & Sync
      • Local vs. Cloud Boards
  • App Blocks
    • Building App Blocks
  • Chrome Extension
    • Deep Links
    • Using Labels
    • Updating the Extension
  • Integrations
    • MCP Server
    • Claude Code Plugin
    • External API
    • Progressive Web App
    • Figma Plugin
    • Coda Pack
    • Overview
    • Managing Runs
    • Board Agents
    • Overview
    • Infa Capture
    • Installation
    • Authentication
    • Connect a Board
    • Run Modes
    • Hooks & Agents
    • File Sync
    • CLI Reference
Switch to Light theme
Switch to Dark theme
TermsPrivacyChat with Us
  1. Docs
  2. Integrations

Claude Code Agent Runners

How to connect a runner to your Infa board and let Claude Code agents execute tasks on your behalf.

This feature is available on all Infa plans (Free, Pro, and Enterprise).

Runners let you trigger Claude Code agent sessions directly from your Infa board — without leaving the browser. You write a prompt, start a run, and a connected runner picks it up, executes the task in your local repository, and streams progress back to the board in real time.

Copy link
How it works

infa.ai board (browser)
    │
    │  You create a run (queued)
    ▼
Supabase Realtime
    │
    │  Runner subscribes and picks up the run
    ▼
Infa CLI / Electron app (your machine)
    │
    │  Spawns a Claude Code session in your repo
    ▼
Claude Code agent
    │
    │  Edits files, runs commands, reports progress via hooks
    ▼
Supabase Realtime → back to your board

We at Infa designed runners so that Claude always has access to your actual filesystem — meaning it can read and modify real files, run your test suite, and commit changes to Git, just as it would in a normal Claude Code session. Everything it does streams back to your board live.

Copy link
What you need

Infa CLI (recommended)
Install the infa npm package and run infa preview from your repo folder. Lightweight, no UI required.
Infa Desktop App
The Infa Electron app includes a built-in runner. Sign in and select a board to connect automatically.

Both options run a local server on http://localhost:7100 that the board polls to detect runner status.

Copy link
Connect with Infa CLI

# 1. Install
npm install -g infa
# 2. Authenticate
infa auth
# 3. Link the board to your local repo
infa board
# 4. Start the runner
infa preview

Once running, the board shows a "Runner connected" indicator at b/{boardId}/runs. Any run you create is immediately picked up.

info icon
Keep it running

The runner only picks up queued runs while the process is active. Runs created while the runner is offline will queue and execute as soon as it reconnects.

Copy link
Connect with the Desktop App

  1. Download and install the Infa desktop app
  2. Sign in with the same account you use on infa.ai
  3. Open the app and select the board you want to work with
  4. The app starts the runner automatically — no extra steps needed

The board detects the connection within 30 seconds.

Copy link
Run configurations

Before starting runs, set up at least one run configuration on your board. A run configuration tells the runner which repository to use, which branch to base new work on, and what the agent is allowed to do.

Run configurations are managed per board. To create one:

  1. In your terminal, run infa board from your repo folder — this walks you through linking a repo and creates the first configuration
  2. Or open your board → overflow menu → Integrations to manage existing configurations

Each configuration stores:

FieldPurpose
Repository pathLocal folder the runner opens Claude Code in
Base branchGit branch new work branches off from
Branch prefixPrefix applied to auto-created branches (e.g. agent/)
PermissionsWhat Claude is allowed to do (read-only, edit files, run commands)

Copy link
Connection status

The Runs page (b/{boardId}/runs) always shows current runner status at the top:

  • Runner connected — a runner is active and will pick up new runs immediately
  • No runner connected — runs will queue; connect a runner to start execution

If you see "No runner connected" but your CLI is running, check that infa preview started without errors and that you are authenticated (infa auth --status).

Copy link
Next steps

Managing Runs
Start runs, track status, view logs, and open live Claude sessions
Board Agents
AI teammates defined in your repository that answer mentions and run blocks through your runtime
Hooks & Agents
How Infa reports Claude activity back to the board in real time
Run Modes
Difference between local, automated, and remote runs
Infa CLI Reference
Full command and flag reference

Content Feedback

Feedback on selected content

Close
Anonymous submissions are auto-posted to #feedback channel. You can also share directly in Slack.

Need help?

Reach out to contact@infa.ai or see docs