This guide walks you through deploying your own instance of Open-Inspect using Terraform.
Important: This system is designed for single-tenant deployment only. All users share the same GitHub App credentials and can access any repository the App is installed on. See the Security Model for details.
Open-Inspect uses Terraform to automate deployment across three cloud providers:
| Provider | Purpose | What Terraform Creates |
|---|---|---|
| Cloudflare | Control plane, session state | Workers, KV namespaces, Durable Objects, D1 Database |
| Vercel | Web application | Project, environment variables |
| Modal | Sandbox execution infrastructure | App deployment, secrets, volumes |
Your job: Create accounts, gather credentials, and configure one file (terraform.tfvars).
Terraform's job: Create all infrastructure and configure services.
Create accounts on these services before continuing:
| Service | Purpose |
|---|---|
| Cloudflare | Control plane hosting |
| Vercel | Web application hosting |
| Modal | Sandbox infrastructure |
| GitHub | OAuth + repository access |
| Anthropic | Claude API |
| Slack (optional) | Slack bot integration |
# Terraform (1.5.0+)
brew install terraform
# Node.js (22+)
brew install node@22
# Python 3.12+ and Modal CLI
pip install modal
# Wrangler CLI (for initial R2 bucket setup)
npm install -g wranglerFork ColeMurray/open-inspect to your GitHub account or organization.
# Clone your fork
git clone https://github.com/YOUR-USERNAME/open-inspect.git
cd open-inspect
npm install
# Build the shared package (required before Terraform deployment)
npm run build -w @open-inspect/shared- Go to Cloudflare Dashboard
- Note your Account ID (visible in the dashboard URL or account overview)
- Note your Workers subdomain: Go to Workers & Pages → Overview, look in the bottom-right
of the panel for
*.YOUR-SUBDOMAIN.workers.dev - Create API Token at API Tokens:
- Use template: "Edit Cloudflare Workers"
- Add permissions: Workers KV Storage (Edit), Workers R2 Storage (Edit), D1 (Edit)
Terraform needs a place to store its state. We use Cloudflare R2.
# Login to Cloudflare
wrangler login
# Create the state bucket
wrangler r2 bucket create open-inspect-terraform-stateCreate an R2 API Token:
- Go to R2 → Overview → Manage R2 API Tokens
- Create token with Object Read & Write permission
- Note the Access Key ID and Secret Access Key
- Go to Vercel Account Settings → Tokens
- Create a new token with full access
- Note your Team/Account ID:
- Go to Settings (Account Settings or Team Settings)
- Look for "Your ID" or find it in the URL:
vercel.com/teams/TEAM_ID/... - Even personal accounts have an ID (usually starts with
team_)
- Go to Modal Settings
- Create a new API token
- Note the Token ID and Token Secret
- Note your Workspace name (visible in your Modal dashboard URL)
- Go to Anthropic Console
- Create an API key
- Note the API Key (starts with
sk-ant-)
Want to use your OpenAI ChatGPT subscription? See Using OpenAI Models for setup instructions (can be configured after deployment).
You only need one GitHub App - it handles both user authentication (OAuth) and repository access.
-
Go to GitHub Apps
-
Click "New GitHub App"
-
Fill in the basics:
- Name:
Open-Inspect-YourName(must be globally unique) - Homepage URL:
https://open-inspect-{your-deployment-name}.vercel.app(or your custom domain) - Webhook: Uncheck "Active" (not needed)
- Name:
-
Configure Identifying and authorizing users (OAuth):
- Callback URL:
https://open-inspect-{your-deployment-name}.vercel.app/api/auth/callback/github
Important: The callback URL must match your deployed Vercel URL exactly. Terraform creates
https://open-inspect-{deployment_name}.vercel.appwhere{deployment_name}is the unique value you set interraform.tfvars(e.g., your GitHub username or company name). - Callback URL:
-
Set Repository permissions:
- Contents: Read & Write
- Pull requests: Read & Write
- Metadata: Read-only
-
Click "Create GitHub App"
-
Note the App ID (shown at top of settings page)
-
Under "Client secrets", click "Generate a new client secret" and note the Client Secret
-
Scroll down to "Private keys" and click "Generate a private key" (downloads a .pem file)
-
Convert the key to PKCS#8 format (required for Cloudflare Workers):
openssl pkcs8 -topk8 -inform PEM -outform PEM -nocrypt \ -in ~/Downloads/your-app-name.*.private-key.pem \ -out private-key-pkcs8.pem
-
Install the app on your account/organization:
- Click "Install App" in the sidebar
- Select the repositories you want Open-Inspect to access
-
Note the Installation ID from the URL after installing:
https://github.com/settings/installations/INSTALLATION_ID
You should now have:
- App ID (e.g.,
123456) - Client ID (e.g.,
Iv1.abc123...) - Client Secret (e.g.,
abc123...) - Private Key (PKCS#8 format, starts with
-----BEGIN PRIVATE KEY-----) - Installation ID (e.g.,
12345678)
Skip this step if you don't need Slack integration.
- Go to Slack API Apps
- Click "Create New App" → "From scratch"
- Name it (e.g.,
Open-Inspect) and select your workspace
- Go to OAuth & Permissions in the sidebar
- Add Bot Token Scopes:
app_mentions:readchat:writechannels:historychannels:readgroups:historygroups:readreactions:write
- Click "Install to Workspace"
- Note the Bot Token (
xoxb-...)
Important: If you update bot token scopes later, you must reinstall the app to your workspace for the new permissions to take effect.
- Go to Basic Information
- Note the Signing Secret
Event Subscriptions require the Slack bot worker to be deployed first for URL verification. You'll configure this in Step 7b after running Terraform.
Generate these random secrets (you'll need them for terraform.tfvars):
# Token encryption key
echo "token_encryption_key: $(openssl rand -base64 32)"
# Repo secrets encryption key
echo "repo_secrets_encryption_key: $(openssl rand -base64 32)"
# Internal callback secret
echo "internal_callback_secret: $(openssl rand -base64 32)"
# NextAuth secret
echo "nextauth_secret: $(openssl rand -base64 32)"
# Modal API secret (use hex for this one)
echo "modal_api_secret: $(openssl rand -hex 32)"Save these values somewhere secure—you'll need them in the next step.
cd terraform/environments/production
# Copy the example files
cp terraform.tfvars.example terraform.tfvars
cp backend.tfvars.example backend.tfvarsFill in your R2 credentials:
access_key = "your-r2-access-key-id"
secret_key = "your-r2-secret-access-key"
endpoints = {
s3 = "https://YOUR_CLOUDFLARE_ACCOUNT_ID.r2.cloudflarestorage.com"
}Fill in all the values you gathered. Here's the structure:
# Provider Authentication
cloudflare_api_token = "your-cloudflare-api-token"
cloudflare_account_id = "your-account-id"
cloudflare_worker_subdomain = "your-subdomain" # from *.your-subdomain.workers.dev
vercel_api_token = "your-vercel-token"
vercel_team_id = "team_xxxxx" # Your Vercel ID (even personal accounts have one)
modal_token_id = "your-modal-token-id"
modal_token_secret = "your-modal-token-secret"
modal_workspace = "your-modal-workspace"
# GitHub App (used for both OAuth and repository access)
github_client_id = "Iv1.abc123..." # From GitHub App settings
github_client_secret = "your-client-secret" # Generated in GitHub App settings
github_app_id = "123456"
github_app_installation_id = "12345678"
github_app_private_key = <<-EOF
-----BEGIN PRIVATE KEY-----
... paste your PKCS#8 key here ...
-----END PRIVATE KEY-----
EOF
# Slack (leave as empty strings to disable Slack integration)
slack_bot_token = ""
slack_signing_secret = ""
# API Keys
anthropic_api_key = "sk-ant-..."
# Security Secrets (from Step 5)
token_encryption_key = "your-generated-value"
repo_secrets_encryption_key = "your-generated-value"
internal_callback_secret = "your-generated-value"
modal_api_secret = "your-generated-value"
nextauth_secret = "your-generated-value"
# Configuration
# IMPORTANT: deployment_name must be globally unique for Vercel URLs
# Use your GitHub username, company name, or a random string
deployment_name = "your-unique-name" # e.g., "acme", "johndoe", "mycompany"
project_root = "../../../"
# Initial deployment: set both to false (see Step 7)
enable_durable_object_bindings = false
enable_service_bindings = false
# Access Control (at least one recommended for security)
allowed_users = "your-github-username" # Comma-separated GitHub usernames, or empty
allowed_email_domains = "" # Comma-separated domains (e.g., "example.com,corp.io")Note: Review
allowed_usersandallowed_email_domainscarefully - these control who can sign in. If both are empty, any GitHub user can access your deployment.
Deployment requires two phases due to Cloudflare's Durable Object and service binding requirements.
Ensure your terraform.tfvars has:
enable_durable_object_bindings = false
enable_service_bindings = falseImportant: Build the workers before running Terraform (Terraform references the built bundles):
# From the repository root
npm run build -w @open-inspect/control-plane -w @open-inspect/slack-botThen run:
cd terraform/environments/production
# Initialize Terraform with backend config
terraform init -backend-config=backend.tfvars
# Deploy (phase 1 - creates workers without bindings)
terraform applyAfter Phase 1 succeeds, update your terraform.tfvars:
enable_durable_object_bindings = true
enable_service_bindings = trueThen run:
terraform applyTerraform will update the workers with the required bindings.
Now that the Slack bot worker is deployed, configure the App Home and Event Subscriptions.
The App Home provides a settings interface where users can configure their preferred Claude model.
- Go to your Slack App → App Home
- Under Show Tabs, toggle "Home Tab" to On
- Click Save Changes
- Go to your Slack App → Event Subscriptions
- Toggle "Enable Events" to On
- Enter Request URL:
(Replace
https://open-inspect-slack-bot-{deployment_name}.YOUR-SUBDOMAIN.workers.dev/eventsYOUR-SUBDOMAINwith your Cloudflare Workers subdomain and{deployment_name}with your deployment name from terraform.tfvars) - Wait for the green "Verified" checkmark
- Under Subscribe to bot events, add:
app_home_opened(required for App Home settings)app_mentionmessage.channels(optional - if you want the bot to see all channel messages)
- Click Save Changes
- Go to Interactivity & Shortcuts
- Toggle "Interactivity" to On
- Enter Request URL:
https://open-inspect-slack-bot-{deployment_name}.YOUR-SUBDOMAIN.workers.dev/interactions - Click Save Changes
In Slack, for each channel where you want the bot to respond:
- Type
/invite @YourBotName, or - Click the channel name → Integrations → Add apps
The bot only responds to @mentions in channels it has been invited to.
Terraform creates the Vercel project and configures environment variables, but does not deploy the code. You have two options:
# From the repository root (replace {deployment_name} with your value from terraform.tfvars)
npx vercel link --project open-inspect-{deployment_name}
npx vercel --prodNote: The Vercel project is configured with custom build commands for the monorepo structure. Terraform sets these automatically:
- Install:
cd ../.. && npm install && npm run build -w @open-inspect/shared- Build:
next build
- Go to Vercel Dashboard
- Find the
open-inspect-{deployment_name}project - Go to Settings → Git
- Click "Connect Git Repository" and select your fork
- Vercel will automatically deploy on push to main
Note: If you link Git, ensure the build settings match those configured by Terraform (Settings → General → Build & Development Settings).
After deployment completes, verify each component:
# Get the verification commands from Terraform
terraform output verification_commandsOr manually:
# 1. Control Plane health check (replace {deployment_name} and YOUR-SUBDOMAIN)
curl https://open-inspect-control-plane-{deployment_name}.YOUR-SUBDOMAIN.workers.dev/health
# 2. Modal health check (replace YOUR-WORKSPACE)
curl https://YOUR-WORKSPACE--open-inspect-api-health.modal.run
# 3. Web app (replace {deployment_name}, should return 200)
curl -I https://open-inspect-{deployment_name}.vercel.app- Visit your web app URL
- Sign in with GitHub
- Create a new session with a repository
- Send a prompt and verify the sandbox starts
Enable automatic deployments when you push to main by adding GitHub Secrets.
Go to your fork's Settings → Secrets and variables → Actions, and add:
| Secret Name | Value |
|---|---|
CLOUDFLARE_API_TOKEN |
Your Cloudflare API token |
CLOUDFLARE_ACCOUNT_ID |
Your Cloudflare account ID |
CLOUDFLARE_WORKER_SUBDOMAIN |
Your workers.dev subdomain |
R2_ACCESS_KEY_ID |
R2 access key ID |
R2_SECRET_ACCESS_KEY |
R2 secret access key |
VERCEL_API_TOKEN |
Vercel API token |
VERCEL_TEAM_ID |
Vercel team/account ID |
VERCEL_PROJECT_ID |
Vercel project ID (from project settings) |
NEXTAUTH_URL |
Your web app URL (e.g., https://open-inspect-{deployment_name}.vercel.app) |
MODAL_TOKEN_ID |
Modal token ID |
MODAL_TOKEN_SECRET |
Modal token secret |
MODAL_WORKSPACE |
Modal workspace name |
GH_APP_CLIENT_ID |
GitHub App client ID |
GH_APP_CLIENT_SECRET |
GitHub App client secret |
GH_APP_ID |
GitHub App ID |
GH_APP_PRIVATE_KEY |
GitHub App private key (PKCS#8 format) |
GH_APP_INSTALLATION_ID |
GitHub App installation ID |
SLACK_BOT_TOKEN |
Slack bot token (or empty) |
SLACK_SIGNING_SECRET |
Slack signing secret (or empty) |
ANTHROPIC_API_KEY |
Anthropic API key |
TOKEN_ENCRYPTION_KEY |
Generated encryption key (OAuth tokens) |
REPO_SECRETS_ENCRYPTION_KEY |
Generated encryption key (repo secrets) |
INTERNAL_CALLBACK_SECRET |
Generated callback secret |
MODAL_API_SECRET |
Generated Modal API secret |
NEXTAUTH_SECRET |
Generated NextAuth secret |
ALLOWED_USERS |
Comma-separated GitHub usernames (or empty for all users) |
ALLOWED_EMAIL_DOMAINS |
Comma-separated email domains (or empty for all domains) |
Once configured, the GitHub Actions workflow will:
- Run
terraform planon pull requests (with PR comment) - Run
terraform applywhen merged to main
To update after pulling changes from upstream:
# Pull latest changes
git pull upstream main
# Rebuild shared package if it changed
npm run build -w @open-inspect/shared
# Re-run Terraform (it only changes what's needed)
cd terraform/environments/production
terraform applyRe-run init with backend config:
terraform init -backend-config=backend.tfvars- Verify the private key is in PKCS#8 format (starts with
-----BEGIN PRIVATE KEY-----) - Check the Installation ID matches your installation
- Ensure the app has required permissions on the repository
- Verify the callback URL matches your deployed Vercel URL exactly
The callback URL in your GitHub App settings doesn't match your deployed URL. Update the callback
URL to match https://open-inspect-{deployment_name}.vercel.app/api/auth/callback/github.
# Check Modal CLI is working
modal token show
# View Modal logs
modal app logs open-inspectTerraform references the built worker bundles. Build them before running terraform apply:
# Build shared package first
npm run build -w @open-inspect/shared
# Build workers (required before Terraform)
npm run build -w @open-inspect/control-plane -w @open-inspect/slack-bot
# Verify bundles exist
ls packages/control-plane/dist/index.js
ls packages/slack-bot/dist/index.js- Verify Event Subscriptions URL is verified (green checkmark)
- Ensure the bot is invited to the channel (
/invite @BotName) - Check that you're @mentioning the bot in your message
- If you updated bot token scopes, reinstall the app to your workspace
If the bot doesn't see the original message when tagged in a thread reply:
- Verify the bot has
channels:historyscope (for public channels) andgroups:history(for private channels). These are required by theconversations.repliesAPI to fetch thread messages. - Verify the bot has
channels:readandgroups:readscopes. These are required byconversations.infoto fetch channel name and description for context. - If you added missing scopes, reinstall the app to your workspace for the new permissions to take effect.
This occurs on first deployment. Follow the two-phase deployment process:
- Deploy with
enable_durable_object_bindings = falseandenable_service_bindings = false - After success, set both to
trueand runterraform applyagain
- Never commit
terraform.tfvarsorbackend.tfvarsto source control - The
.gitignorealready excludes these files - Use GitHub Secrets for CI/CD, not hardcoded values
- Rotate secrets periodically using
terraform applyafter updatingterraform.tfvars - Review the Security Model - this system is designed for single-tenant deployment
For details on the infrastructure components, see:
- terraform/README.md - Terraform module documentation
- README.md - System architecture overview
- OPENAI_MODELS.md - Configuring OpenAI Codex models