Skip to main content
Connectors let AMFS ingest events from external systems and turn them into structured memory entries that agents can query and learn from.

​
How It Works

  1. Enable a connector in Dashboard → Connectors
  2. Copy your webhook URL
  3. Paste it into the external system’s webhook settings
  4. Events flow in automatically — agents see them via search() and briefing()
Every event is validated, deduplicated, and transformed into versioned memory entries with proper entity paths and confidence scores.

​
Available Connectors

​
PagerDuty

Ingests incident lifecycle events: triggered, acknowledged, resolved. What it captures:
  • Incident title, severity, and status
  • Assigned responders
  • Service and escalation policy
  • Resolution notes
Entity path: incidents/pagerduty/{service_name} Setup:
  1. In AMFS Dashboard → Connectors, enable PagerDuty
  2. Copy the webhook URL
  3. In PagerDuty → Integrations → Generic Webhooks (v3), add the URL

​
GitHub

Ingests pull request events, deployment statuses, and issue updates. What it captures:
  • PR opened/merged/closed events with diff stats
  • Deployment success/failure with environment info
  • Issue state changes and label updates
Entity path: repos/{owner}/{repo} Setup:
  1. In AMFS Dashboard → Connectors, enable GitHub
  2. Copy the webhook URL and signing secret
  3. In your GitHub repo → Settings → Webhooks, add the URL with the secret

​
Slack

Ingests channel messages and thread context relevant to incidents or decisions. What it captures:
  • Messages from monitored channels
  • Thread context around incident discussions
  • Bot interaction logs
Entity path: comms/slack/{channel} Setup:
  1. In AMFS Dashboard → Connectors, enable Slack
  2. Copy the webhook URL
  3. In your Slack app → Event Subscriptions, add the URL

​
Jira

Ingests issue transitions, sprint events, and release notes. What it captures:
  • Issue status transitions (e.g., In Progress → Done)
  • Sprint start/complete events
  • Release creation and deployment tracking
Entity path: projects/jira/{project_key} Setup:
  1. In AMFS Dashboard → Connectors, enable Jira
  2. Copy the webhook URL
  3. In Jira → System → Webhooks, add the URL

​
Direct Event Ingestion

For any system that doesn’t have a built-in connector, push events directly via the REST API: 
curl -X POST https://amfs-login.sense-lab.ai/api/v1/events \
  -H "Content-Type: application/json" \
  -H "X-AMFS-API-Key: <your-api-key>" \
  -d '{
    "source": "monitoring",
    "entity_path": "myapp/checkout",
    "key": "high-cpu-alert",
    "value": {"host": "prod-3", "cpu_percent": 95},
    "event_type": "alert.triggered"
  }'
Events are stored as shared memory entries with agent_id="external/{source}", visible to all agents and automatically included in Cortex digest compilation. Use this for:
  • Monitoring alerts (Datadog, Grafana, custom)
  • CI/CD pipelines reporting deployment status
  • Cron jobs pushing periodic metrics
  • Any system with an outgoing webhook

​
Webhook Authentication

All webhook endpoints require your API key. Include it as a header when configuring webhooks in external systems: 
URL:    https://amfs-login.sense-lab.ai/api/v1/webhooks/pagerduty
Header: X-AMFS-API-Key: <your-api-key>
AMFS also validates the source system’s signature (e.g., PagerDuty’s X-PagerDuty-Signature, GitHub’s X-Hub-Signature-256) using the signing secret configured in Dashboard → Connectors.

​
Verifying Events

After configuring a webhook, trigger a test event from the external system and check that it arrived: 
curl "https://amfs-login.sense-lab.ai/api/v1/entries?entity_path=incidents/pagerduty" \
  -H "X-AMFS-API-Key: <your-api-key>"
Or check the Dashboard → Memory Explorer to see incoming entries in real-time.