Toggle can do a lot. This page walks you through each feature so you can turn on exactly what you want — from basic recall to full autopilot.
Sign up at x.toggle.pro, install the Chrome extension, then go to clawbot-integration to generate your key.
Add the key to your OpenClaw settings. Set it in your config file under skills.entries.toggle.apiKey or export it as TOGGLE_API_KEY.
Add the Toggle skill to your Claw. Once installed, say anything about your work and it'll fetch your context automatically.
Your Claw will configure everything. Never paste your key in a public channel.
Each feature builds on the last. Start with what feels right and add more as you get comfortable.
No setup needed beyond the API key. Just start asking.
You can change the time anytime. Just say “change my digest to 8 PM.”
Activated automatically once auto-sync is running and history builds up. Say “I dropped that” to dismiss a project permanently.
Requires auto-sync to be running. The longer it runs, the better the pattern detection gets.
Predictions activate automatically once 5 days of data exist. They self-correct — predictions you ignore get retired silently. Say “stop predicting” to pause for 7 days.
Four ready-made configurations depending on how much you want your agent to do.
Context when you ask for it. Nothing proactive.
Auto-sync + daily digest. Fresh context and a summary every evening.
Everything proactive — nudges, focus alerts, pattern detection.
Everything on. Your agent learns your routines and anticipates what's next.
All of these are adjustable. Tell your agent to change any setting, or edit state.yaml directly.
| Setting | Default | What it controls |
|---|---|---|
| digest_time | "18:00" | When the daily digest fires. 24h format. |
| nudge_stale_hours | 48 | Hours of inactivity before a project is flagged as stale. |
| focus_alert_threshold | 30 | Focus score below this triggers a context-switch alert. |
| focus_alert_window_min | 20 | Minutes of scattered behavior before alerting. |
| pattern_detection_days | 7 | Days of history scanned for repeating workflows. |
| pattern_min_occurrences | 3 | How many times a workflow must repeat before suggesting automation. |
| prediction_min_days | 5 | Minimum days of data before predictions activate. |
| prediction_confidence_min | 3 | Minimum occurrences of a routine before it becomes a prediction. |
| timezone | null | Your local timezone. Set once — used for all timestamps and scheduling. |