Why Manifest
Smart routing
Scores each query across 23 dimensions and picks the cheapest model that can handle it. Saves up to 90%.
Real-time dashboard
Track tokens, costs, messages, and model usage at a glance.
Set limits
Get notified or automatically block requests when spending exceeds a threshold.
How it works
Manifest intercepts each OpenClaw request, runs a scoring algorithm in under 2 ms, assigns a tier (simple / standard / complex / reasoning), and forwards the query to the matching model. All telemetry is captured via OpenTelemetry and displayed in the dashboard.Manifest vs OpenRouter
| Manifest | OpenRouter | |
|---|---|---|
| Open source | Yes | No |
| Self-hostable | Yes | No |
| Privacy | Metadata only (or 100% local) | Full request proxied |
| Routing logic | Transparent, 23-dimension scoring | Black box |
| Cost | Free | Per-token markup |
| Dashboard | Built-in | Separate |
| Works with OpenClaw | Native plugin | Requires config |
Privacy
- Local mode: All data stays on your machine. Nothing is sent anywhere.
- Cloud mode: Only OpenTelemetry metadata (model name, token counts, latency) is sent — never message content.
- Opt-out of analytics: Set
MANIFEST_TELEMETRY_OPTOUT=1to disable anonymous usage analytics.
Next step
Install Manifest
Get Manifest running in under a minute.