Manifest

Manifest is an open-source LLM (Large Language Model) router purpose-built for OpenClaw. If you rely on AI every day but watch your token bills climb, Manifest helps you take control by intercepting queries and routing each one to the most cost-effective model based on how complex the task actually is.

The savings can be substantial: users may cut token costs by up to 70% simply by letting Manifest pick the right model for each request. Despite this intelligent routing, queries are analyzed locally in less than 2ms, so latency stays minimal and your workflow never feels sluggish.

Privacy is a core design principle. Query scoring runs entirely on your own machine, and even the cloud version uses a blind proxy architecture, so your prompts are not exposed along the way.

Beyond routing, Manifest gives you full visibility into your AI spending. You can track costs in real time, set usage limits to avoid surprise bills, and export your data using the OpenTelemetry standard for easy integration with your existing monitoring stack.