Manifest

Route each query to the cheapest model on your machine

Manifest routes your AI requests to the most cost-effective model while keeping scoring on your machine. It intercepts each query, evaluates it locally in under 2 ms, and sends it to the right model to reduce costs and avoid overusing large models. You can track spending with a dashboard for costs, tokens, and alerts. Manifest exports telemetry via OpenTelemetry, offers a native OpenClaw plugin for quick installation, and is fully open source, allowing you to inspect, extend, or self-host.

More like Manifest

Startups doing something similar, featured in the last two years

Scan your live site for risks and get a clear security grade

Connect AI costs to Stripe revenue to see margins per customer

Track and optimize AI spend across providers, teams, and features

Turn receipts, email & photos into clean, tax-ready insights, automatically

Track AI costs by customer and feature to see real margins

Route any AI model through a self-hosted private P2P marketplace

The only MCP connecting AI agents to live travel data and checkout

AI SEO platform integrating AI visibility and SEO data into your AI agent

Add one line of code, Cut your AI bill by 40%

Optimize Amazon PPC profitably with transparent AI-powered bids

Build and run production AI agents via one API across LLMs

Run Claude Code and Codex 24/7 with SSH and a browser terminal on mobile

Visit website
Open page