skills.rest
mnfst
mnfstOFFICIAL
Explore all skills by this author →
WebsiteGitHub

manifest

Route OpenClaw LLM requests to cost-effective models by query complexity.

7.4k|494|Updated Sep 27, 2022
Search Tags:#ai#llm#observability#router#cost optimization#openclaw
One-click install
npx skills add https://github.com/mnfst/manifest --skill manifest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: manifest
Source: https://github.com/mnfst/manifest/tree/main/skills/manifest
Command: npx skills add https://github.com/mnfst/manifest --skill manifest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill optimizes LLM request routing to significantly reduce costs and improve efficiency by directing queries to the most cost-effective model.

Core Features & Use Cases

  • Intelligent Routing: Automatically selects the best model based on query complexity and cost.
  • Cost Savings: Reduces LLM expenses by up to 70%.
  • Observability: Provides real-time dashboards for cost, token usage, and performance monitoring.
  • Use Case: An agent needs to perform a simple lookup and then a complex reasoning task. Manifest routes the lookup to a cheap, fast model and the reasoning task to a more powerful, albeit expensive, model, optimizing both cost and performance.

Quick Start

Install the manifest plugin for OpenClaw by running the command openclaw plugins install manifest.

Frequently Asked Questions about manifest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reduce LLM API costs by routing requests to cheaper models?▼

To reduce LLM API costs, intelligent routing analyzes query complexity and model pricing to direct simple lookups to cheaper models and complex reasoning to powerful ones, cutting expenses by up to 70%.

What is LLM observability and how does it monitor token usage?▼

LLM observability monitors token usage through real-time dashboards that track cost, token consumption, and performance metrics for routed requests across multiple LLM providers.

How do I install a smart LLM router for OpenClaw?▼

To install a smart LLM router for OpenClaw, run the command `openclaw plugins install manifest` to integrate intelligent routing and cost optimization into your agent workflows.

Does cloud mode for LLM routing require API key configuration?▼

Yes, cloud mode for LLM routing requires API key configuration and a gateway restart, whereas offline use relies on local configuration to manage request routing.

Can I use a single router for multiple LLM providers?▼

Yes, you can use a single router for multiple LLM providers because the system supports routing requests across different providers while optimizing for both cost and performance.

What are the limitations of using a cost optimization router for LLM requests?▼

Limitations include the necessity of a gateway restart and API key configuration for cloud deployments, plus the requirement of local configuration setups for offline use.

Related Skills

Explore More Software Engineering Skills→
AIAsysAIAsys
21

aiasys-llm-config

Validate and sync AIASys LLM configuration files and API keys.

Official
Intermediate
dkyazzentwatwadkyazzentwatwa
32

nav-stats

Generate session efficiency reports with token savings and cache performance metrics.

Community
Intermediate
alceupassosalceupassos

cli

Manage LobeHub services and automate tasks via command-line interface using Bun and Node.js.

Community
Advanced
Shakes-tzdShakes-tzd
3

Orchestrator Directives Skill

Delegate tasks across AI agents with cost-aware patterns and task IDs.

Community
Advanced