agnes-quota-router

Routes image and video generation requests to Agnes AI and all other tasks to DeepSeek.

Updated Jul 6, 2026
One-click install
npx skills add https://github.com/Lucien-1127/strata-skill --skill agnes-quota-router-lucien-1127
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agnes-quota-router
Source: https://github.com/Lucien-1127/strata-skill/tree/main/agnes-quota-router
Command: npx skills add https://github.com/Lucien-1127/strata-skill --skill agnes-quota-router-lucien-1127

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Managing a limited Agnes AI quota (1,500 requests per 5-hour sliding window) requires strict routing so that only image and video generation consume Agnes tokens, while text, reasoning, code, and vision tasks use DeepSeek instead. ## Core Features & Use Cases - 2-Tier Request Routing: Forces image generation (text-to-image, image-to-image) and video generation (text-to-video, image-to-video) through Agnes, and sends everything else to DeepSeek. - Quota Monitoring: Integrates with a cronjob-based API status monitor that alerts when quota drops below 300 (warning) or 100 (critical). - Modular Key Management: Stores provider keys separately in ~/.hermes/env/ files (agnes.env, deepseek.env) sourced automatically via .bashrc. - Use Case: When generating a 5-second animation, the router sends the text-to-image step to Agnes Image 2.1 Flash, feeds the resulting public URL into Agnes Video V2.0 for image-to-video, and polls the task status until completion. ## Quick Start Route my request to generate an image with Agnes and handle all my text and code questions with DeepSeek.

Frequently Asked Questions about agnes-quota-router

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

FAQPage Schema
How do I route image and video generation to a specific AI provider?▼

Classify each incoming request by task type: send image generation, image editing, and video generation to Agnes AI, and route text, reasoning, code, and vision analysis to DeepSeek. This ensures only multimodal output consumes the limited Agnes quota.

How to generate video from an image with the Agnes Video API?▼

First generate an image with Agnes Image 2.1 Flash to get a public platform-outputs URL, then POST that URL as the image parameter to /v1/videos with model agnes-video-v2.0. Poll GET /agnesapi?video_id=<ID> until status is completed.

Does the Agnes video API accept Base64 image input?▼

No, the video API rejects Base64 Data URIs for image-to-video; the image parameter must be a single publicly accessible URL string. The image API, by contrast, accepts Base64 Data URIs in its extra_body.image array.

Why did my Agnes API request fail with an external image URL?▼

External CDN URLs such as Wikimedia may be rejected by the Agnes image API. Use a Base64 Data URI for image-to-image, or use the platform-outputs URL returned by Agnes text-to-image for image-to-video pipelines.

What are the frame count limits for Agnes video generation?▼

The num_frames parameter must follow the 8n+1 rule with a maximum of 441 frames. At 24fps, 121 frames yields about 5 seconds and 441 frames yields about 18 seconds of video.