- Home
- Skills
- APIs & Backend
- agnes api
agnes api
Works with the AI Agents you already use
agnes api
Python client for AGNES API image and video generation with automated polling, key rotation, and content pipelines.
$1
agnes api
Example session with this skill installed
Create a 4-second 16:9 video of a futuristic neon city in the rain using text-to-video mode and save it to the default video directory.
- Read your context and instructions
- Compiled the agnes api
I have initiated the video generation task for the futuristic neon city. The request has been sent to the AGNES API, and I am now polling the task status.
Task Summary:
- Model: agnes-video-2.5-flash
- Mode: text
- Parameters: 16:9, 720P, 4 seconds
- Local Path:
~/agent/media/videos/agnes-video-1715832000.mp4
Video Generation Log
| Stage | Status | Detail |
|---|---|---|
| API Request | Success | Task ID: vid_8f2k9s01am2 |
| Queuing | Completed | Position in queue: 2 |
| Processing | Completed | Rendering frames at 720P |
| Polling | Success | Status: completed |
| Download | Success | File saved to ~/agent/media/videos/ |
Next steps
- Run
@scripts/query_video.py --task_id vid_8f2k9s01am2if you need to re-verify the metadata. - Use the generated video as a
first_frameinput for@scripts/keyframes.pyto extend the animation. - Apply
@scripts/i2i.pyto a captured frame if you want to generate matching promotional images.
Connects securely to your tools. The creator never sees your data.
About this skill
Generating high-quality visual assets through APIs is often plagued by complex polling logic, key rotation, and strict parameter constraints. This skill provides a production-ready Python interface for the AGNES API, handling media generation workflows from basic text-to-image to complex multi-step video pipelines.
What it does
- Image Generation produces visual assets using the
agnes-image-2.5-flashmodel with support for specific aspect ratios and resolutions up to 4K. - Video Synthesis handles asynchronous task creation and polling for
agnes-video-2.5-flash, including text-to-video and image-to-video modes. - Advanced Editing enables image-to-image refinement, multi-image composition, and consistent character anchoring for comic generation.
- Content Pipelines automates specialized formats like ink-wash style poem recitations, multi-character story videos, and historical news clips.
- Client Management implements automatic API key rotation and request retries to handle rate limits and service availability.
How it works
- Configuration requires placing API keys in
~/.config/agnes/paths.yamland verifying them with the provided validation script. - Initialization uses the unified
AgnesClientto handle authentication and low-level HTTP transport. - Execution triggers specific scripts like
t2v.pyfor video orcompose.pyfor image layering based on the desired output. - Polling monitors the asynchronous video task status from
queuedtocompletedbefore downloading the final file to local media directories.
Frameworks & tools
Python-based client utilizing urllib, ffmpeg for video processing, and edge-tts for audio synthesis.
Why this beats prompting it yourself
Writing raw API calls for asynchronous video tasks requires manual polling loops and error handling for 429 rate limits. This skill abstracts that complexity into a robust client that manages state, file downloads, and directory organization automatically.
Use cases
- Generate consistent comic strips with character anchoring and speech bubbles.
- Create automated 9:16 social media videos with synchronized TTS and subtitles.
- Upscale and refine existing images using style transfer and quality enhancement.
- Batch process video clips from static image assets for content marketing.
Known limitations
Video generation is restricted to 720P resolution and requires up to 5 minutes per segment. Flash models support a maximum of five reference images and three audio tracks.
Video limited to 720P. Polling required for async tasks. Flash model limits: 5 images/3 audios max. i2v speed is approx 5 mins per segment.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 15 days ago
Requires
Permissions
Allowed Hosts