agent-mediaGenerate AI-powered videos and images from the terminal using the `agent-media` CLI.
Install via ClawdBot CLI:
clawdbot install nevo-david/agent-medianpm release: https://www.npmjs.com/package/agent-media-cli
agent-media cli github: https://github.com/gitroomhq/agent-media
official website: https://agent-media.ai
Generate AI-powered videos and images from the terminal using the agent-media CLI.
The agent-media CLI must be installed and authenticated:
npm install -g agent-media-cli
agent-media login
Verify with agent-media whoami. If not logged in, run agent-media login and follow the OTP flow.
| Slug | Name | Type | Notes |
|------|------|------|-------|
| kling3 | Kling 3.0 Pro | Video | text-to-video/image-to-video, 5-10s, 1080p |
| veo3 | Veo 3.1 | Video | text-to-video/image-to-video, 4-8s, up to 4K |
| sora2 | Sora 2 Pro | Video | text-to-video/image-to-video, 4-25s, 1080p |
| seedance1 | Seedance 1.0 Pro | Video | text-to-video/image-to-video, 2-12s, 1080p |
| flux2-pro | Flux 2 Pro | Image | text-to-image |
| flux2-flex | Flux 2 Flex | Image | text-to-image |
| grok-image | Grok Imagine | Image | text-to-image |
# Video generation
agent-media generate kling3 -p "A robot walking through a neon-lit city" --sync
# Image generation
agent-media generate flux2-pro -p "Cyberpunk samurai portrait" --sync
# Image-to-video (provide input image)
agent-media generate seedance1 -p "Make it dance" --input ./photo.jpg --sync
# With options
agent-media generate sora2 -p "Ocean waves at sunset" -d 10 -r 1080p --aspect-ratio 16:9 --sync
Flags:
-p, --prompt — Generation prompt (required)-d, --duration — Video duration in seconds-r, --resolution — Output resolution (720p, 1080p)--aspect-ratio — Aspect ratio (16:9, 9:16, 1:1, etc.)--input — Input image for image-to-video--sync, -s — Wait for completion and print the output URL--json — Output as JSON (for parsing)# Credit balance
agent-media credits
# Current plan
agent-media plan
# Job status
agent-media status <job-id>
# List recent jobs
agent-media list
agent-media list --status completed --limit 5
# List all models
agent-media models
# Detailed pricing
agent-media pricing
agent-media pricing --model kling3
# Download a completed job
agent-media download <job-id>
# Retry a failed job
agent-media retry <job-id>
# Cancel a running job
agent-media cancel <job-id>
# Delete a job
agent-media delete <job-id>
agent-media whoami # Current user
agent-media credits # Credit balance
agent-media plan # Current subscription
agent-media subscribe # Interactive plan/credits menu (waits for confirmation)
agent-media subscribe --plan starter # Subscribe to a plan directly
agent-media subscribe --credits 500 # Buy a credit pack directly
agent-media subscribe --manage # Open Stripe billing portal
agent-media apikey list # List API keys
agent-media apikey create # Create new API key
agent-media subscribe opens Stripe Checkout in the browser then polls for up to 2 minutes until the payment is confirmed, showing the new plan/credits on success.--sync when you want to wait for the result and get the output URL.--json when you need to parse the output programmatically.agent-media credits before generating to ensure sufficient balance.--sync flag prints the public URL of the completed media.Generated Mar 1, 2026
Marketing teams use agent-media to quickly generate custom video and image assets for campaigns, such as promotional clips or branded visuals, directly from their development or content workflows. It streamlines production by allowing on-demand generation without specialized design software.
Online retailers employ the tool to create AI-generated product images or short videos showcasing items in various settings, enhancing listings without costly photoshoots. This enables rapid prototyping and A/B testing of visual content to boost sales.
Educators and e-learning platforms generate instructional videos or illustrative images from text prompts to support course materials, making content creation more accessible and scalable. It reduces reliance on external video production resources.
Creative professionals use agent-media to produce initial video and image concepts for client pitches or storyboards, accelerating the ideation phase. It allows rapid iteration based on feedback before committing to full-scale production.
Offer tiered subscription plans with monthly credits for video and image generation, targeting individual creators and businesses. Revenue is generated through recurring payments, with upsells for additional credits or premium models like Sora 2 Pro.
Sell credit packs that users purchase as needed for generating media, appealing to occasional users or those with variable workloads. Revenue comes from one-time credit sales, with potential bulk discounts to encourage higher spending.
Provide API access to the generation models for integration into custom applications or platforms, charging based on usage volume or through enterprise contracts. This targets developers and large organizations needing scalable AI media solutions.
💬 Integration Tip
Integrate agent-media into CI/CD pipelines for automated asset generation, using the --json flag to parse outputs programmatically and the --sync flag to wait for results in scripts.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection