Capabilities · Last updated July 11, 2026
Video analysis
for AI agents.
AnyCap lets an agent analyze one remote video or uploaded local recording with the video-read action. Add an instruction when the workflow needs a focused answer, then carry the returned content and request context into review, extraction, or the next automated step.
A recording is input, not a separate review queue.
The agent can inspect it before the workflow continues.
AnyCap turns video evidence into agent context.
The operational answer
Use video-read when an agent must inspect a recording, extract a useful finding, and keep that finding inside the active workflow.
01
The action accepts one video URL or one uploaded local file and an optional instruction or model.
02
The CLI returns analysis content with request context instead of exposing provider-specific response fields.
03
The same result can support quality review, content extraction, or a checkpoint before another agent action.
How video analysis fits the workflow
01 / Provide
Give the action one remote video URL or one local file. Local files are uploaded before analysis.
02 / Direct
Use --instruction when the agent needs a focused result such as a defect, event list, or checkpoint decision.
03 / Continue
Use the returned content in the next review, document, generation, or automation step and retain request context for support.
CLI usage and representative output
Analyze a remote video
anycap actions video-read --url https://example.com/demo.mp4Analyze a local recording
anycap actions video-read --file ./recording.mp4Ask a focused question
anycap actions video-read --url https://example.com/demo.mp4 --instruction "Identify the visible checkout defect"Representative successful response — 10 credits per request
{
"status": "success",
"content": "The recording shows the checkout modal clipping its submit button on a narrow viewport.",
"credit_cost": 10,
"request_id": "req_abc123"
}Three ways agents use video analysis
Quality review
Inspect a bug recording or recorded test session for visible defects, reproduction evidence, and UI behavior.
Content extraction
Turn a demo, walkthrough, or research clip into a summary, event list, or focused observation.
Workflow checkpoint
Confirm that a recorded step reached the expected state before the agent writes, routes, or generates the next artifact.
Continue the video workflow
Agent page
Video workflows for Codex
See how Codex discovers AnyCap actions and carries structured results into the next step.
Related capability
Video generation
Create or edit a clip, then use video analysis when the workflow needs to inspect it.
Implementation guide
Add video generation to an AI agent
Follow the schema-first generation flow and connect returned clips to review and delivery.
FAQ
What does the video-read action accept?
Provide either one --url or one --file. A local file is uploaded first and must be no larger than 100 MB. You can also add --instruction or select a model.
Why is the command named video-read?
video-read is the AnyCap action for analyzing video content. It sends the supplied video and optional instruction to the video read capability and returns the analysis as structured CLI output.
Which fields can the CLI return?
Every successful video-read request costs 10 credits and includes credit_cost: 10. The response also includes status and content; request_id appears when the server supplies one, and the top-level CLI normally adds trace_id. Additional operational fields may appear.
Can an agent ask a focused question about a recording?
Yes. Pass --instruction to request a specific observation, summary, event list, or review finding instead of a general description.
Turn the recording into a decision.
Equip the agent, provide a video, and keep the resulting evidence in the workflow that needs it.