Capabilities · Last updated August 5, 2026
AI video analyzer
for AI agents.
AnyCap is an AI video analyzer for agent workflows. Give video-read one URL or local recording and ask a specific question; it returns text the agent can use, such as reproduction evidence from a bug recording, key events from a demo, or a checkpoint before the next action.
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.
Use a focused instruction
Ask for the evidence you actually need: visible defects, timestamps, event order, or a concise summary. A narrow instruction produces a more useful result than a generic request to analyze the video.
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.
Checked in the current CLI · CLI verified August 5, 2026
Video analysis accepts a URL or a local file.
We checked the video-read help output in AnyCap CLI 0.6.0. It accepts one remote URL or one local file, plus an optional instruction for a focused answer. This confirms the command interface; the example analysis elsewhere on this page remains illustrative.
Remote input
One video URL
Local input
One uploaded video file
Instruction
Optional focused analysis prompt
Successful request
10 credits
Why AnyCap maintains this catalog
Models change. The agent workflow should not need rebuilding every time they do.
AnyCap keeps model discovery, supported modes, authentication, execution, and output delivery behind one agent-facing interface. The model still does the generation or analysis; AnyCap carries the operational work around it so an agent can choose a valid option today and switch when the catalog changes tomorrow.
anycap actions video-read --helpHow 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 architecture
Put video understanding inside the harness
Keep reasoning and media analysis separate: the harness exposes the capability, while the agent decides when the workflow needs it.
Claude Code workflow
Can Claude analyze videos?
See the practical URL and local-file workflow, focused instructions, and limits before using video evidence in a Claude Code task.
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.
Ask the recording a useful question.
Provide the video, name the evidence you need, and pass the answer to the review or task that prompted it.