Space Context for developers

Your agents know your code, your documents and your calendar. They know nothing about the places you live and work in. Film a space once, and they know it too.

Space Context turns a video of a physical space (a flat, a holiday rental, an office, a van, an appliance) into a structured Space Document: every area, every item and where it is, its condition, what is broken, where the water shut-off and the fuse box are, how things work, with the original video frames as evidence. You read it, search it and ask it questions from your code, from the terminal or from an AI assistant.

Three ways in

	Best for	Start here
MCP server	Giving Claude (or any MCP client) read access to your spaces	Connect an assistant
CLI	Scanning a video and exporting an Agent Skill from the terminal	Install the CLI
API and SDK	Building it into your product	API overview, TypeScript SDK

All three use the same account as the Space Context iPhone app, and the same API keys from the console.

What you can do

• Scan a video (MP4, MOV, M4V up to 500 MB and 20 minutes) or up to 120 photos. The analysis runs on our side; no ffmpeg needed. → Scans
• Read a space as JSON, by section. → The Space Document
• Search across all your spaces, in any language: "where did I see a ladder?" → Search and ask
• Ask one space a question and get a short answer with its sources and photos, or "not documented". → Search and ask
• Compare two scans of the same space: items added, removed, moved, issues new or resolved. → Skills and comparisons
• Export a space as an Agent Skill folder that any agent can read. → Use a space in Claude Code
• Get notified when a scan completes or fails. → Webhooks

Try it for free

A test key (sc_test_…) runs every flow for free on a hand-made demo space: scans complete instantly, nothing is charged and no real data is involved. Create one in the console and follow the quickstart.

Your first live scan is free as well. After that, live scans are paid from a prepaid balance: see Billing.