AI-native video & docs

Make videos and docs with Claude

decodx gives your AI agent a real video skill and an MCP server. Describe what you want — it authors the spec, renders the video, and writes the matching guide, the same way every time.

For your AI agent

Connect this MCP

Paste into Claude, Codex, Cursor, Gemini, or ChatGPT.

Raw capture
decodx result

Drag to compare — raw capture vs. decodx render

For every team that has to explain software

Developer relationsProduct marketingCustomer educationSales enablementSupportEngineering
How it works

From recording to finished video

01

Record or point at clips

Bring a screen recording, a slide deck, or clips you already have. Captures are cached, so you record once.

02

Author the spec

Scenes and narration live as plain text you can review in a pull request — no timeline to scrub.

03

Render deterministically

decodx adds narration, captions, chapters, and branding, then renders the same way every time.

04

Tweak and re-render free

Change one scene; cached assets are reused and only what changed rebuilds — in seconds.

Everything you need

A video engine, built like a build tool

Video as code

Author a video the way you author source. It lives in your repo and reviews like a diff.

Deterministic renders

The same spec and assets always produce the same MP4. No model in the render loop.

Free re-renders

Content-hash caching means iterating costs seconds, not another export.

Captions & chapters

Accurate burned-in captions and chapter markers, generated from your narration.

A guide with every video

The same render produces a written step-by-step article from the exact clips it used.

Agent-ready & safe

Non-interactive commands, schema-validated JSON, and spend gated behind approval.

Your next product video is one spec away

Hand it to your agent or author it yourself — decodx renders it the same way, every time.