---
title: "Clips"
description: "Clips is an agent-native screen recording app that replaces Loom. The agent transcribes, titles, and summarizes every recording, edits it non-destructively when you ask, and makes shared clips readable by any agent."
search: "Clips screen recording Loom import video sharing transcript library non-destructive editing"
---

# Clips

Clips is an agent-native screen recording app. Record your screen and the agent transcribes, titles, summarizes, and indexes it into one searchable library, so you can ask "find the clip where we discussed the rollout plan" and search across every recording you've ever made. It replaces Loom with one app, so every recording you make lives in one searchable place you own, instead of a separate tool with its own transcript.

<Cards columns={1}>

### [Try it out now →](https://clips.agent-native.com)

See Clips live and record something real.

</Cards>

<Video
  src="https://cdn.builder.io/o/assets%2FYJIGb4i01jvw0SRdL5Bt%2Fbdf7739806a54c0e9e2852504c7ff922?alt=media&token=e13e8900-a337-4ff2-8ba6-13ca6764912a&apiKey=YJIGb4i01jvw0SRdL5Bt"
  alt="A brief tour of the clips application."
  caption="A brief tour of the clips application."
  autoplay={true}
  loop={true}
/>

The agent is a first-class editor across every recording, and everything you capture is yours, not a SaaS vendor's. Clips also makes a shared recording readable by any agent, not only its own. Pasting a clip's share link into Claude, ChatGPT, or another assistant lets it read the transcript and see timestamped screen frames without downloading raw video. See [Clips in a Multi-App Workspace](/docs/template-clips-integrations) for how that works.

## What it replaces

<Comparison>

### Before

- Loom for screen recordings
- A separate tool, or manual work, for transcripts, titles, and summaries
- Re-recording or re-uploading a clip just to get AI cleanup on it
- No way for an outside agent to actually understand what's in a recording

### After

- One recorder, with Loom import for anything you've already got there
- The agent titles, summarizes, and chapters every recording automatically
- Trim, remove filler words, or combine clips just by asking
- Share links that any agent can read, not only Clips' own

</Comparison>

## Clips in a multi-app workspace

If you run Clips alongside other apps in [Dispatch](/docs/template-dispatch), a recording stops being something you only watch by hand. Other apps can pull ready transcripts into Brain, hand a CRM automation a durable call-evidence link, or ask Clips' agent a question directly, the same way you would in chat. See [Clips in a Multi-App Workspace](/docs/template-clips-integrations) for how this works.

## What you can do with it

- **Record your screen or import from Loom.** Try "record my screen" or paste a public Loom link to bring it into your library. See [Create a clip](/docs/template-clips-features#create-a-clip).
- **Edit non-destructively through chat.** Try "remove the ums and uhs" or "trim the first 10 seconds." See [Non-destructive editing](/docs/template-clips-features#non-destructive-editing).
- **Share and protect what you record.** Set visibility, a password, or an expiry date, and let any agent read a shared clip's transcript. See [Share](/docs/template-clips-features#share).

## What's next

- [**Features**](/docs/template-clips-features) — recording, importing, editing, sharing, and insights, with setup steps for each
- [**Talk to the Agent**](/docs/template-clips-agent) — prompts by task and how the agent sees your screen
- [**Clips in a Multi-App Workspace**](/docs/template-clips-integrations) — agent-readable clips, Brain export, and CRM call evidence
- [**Developer Guide**](/docs/template-clips-developers) — quick start, actions, data model, and routes
- [**Embed Clips**](/docs/template-clips-embed) — add anonymous recording to another product
- [**Templates**](/docs/cloneable-saas) — the Cloneable SaaS model
- [**Getting Started**](/docs/getting-started) — the framework fundamentals: actions, application state, and live sync
- [**Context Awareness**](/docs/context-awareness) — how the agent knows the current clip and playhead
- [**Agent Teams**](/docs/agent-teams) — delegate transcript cleanup to a specialist sub-agent