> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getjumper.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Using Jumper with local LLM agents

> Run an AI agent entirely on your own machine and let it search, review, and edit your footage through Jumper.

An AI agent can do the legwork in Jumper. It finds the shots, checks whether they are any good, and builds a timeline from what it picked.

Run that agent on your own computer and nothing goes to a cloud AI service, with no subscription to pay for. Your footage, your transcripts, and the agent's tool calls all stay on your machine.

## What you need

<Steps>
  <Step title="Jumper, running">
    With [media analyzed](/core-concepts/processing), so there is something to search.
  </Step>

  <Step title="An agent app">
    This is the program you actually chat with. Pick one below.
  </Step>

  <Step title="A model">
    Downloaded inside the agent app. It needs **Tool Use** to operate Jumper, and ideally **Vision** so it can look at your footage.
  </Step>
</Steps>

## Choose your agent app

<CardGroup cols={2}>
  <Card title="Bionic" icon="https://mintcdn.com/jumper/Y28CyRKYcGf2dmI_/images/agent_icons/bionic_icon_color.avif?fit=max&auto=format&n=Y28CyRKYcGf2dmI_&q=85&s=ea75b9f29c503abf50efc801fbe8a4e0" arrow="true" href="/guides/bionic" width="256" height="256" data-path="images/agent_icons/bionic_icon_color.avif">
    **Recommended.** Built for agent work, and it sees your footage out of the box. The least setup.
  </Card>

  <Card title="LM Studio" icon="https://mintcdn.com/jumper/Y28CyRKYcGf2dmI_/images/agent_icons/lmstudio_icon_color.avif?fit=max&auto=format&n=Y28CyRKYcGf2dmI_&q=85&s=6e13d1e49f8549d46649f561af467068" arrow="true" href="/guides/lm-studio" width="256" height="256" data-path="images/agent_icons/lmstudio_icon_color.avif">
    A chat app with a large model library. More setup, and it needs a hand to look at shots.
  </Card>
</CardGroup>

<Note>
  Bionic and LM Studio are made by the same team, and they share settings and downloaded models. You can install both and switch between them without redoing anything.
</Note>

## What the agent can do

* Search your footage by what it looks like, by what is said, and by who is on screen
* Look at the frames it found and judge whether they actually match
* Export clips, or read a timeline out of your NLE and send an edited one back

For the full picture, see [Agentic video editing](/core-concepts/agentic-editing). To try it on real footage, follow the [agentic editing tutorial](/tutorials/agentic-editing).

## Local or cloud?

Local models are free and private, but a local model is only ever as good as your hardware allows. Cloud agents like Claude and Codex are stronger and faster, at the cost of a subscription and sending your prompts off the machine.

Jumper works the same way with both, since it is the same set of tools either way. To use a cloud agent instead, see [the agent settings](/interface/settings-tab#ai-agent).

<Card title="Agentic editing and data privacy" horizontal arrow="true" icon="lock" iconType="regular" href="/core-concepts/agentic-editing-privacy">
  What stays local and what the model actually receives
</Card>