BasedLabs

Ask an agent to

• Generate an image of a neon city at night
• Swap my face into this photo
• Turn this script into a voiceover

8 tools

When we loaded basedlabs.ai again on Oct 24, 2026, it registered these through navigator.modelContext or provideContext(), from earlier WebMCP drafts. Chrome 154 only offers document.modelContext, so Chrome’s own agent support does not see them.

• edit_photo

  Edit or enhance a photo with AI.

  prompt: string

• face_swap

  Swap faces in a photo or video.

  prompt: string

• generate_avatar

  Create an AI-generated avatar or profile picture.

  prompt: string

• generate_image

  Generate an AI image from a text prompt.

  prompt: string

• generate_video

  Generate a video from a text prompt.

  prompt: string

• generate_voice

  Generate speech audio from text.

  prompt: string

• remove_watermark

  Remove watermarks or objects from an image.

  prompt: string

• virtual_try_on

  Try on clothing virtually using a photo.

  prompt: string