AI News

Trending story

ArtCraft open-sources the Craft Anything tool

1 reports1 story updatesUpdated Nov 7 21:15

Understand this story

AI overview

On November 7, 2026, ArtCraft open-sourced the Craft Anything tool. The tool lets an Agent first collect information about a target's appearance, layout, and behavior, and then build its own version based on that; webpage inspection covers three screen widths. The project provides more than 300 tools, supports both the command line and the MCP interface, and can serve as a research toolbox for other Agents. The default clean-room mode uses only external information such as screenshots, visible text, and layout, and sets a tool whitelist, while the deep mode can analyze code, files, and webpage scripts. Currently, the build path invokes the locally logged-in Claude Code, with costs borne by the user, and image and 3D generation additionally require a fal key. The project uses a dual MIT / Apache-2.0 license, and adaptations such as Codex have not yet been verified in a real environment.

AI-generated from public reports

Latest development · Report

ArtCraft open-sources Craft Anything: research the target first, then have the Agent imitate it

Developments

1 confirmed developments

  1. ArtCraft open-sources the Craft Anything tool

    Source:Shao Meng

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 7

  1. Shao Meng

    ArtCraft open-sources Craft Anything: research the target first, then have the Agent imitate it

    ArtCraft, which previously open-sourced a full suite of Photoshop and Office tools, has open-sourced Craft Anything, letting the Agent first collect information about the target's appearance, layout, and behavior, and then build its own version based on that; the web page inspection covers three screen widths. The project provides more than 300 tools and supports both a command line and an MCP interface, so it can serve as a research toolbox for other Agents. The default clean-room mode uses only external information such as screenshots, visible text, and layout, and sets a tool whitelist, while the deep mode can analyze code, files, and web page scripts; currently the build path calls the locally logged-in Claude Code, with costs borne by the user, and image and 3D generation additionally require a fal key. The project uses a dual MIT / Apache-2.0 license, and adaptations such as Codex have not yet completed real-environment verification.

Related stories

  1. Related storiesThe DeepSeek Harness team shares its Super-agent design exploration
  2. Related storiesMiniMax Code team open-sources Agent workflow and Skills
  3. Related storiesShao Meng introduces how Graphify builds a persistent knowledge graph for the entire repository for coding agents to query
  4. Related storiesEnglish translation is being prepared.