DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let an AI agent create and edit images on your machine with Kokon

Connect Claude or Cursor to Kokon's built-in MCP server so the agent can generate and edit images locally.

  • Content
  • Advanced
  • 45 minutes
  • From the README
  • Claude Code
  • Cursor

Who it is forA developer or content operator whose AI coding or chat agent needs to produce or revise images as part of a workflow, without sending files to a cloud image service.

The problemAgents can write text but cannot make or edit images, and cloud image APIs send prompts and pictures off the machine.

The outcomeAn agent that creates or edits images through Kokon, with the files written to the user's own computer.

What you need first

  • Windows 10 64-bit or later, an Apple M1 or newer Mac on macOS 15 or later, or x86-64 Linux
  • A graphics card with 12 GB VRAM or more (NVIDIA recommended), or an Apple Silicon Mac with 16 GB unified memory or more
  • 15 GB of free disk space (25 GB recommended) and about 12 GB of model downloads on first run
  • A photo to edit, or a sentence describing the image to create

Steps

  1. Install Kokon and finish the model setup, following the Install section of the README.
  2. Open the AI agents section of the Kokon README to find the MCP server and local HTTP API details (inferred: the README links to this section from its header).
  3. Add the Kokon MCP server to your agent's MCP configuration, using the server details from that section. (inferred, check the README)
  4. Restart the agent and confirm that the Kokon tools are listed.
  5. Ask the agent for one new image and one edit of an existing photo, then open the results in Kokon's gallery to check them.

Prompt for your agent

Using the Kokon MCP server in this repo (GabrieleLozupone/kokon), edit the image at <image path> with the instruction '<edit description>' and save the result to <output folder>. Expected output: the path of the new image file. Verify that the file exists and that its dimensions match the source image.

Caveat. The README names the MCP server and local HTTP API but does not show their setup commands or tool names in the visible text, so the agent must read the AI agents section before configuring anything.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page