DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to replace a headless Claude Code script with Maki with Maki

Run Maki without the UI and keep the same stream-json output your scripts already parse.

Short answer: Install Maki on the machine that runs your script; then Replace the agent call with Maki using --print --output-format stream-json; run the script on a test task and compare the output with the old run. All steps.

Who it is forA team with CI or automation built on Claude Code's print mode that wants to try another agent.

The problemSwitching agents usually means rewriting the parsing code around them.

The outcomeYour existing pipeline running Maki with compatible JSON output.

What you need first

  • Linux, macOS or Windows
  • An API key or sign-in for a supported provider, or a local Ollama or llama.cpp server
  • Optional: rtk installed for smaller bash output

Steps

  1. Install Maki on the machine that runs your script
  2. Replace the agent call with Maki using --print --output-format stream-json
  3. Run the script on a test task and compare the output with the old run
  4. Optionally turn on the OpenTelemetry export, which uses the same format as Claude Code's

Prompt for your agent

Change my <script> that runs Claude Code in print mode to call tontinton/maki with --print --output-format stream-json instead, run it on <test task>, and diff the outputs.

Caveat. This card is written from the tontinton/maki README, not from a test run by Deduped. Before you start, make sure you have Linux, macOS or Windows. Check the repo for newer instructions before you rely on these steps.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for tontinton/maki and "Replace a headless Claude Code script with Maki"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer