DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to shrink what your agent reads: logs, test output and web pages with Caveman

Turn on the read-less rocks so tool output and pages come back compressed before they hit the context.

Short answer: Install with npx @caveman-ai/cli@latest; then check what is on with caveman status; turn a feature off if it gets in the way, for example caveman off browse. All steps.

Who it is forSomeone whose agent context fills up with test logs and HTML.

The problemLong command output and pages eat the context window and push out what matters.

The outcomeFewer input tokens per session, with `caveman status` showing what is active.

What you need first

  • A coding agent such as Claude Code, Codex or Gemini CLI
  • Node.js for the npx installs (22.13+ for the all-agents installer)

Steps

  1. Install with npx @caveman-ai/cli@latest
  2. Check what is on with caveman status
  3. Turn a feature off if it gets in the way, for example caveman off browse
  4. Compare session token counts before and after

Prompt for your agent

Set up JuliusBrussee/caveman's CLI, show me caveman status, and measure input tokens for one full test-fix loop on this repo with and without it.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for JuliusBrussee/caveman and "Shrink what your agent reads: logs, test output and web pages"

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