Who it is forA developer whose agent sessions burn through tokens by reading whole files.
The problemAgents that read entire files and call tools one by one fill the context window fast and cost more.
The outcomeA coding agent that reads file skeletons first and batches tool calls, with full visibility into what it reads.
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
- Download the installer with
curl -fsSL https://maki.sh/install.sh -o install.shand read it withcat install.sh - Run it with
chmod +x install.sh && sh install.sh, or usebrew install maki - Set your provider key, for example OPENAI_API_KEY or GEMINI_API_KEY
- Start Maki in your project and give it a task; watch the index tool read skeletons before full files
Prompt for your agent
Install tontinton/maki, configure it with <provider>, and run it on <repo> to <task>. Report how many lines it read and which tools it used.
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 "Install Maki and cut the tokens your coding agent spends"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer