A memory layer that cuts Claude token use for coding agents
This is an open-source workflow for reducing how much of Claude’s a uses. The main idea is to avoid sending large parts of the codebase to Claude again and again. Instead, a local graph remembers the code structure and helps fetch only the code slices needed for the current task.
In the example given, token use dropped from 12.3 million tokens to 2.4 million tokens. That can let a Claude coding session run longer and lower the cost of repeated model calls. The workflow is available as a , so it can be adapted to other setups.
It is marked as advanced, so it likely needs setup work rather than being a simple plug-and-play tool.
Key points
- The workflow targets Claude and their limits.
- A local graph is used to find only the code slices needed for a task.
- The example claims token use fell from 12.3 million tokens to 2.4 million tokens.
- Lower token use can reduce cost and help sessions last longer.
- The tool is open source but described as advanced.