MirevoxGitHub (opens in a new tab)

Module 05 · Shared context index

runnable

Context Engine

Index once, reuse context across agents.

View on GitHub (opens in a new tab)

Runnable v0.1 slice available on GitHub — architecture and scope below.

Problem

An agent working across 15 repositories can spend more tokens rediscovering the codebase than answering the question. Every tool builds its own partial picture, then throws much of that work away.

Where it sits

Sits beneath agents and delivery modules as a shared index. It is meant to expose relevant context over MCP so each tool does not repeatedly scan the same repositories.

The Context Engine is designed for environments where a change may touch 15 repositories, shared libraries, architecture notes, and service contracts. It keeps an index that other modules and agents can query instead of repeatedly reading everything from scratch—so teammates are not re-burning tokens on the same corpus.

MCP is the access layer, not the product story. The useful part is a portable, inspectable context contract: what was indexed, where an answer came from, and which source should be opened when more detail is needed.

How it fits

This is the shared index that the other modules lean on. Stage Gate and Shadow Versioning can retrieve project material; agents calling through Smart Router can resolve service context without folding indexing into their own runtimes.

Capabilities