Why I Spent a Year Building Sentinel-IR?

Description and use

Sentinel-IR offers a compact index of structured facts about a JavaScript codebase, reducing the need to repeatedly explain projects and saving tokens for AI agents.

Problem

AI agents lack concise context about codebases, leading to repeated rediscovery and wasted tokens and money.

Outcome

Sentinel-IR reduces the need to re-explain projects to new assistants and cuts token usage by providing a concise codebase index for AI agents.

Workflow

• Extract structured facts from the codebase
• Store facts in a searchable index
• Provide index to AI agents as initial context
• Agents use index to locate relevant code sections

Evidence

AI agents can write code, investigate bugs, and review projects. But giving them more tools doesn't automatically give them better context.

Sentinel-IR does something similar for JavaScript code. It extracts structured facts about a codebase so an AI agent can get an initial map before deciding what deserves deeper investigation.