Overview

Agentic Search answers questions about your code and the work that produced it. One query returns the commits and sessions behind a change alongside the matching code. Search runs on a dual engine:

• Semantic search matches meaning and keywords across commits and sessions, surfacing the reasoning behind a change.
• Code Search finds literal text such as function names, error messages, and configuration keys. It is symbol-aware, with definitions and references.

entire.io searches every repository you can access. The Entire CLI starts with the current repository and widens with --repo or --all-repos. Search reads Entire’s indexes, not your local working tree. See What Is Indexed and When for what it covers and when new work shows up.

​

Benefits of Using Search

• Ask why code is the way it is and get the commit, session, and prompt behind it, not just the lines that changed.
• Find precedent in repositories your agent has never cloned.
• Answer in fewer turns than cloning and grepping take, leaving more context window for the task.
• Find literal source text across your repositories in one query.

We benchmarked those claims. On nine engineering-history questions from our own repositories, run ten times each, an agent with Search answered 81 of 90 correctly. The same agent working from full Git history and the GitHub CLI answered 70 of 90, using more than twice the tokens and twice the steps. These questions come from our own history rather than a public corpus. The harness, tasks, grading, and per-run results are at entireio/searchmark, so you can rerun it against your own organization.

​

How to Use Search

See Use Search with Your Coding Agent for the Skill that runs these queries on your agent’s behalf.

​

Continue With