The index for AI agents
RepoQL indexes your repository into a living graph — every file, symbol, and relationship — so agents understand in seconds what used to take thirty tool calls.
One index, four senses
Every file is pre-parsed into three levels — a one-line headline, its structure, its content. Agents spend tokens only on what matters.
Hybrid lexical + semantic search over everything. The landscape, ranked by meaning — before committing to read anything.
A single method body. A line range. A glob across every file. Progressive detail that honors a token budget exactly.
SQL over the whole graph — code, git history, parsed data files. What calls what; what depends on what.
A synthesized answer with citations, drawn from up to 50k tokens of source the agent never had to hold.
Progressive disclosure
Every file is pre-computed at three levels — a one-line headline, its structure, its full content. The token budget decides which one you get; the address never changes.
An agent scans a thousand headlines to know what exists, narrows to twenty structures to see the shape, and reads three bodies to understand — never opening a file it didn't need.
Try the tabs. Same file, three bets.
What the agent sees
Everything is addressable. Files, symbols, line ranges, globs — one URI scheme across your repo, imported repos, and the docs themselves.
Ask for every Service member's signature across the codebase and the index answers from what it already knows — nothing is opened, nothing is wasted.
The risk is asymmetric. A bad query costs 1,500 tokens. A good one saves 50,000.
Works where your agent works
One long-lived host per machine. Agents connect and disconnect freely; the index is always warm.
22 format families
Code, data, documents — parsed to symbols and structure, not just text. Even the PDFs.