Cursor Instant Grep Cuts Codebase Search from 16.8s to 13ms

Cursor

Apr 18, 2026 · Updated Apr 25, 2026

Regex searches in large codebases can take over 15 seconds, stalling AI agents mid-task. Cursor's Instant Grep indexes files locally, cutting latency to 13 milliseconds. Agents in big monorepos can now iterate without multi-second delays.

Cursor's Instant Grep is a client-side search index that speeds up regex queries in large codebases. It builds an inverted index using sparse n-gram decomposition — a variable-length indexing technique that minimizes posting lookups and narrows candidate files with high specificity. Queries that took 15 seconds in Chromium now complete in 13ms. The index syncs on Git commits, staying fresh without full rebuilds.

Keeping the index on the user's machine eliminates the network roundtrips that would otherwise slow every search. Since agents search constantly and often in parallel, this keeps Composer 2 running without stalls. The speed difference is most noticeable in enterprise monorepos.

Instant Grep is already shipped and works with Composer 2. Point your agent at a large codebase and let the index handle grep — the iteration loop is faster when search no longer introduces multi-second delays.

View the full update on cursor.com

Cursor

@cursor_aiMar 23

Cursor can now search millions of files and find results in milliseconds. This dramatically speeds up how fast agents complete tasks. We're sharing how we built Instant Grep, including the algorithms and tradeoffs behind the design. https://t.co/uzqMUgHvYn

300

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Cursor →

Keep reading

Cursor Reduces Desktop Application Memory Crashes by 80 Percent via Agentic Engineering

Cursor reduced desktop application memory crashes by 80% since February by implementing a dual-strategy debugging system that monitors memory pressure and automates fixes. As AI agents take on more complex tasks like web browsing and codebase indexing, the IDE must evolve from a text editor into a high-performance runtime.

Cursor Publishes CursorBench, Its Internal Agentic Coding Evaluation Methodology

OpenAIMar 15

Cursor Publishes CursorBench, Its Internal Agentic Coding Evaluation Methodology

Cursor published CursorBench, its internal eval suite that scores models on real coding agent tasks from actual developer sessions. Public benchmarks struggle to differentiate frontier models reliably — CursorBench produces more separation where it matters most.