Fast regex search: indexing text for agent tools · Cursor

How we're building indexes for regular expression search so agents can find text in large monorepos without the 15-second ripgrep waits.

Blog / research Time is a flat circle. When the first version of grep was released in 1973, it was a basic utility for matching regular expressions over text files in a filesystem. Over the years, as developer tools became more advanced, it was gradually superseded by more specialized tools. First, by roughly syntactic indexes such as ctags . Later on, many developers moved to specialized IDEs for specific programming languages that allowed them to navigate codebases very efficiently by parsing and building syntactical indexes, often augmented with type-level information. Eventually this was s

saved by

• Yudhister Joel Kumar
• Kushal Thaman
• Tracy Tsoi

related reading

• Regular Expression Matching with a Trigram Indexswtch.com
• The technology behind GitHub’s new code search - The GitHub Bloggithub.blog
• The technology behind GitHub’s new code search - The GitHub Bloggithub.blog
• Faster phrase search with shingled bloom filters in Brainstorebraintrust.dev
• Optimizing Postgres Text Search with Trigrams - Alex Klibiszalexklibisz.com
• Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval | Cognitioncognition.ai
• The Anatomy of a Search Engineinfolab.stanford.edu
• string - Data structure for fast full text search - Stack Overflowstackoverflow.com
• GitHub - thesephist/monocle: Universal personal search engine, powered by a full text search algorithm written in pure Ink, indexing Linus's blogs and private note archives, contacts, tweets, and over a decade of journals.github.com
• Create an advanced search engine with PostgreSQL | xataxata.io
• Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
• Home | infini-graminfini-gram.io