Fast regex search: indexing text for agent tools
noor_z
14 points
2 comments
March 23, 2026
Related Discussions
Found 5 related stories in 95.7ms across 8,358 title embeddings via pgvector HNSW
- The future of code search is not regex – 100x faster than ripgrep neogoose · 14 pts · April 02, 2026 · 58% similar
- Chroma Context-1: Training a Self-Editing Search Agent philip1209 · 35 pts · March 26, 2026 · 53% similar
- Optimizing Content for Agents vinhnx · 25 pts · March 14, 2026 · 48% similar
- DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost Alifatisk · 507 pts · May 24, 2026 · 47% similar
- Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep Bibabomas · 261 pts · May 17, 2026 · 47% similar
Discussion Highlights (2 comments)
HeyMeco
Instant Grep 13ms vs 16.8s ripgrep seems very useful
rfw300
I don't understand why their "Instant Grep + roundtrip to us-east-1" is so slow. First of all, the round-trip latency should not be nearly so bad to us-east-1. But second, and much more importantly, the LLM runs in the cloud. Shouldn't you just situate the LLM, agent runtime, and regex index in the same region? Wouldn't that be faster than round-tripping to the user's local machine?