Crawler, index and ranking rebuilt for AI scale: 100B+ documents, <250ms p95 (US East), from $1 / 1K requests @ 100 RPS+. API, MCP and CLI on one key
Point-in-time web search and page fetch over a frozen archive. Query the web as it existed on any past date, reproducibly.
Open-source incremental data framework for AI agents. Keep codebases, docs, and knowledge continuously indexed — fresh context, zero re-processing. Python API.
The Exa Web search API retrieves the best, realtime data from the web for your AI
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.