AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
title: "How do I search a folder of PDFs?" target_format: pdf evidence:
- claim: "pdf.rs extracts text from PDF files during autoindex" source: "engine/crates/xerj-autoindex/src/extract/pdf.rs"
- claim: "autoindex walks a local filesystem and types each file" source: "engine/crates/xerj-autoindex/src/lib.rs"
How do I search a folder of PDFs?
Point xerj autoindex at the directory. XERJ types each file, extracts the text
with its PDF extractor, and writes one searchable document per file on a
single-node install.
xerj autoindex ./papers
Query it over the Elasticsearch-shaped API on the same box. There is no crawler and no object-store reader: the files must already be on local disk.