⬢github Rust · 5.5K ★ +749 since we first saw it · pushed 20 h ago · Apache-2.0
xerj-org/xerj
XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. Elasticsearch compatible, so existing clients just work.
XERJ is a local search engine written in Rust that indexes code, docs, logs, and PDFs in a folder with one command, letting AI agents retrieve the exact snippets they need instead of reading files with grep. It combines BM25, vector, and hybrid search, works as agent memory, and speaks the Elasticsearch API so existing clients work unchanged.
Why now: It is trending for its claimed token savings (40x vs grep, 2.7x fewer output tokens in a coding-agent study) and its Elasticsearch-compatible, single-binary, zero-config positioning amid the agent-coding boom.
Who it is for: Developers using AI coding agents (Claude Code, Cursor) who want cheaper, token-efficient search over codebases and documents.
ai-searchai-search-algorithmsai-search-engineai-search-freeai-search-moduleai-search-optimizationai-searchenginebm25-searchelastic-searchelasticsearch
Stars over our 34 snapshots: 4.7K to 5.5K, since 1 d ago.
Where people talked about it
- ⬢github xerj-org/xerj just now
API: https://socialmediatrends-api.osmike.com/v1/repos/xerj-org/xerj