xerj-org/xerj
Indexes your codebase locally so agents search it instead of grepping file by file.
XERJ indexes a folder of code, docs, logs or PDFs into a local search engine an agent can query instead of grepping through files one by one. Its reference-coding mode clones and indexes open-source repos closest to your task so an agent reuses how they solved a similar problem before writing new code — in a controlled case study this cut a coding agent's output tokens 2.7x at the same 16/16 solve rate, with field reports of roughly 5x in everyday use. It's Elasticsearch-compatible, so existing clients work against it, and it's free and Apache-2.0 licensed — the only ask is one field-report PR back to the project.
What holds up
- +Cut a coding agent's output tokens 2.7x at the same 16/16 solve rate in a controlled study
- +Elasticsearch-compatible, so existing clients and tooling work against it without rewrites
- +Free, Apache-2.0 licensed binary — no subscription or usage fee
Mind the limits
- −The --insecure dev mode disables TLS and API-key auth — anyone reaching the port becomes superuser
- −Project asks every user for a field-report PR back — a usage obligation most free tools don't have
Picked here? Add the badge
Put it on your site. It links back to this page. Free for every listed product.
<a href="https://stillworks.dev/products/p/xerj-org-xerj/"><img src="https://stillworks.dev/badge/xerj-org-xerj.svg" alt="Picked by StillWorks" width="230" height="54"></a>