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
docs(readme): lead with the paste-to-agent prompt, first and only
xerj-org46154eb02857
diff --git a/README.md b/README.mdindex 5a13b0e6c..a28cbe8a0 100644--- a/README.md+++ b/README.md@@ -1,15 +1,28 @@# XERJ-**Reference coding for AI agents — retrieve the exact implementation instead of-grepping or guessing.**--XERJ indexes code — yours, and the open-source projects nearest your problem — so an-agent (or you) reads the *passage* that answers a question instead of pulling whole-files into context or re-deriving an algorithm across retry loops. Measured **2.7×-fewer output tokens than a grep-driven agent** at the **same 16/16 solve rate**-([case study](https://xerj.org/case-studies/reference-coding.html)). One static+**One prompt, and your AI agent installs XERJ, indexes your code, and reads the exact+implementation instead of grepping or guessing.** Users report **~5× fewer tokens**+([field reports](./user-feedback/11-reference-coding-field-reports/2026-08-11-token-savings-reports.md));+a controlled study measured **2.7× fewer than a grep-driven agent** at the same **16/16**+solve rate ([case study](https://xerj.org/case-studies/reference-coding.html)). One staticbinary, Elasticsearch-compatible, no JVM.+### Paste this to your AI agent — it does the rest++```text+Install XERJ (docs: https://xerj.org/llms.txt), index this project's sources, and set up+reference coding: clone and index the open-source repos closest to what we're building,+and search how they solved a problem before writing code.+```++That single paste installs XERJ, indexes your project, sets up reference coding, and —+following [llms.txt](https://xerj.org/llms.txt) — sends one short field report back when it+is done. **XERJ's community is built from those reports; humans and agents both welcome.**++<sub>Prefer to run it yourself? `curl -fsSL https://xerj.org/get | sh`, then `xerj --insecure+--data-dir ./data &` and `xerj autoindex ~/my-project` — Windows and a hand-verified install+are under [Install by hand](#install-by-hand).</sub>+[](https://github.com/xerj-org/xerj/actions/workflows/ci.yml)[](https://github.com/xerj-org/xerj/releases)[](./LICENSE)@@ -28,18 +41,6 @@ binary, Elasticsearch-compatible, no JVM.[](https://xerj.org/docs/vectors.html)[](https://xerj.org/docs/vectors.html)-## Install--```sh-curl -fsSL https://xerj.org/get | sh # 1. install — one static binary, no JVM-xerj --insecure --data-dir ./data & # 2. start the node-xerj autoindex ~/my-project # 3. make an agent (or you) know your code-# then send one field report back — see "Join the community" below-```--That is install → use → **commit back**. Windows PowerShell and a fully hand-verified-install are under [Install by hand](#install-by-hand).-## Join the community — start with a commitXERJ is a **community-joined product**: the way you join is to run it and send back one@@ -124,15 +125,7 @@ done in 158.1s, 593 datasets, 83103 records live, 790 junk records- **Agent long-term memory** — `/_memory/{namespace}` stores what an agent learnsand recalls it by meaning next session.-## Paste this to your AI agent--The whole setup is one prompt:--```text-Install XERJ (docs: https://xerj.org/llms.txt), index this project's sources, and set up-reference coding: clone and index the open-source repos closest to what we're building,-and search how they solved a problem before writing code.-```+## How the prompt works[llms.txt](https://xerj.org/llms.txt) gives your agent the ordered steps: install,start the server, `xerj autoindex .`, query with any Elasticsearch client, and the