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
feat(case-study): homepage-matching gradient prompt card + HOW IT WORKS IN DEPTH
xerj-org2bc8c797170c
diff --git a/landing/case-studies/reference-coding.html b/landing/case-studies/reference-coding.htmlindex 5057599fa..6f5481fad 100644--- a/landing/case-studies/reference-coding.html+++ b/landing/case-studies/reference-coding.html@@ -11,7 +11,7 @@<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin><link href="https://fonts.googleapis.com/css2?family=Big+Shoulders+Display:wght@400;700;800;900&family=Inter:wght@400;500;600;700&family=IBM+Plex+Sans:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;700&display=swap" rel="stylesheet"><link rel="icon" href="data:image/svg+xml,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%230b0b0d'/><text x='50' y='68' font-size='60' font-family='Big Shoulders Display,sans-serif' font-weight='900' fill='%23ffc400' text-anchor='middle'>X</text></svg>">-<link rel="stylesheet" href="/style.css?v=cs0728">+<link rel="stylesheet" href="/style.css?v=if9"><style>/* three-arm bars — self-contained, robust to the shared 2-col grid */.arm3 { margin: 12px 0 6px; }@@ -67,10 +67,13 @@<!-- OPENER PROMPT --><section class="scene-section" style="border-top:0; padding-top:0;"><div class="opener">- <div class="lbl">◆ Paste this into Claude Code to turn it on</div>- <pre>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.</pre>+ <div class="prompt-stage" id="prompt" style="max-width:880px; margin:0 auto 18px;">+ <div class="prompt-card">+ <span class="prompt-label">PASTE THIS TO YOUR AI AGENT — IT DOES THE REST</span>+ <code>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.</code>+ <button type="button" class="prompt-copy" data-copy="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.">COPY THE PROMPT</button>+ </div>+ </div><div class="hint">That is the current one-line setup — <a href="https://xerj.org/llms.txt" rel="external" style="color:var(--accent);">llms.txt</a> walks the agent through the full loop. The measurement below ran the study's original long-form prompt.</div><div class="lbl" style="margin-top:18px;">◆ The exact prompt the study measured</div><pre>Set me up for reference-coding with XERJ and then use it automatically for the@@ -135,6 +138,43 @@ Do this proactively for the rest of the session without me asking again.</pre></div></div>+<!-- How it works, in depth -->+<section class="scene-section">+ <h2 class="scene" style="font-size:var(--fs-56);">HOW IT WORKS, <span class="accent">IN DEPTH.</span></h2>+ <ul class="deep">+ <li><strong>1 · The prompt resolves to llms.txt.</strong> The one-liner points the agent at+ <a href="https://xerj.org/llms.txt" rel="external">xerj.org/llms.txt</a> — ordered machine-readable steps:+ install from xerj.org/get, start the single binary, index, query over the Elasticsearch wire, and the+ reference-coding rules (retrieve before writing, cite what you use, respect licences).</li>+ <li><strong>2 · The corpus is chosen by problem domain, not language.</strong> The agent reads the project's+ dependencies and domains, picks the open-source repos that already solve those problems, and+ <code class="inline">xc-corpus.sh</code> shallow-clones them into a named corpus. Each repository's licence+ is recorded in <code class="inline">corpus.json</code>; GPL/AGPL entries are approach-only — read the design,+ never copy the code.</li>+ <li><strong>3 · Indexing is AST-aware.</strong> <code class="inline">xc-index.sh</code> runs+ <code class="inline">xerj autoindex</code>: every file is sniffed by content, and source files go through+ tree-sitter grammars (13 languages) that emit the language, every symbol with its kind and line number, a+ searchable <code class="inline">defs</code> field, and the full body. One index per dataset, incremental on+ re-runs — re-index when the references change.</li>+ <li><strong>4 · Retrieval is hybrid, with a stated fallback.</strong> <code class="inline">xc.py</code> runs+ BM25 <code class="inline">multi_match</code> over <code class="inline">body</code>,+ <code class="inline">defs</code> and <code class="inline">title</code> — with a measured (not hand-picked)+ boost on <code class="inline">defs</code> so exact symbol names outrank prose — RRF-fused with a vector arm+ where an index supports it. When no index does, it degrades to BM25-only and says so; a silently+ lexical-only "hybrid" would be a lie. The default embedder is lexical feature-hashing — vocabulary overlap,+ not neural understanding.</li>+ <li><strong>5 · The loop has discipline.</strong> Before writing non-trivial code against an unfamiliar API the+ agent retrieves, reads the returned definition with its <code class="inline">file:line</code>, adapts it,+ cites the source, and checks the licence. If nothing relevant comes back it says so and falls back to normal+ work — forcing a bad match in is worse than not retrieving.</li>+ <li><strong>6 · Why the tokens collapse.</strong> A retry loop on an unmemorised API burns <em>output</em>+ tokens — the kind priced 5× above input on Claude models. Grep recovery pulls source into context: up to+ <strong>1.06M input tokens</strong> on one corpus in this study. A retrieved passage is a few hundred tokens+ and carries the one thing a compiler can never leak — the runtime contract. The per-task table below shows+ the collapse: thousands of tokens from memory, hundreds with retrieval.</li>+ </ul>+</section>+<!-- Everything we built --><section class="scene-section"><h2 class="scene" style="font-size:var(--fs-56);">EVERYTHING WE BUILT <span class="accent">TO TEST IT.</span></h2>@@ -281,5 +321,20 @@ Do this proactively for the rest of the session without me asking again.</pre></footer><script src="/interact.js" defer></script>+<style>+ ul.deep { list-style:none; padding:0; max-width:900px; }+ ul.deep li { margin:14px 0; line-height:1.65; color:var(--z-mute); font-size:15px; }+ ul.deep li strong { color:var(--z-ink); }+ ul.deep code.inline { color:var(--z-ink); }+</style>+<script>+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('[data-copy]'); if (!btn) return;+ navigator.clipboard.writeText(btn.getAttribute('data-copy')).then(function () {+ var orig = btn.textContent; btn.textContent = 'COPIED';+ setTimeout(function () { btn.textContent = orig; }, 1400);+ });+ });+</script></body></html>