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
fix(landing): bottom GET XERJ CTA was a dead link; now copies the prompt with visible feedback
xerj-orgb40019d521f6
diff --git a/landing/index.html b/landing/index.htmlindex 604ed090a..59079ed4d 100644--- a/landing/index.html+++ b/landing/index.html@@ -321,7 +321,7 @@ $ curl -sXPOST localhost:9200/_memory/agent-demo/_recall \</div></section>-<a href="#demo" class="cta">+<a href="#prompt" class="cta" id="ctaCopy" data-prompt="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."><span>GET XERJ</span><span class="arrow">↑</span></a>@@ -368,6 +368,21 @@ $ curl -sXPOST localhost:9200/_memory/agent-demo/_recall \}});}+ const cta = document.getElementById('ctaCopy');+ if (cta) {+ cta.addEventListener('click', () => {+ const label = cta.querySelector('span');+ const done = () => {+ const orig = label.textContent;+ label.textContent = 'PROMPT COPIED ✓';+ setTimeout(() => { label.textContent = orig; }, 1600);+ };+ const text = cta.getAttribute('data-prompt');+ if (navigator.clipboard && navigator.clipboard.writeText) {+ navigator.clipboard.writeText(text).then(done).catch(done);+ } else { done(); }+ });+ }})();</script>