recallbench 0.4.0

A universal benchmark harness for AI memory systems
Documentation
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>RecallBench</title>
    <link rel="stylesheet" href="/static/style.css">
</head>
<body>
    <header>
        <h1>RecallBench</h1>
        <p>Universal AI Memory System Benchmark</p>
    </header>
    <nav id="nav">
        <a href="#" onclick="showDashboard()" class="active">Dashboard</a>
    </nav>
    <main id="content">
        <div id="dashboard">
            <h2>Benchmark Runs</h2>
            <div id="runs-list">Loading...</div>
        </div>
        <div id="run-detail" style="display:none">
            <h2 id="run-title"></h2>
            <div id="metrics-section"></div>
            <h3>Questions</h3>
            <div id="questions-controls">
                <label><input type="checkbox" id="show-failures-only" onchange="filterQuestions()"> Show failures only</label>
                <select id="type-filter" onchange="filterQuestions()"><option value="">All types</option></select>
            </div>
            <table id="questions-table">
                <thead><tr><th>ID</th><th>Type</th><th>Correct</th><th>Ground Truth</th><th>Hypothesis</th></tr></thead>
                <tbody id="questions-body"></tbody>
            </table>
        </div>
    </main>
    <script src="/static/app.js"></script>
</body>
</html>