File size: 8,893 Bytes
05be922 b38f5dc 281ef6a b38f5dc 281ef6a b38f5dc 281ef6a b38f5dc 281ef6a b38f5dc 281ef6a b38f5dc 05be922 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 | <!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="description" content="Map an agent-memory evaluation need to public papers, benchmarks, frameworks, and reproducible questions.">
<meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self'; style-src 'self'; img-src 'self' data:; connect-src 'self'; object-src 'none'; base-uri 'none'; form-action 'none'">
<title>Agent Memory Evaluation Map</title>
<link rel="icon" href="favicon.svg" type="image/svg+xml">
<link rel="stylesheet" href="styles.css">
<script src="app.js" defer></script>
</head>
<body>
<a class="skip-link" href="#evidence">Skip to evidence</a>
<header class="site-header">
<a class="brand" href="#top" aria-label="Agent Memory Evaluation Map home">
<span class="brand-mark" aria-hidden="true">M</span>
<span>Memory Evaluation Map</span>
</a>
<nav aria-label="Primary">
<a href="#evidence">Evidence</a>
<a href="#compare">Compare</a>
<a href="#recipe">Recipe</a>
<a href="SOURCES.md">Sources</a>
</nav>
</header>
<main id="top">
<section class="hero" aria-labelledby="hero-title">
<div class="hero-copy">
<p class="eyebrow">Public evidence · no ranking</p>
<h1 id="hero-title">What should your agent memory actually prove?</h1>
<p class="hero-lede">Start with the capability, not the architecture. Filter public artifacts, compare their evidence boundaries, then export the questions your evaluation must answer.</p>
<div class="hero-actions">
<a class="button primary" href="#evidence">Map the evidence</a>
<a class="button quiet" href="#recipe">Build a recipe</a>
</div>
</div>
<aside class="principle-card" aria-label="Core principle">
<span class="signal" aria-hidden="true"></span>
<p class="principle-label">The core distinction</p>
<p class="principle">“Not evaluated” is not “failed.” “Unknown” is not “absent.”</p>
<p class="principle-note">The map keeps evidence gaps visible instead of converting them into a score.</p>
</aside>
</section>
<section class="metrics" aria-label="Map summary">
<div><strong id="artifact-count">7</strong><span>public artifacts</span></div>
<div><strong id="target-count">8</strong><span>evaluation targets</span></div>
<div><strong>0</strong><span>composite rankings</span></div>
<div><strong id="verified-date">2026-09-20</strong><span>latest source update</span></div>
</section>
<section class="workspace" id="evidence" aria-labelledby="evidence-title" tabindex="-1">
<div class="section-heading">
<div>
<p class="eyebrow">01 · Find useful evidence</p>
<h2 id="evidence-title">Choose what you need to measure</h2>
</div>
<p>Results show scope and source boundaries, not recommendations.</p>
</div>
<div class="controls" aria-label="Evidence filters">
<label class="search-control" for="search">
<span>Search the map</span>
<input id="search" type="search" placeholder="Try temporal, graph, abstention…" autocomplete="off">
</label>
<label for="target-filter">
<span>Evaluation target</span>
<select id="target-filter">
<option value="all">All public evidence</option>
</select>
</label>
<label for="outcome-filter">
<span>Outcome level</span>
<select id="outcome-filter">
<option value="all">All outcome levels</option>
<option value="retrieval">Retrieval</option>
<option value="answer">Answer</option>
<option value="agent_task">Agent task</option>
<option value="mixed">Mixed</option>
<option value="unknown">Unknown / not evaluated</option>
</select>
</label>
<button class="button quiet reset" id="reset-filters" type="button">Reset filters</button>
</div>
<div class="result-toolbar">
<p id="result-summary" aria-live="polite">Loading public evidence…</p>
<div class="view-switch" role="group" aria-label="Evidence view">
<button class="view-button active" type="button" data-view="cards" aria-pressed="true">Cards</button>
<button class="view-button" type="button" data-view="matrix" aria-pressed="false">Matrix</button>
</div>
</div>
<div id="card-view" class="evidence-grid" aria-label="Evidence cards"></div>
<div id="matrix-view" class="matrix-wrap" hidden>
<table>
<caption>Source-backed comparison matrix. Scroll horizontally for all fields.</caption>
<thead>
<tr>
<th scope="col">Artifact</th>
<th scope="col">Memory unit</th>
<th scope="col">Time model</th>
<th scope="col">Update / conflict model</th>
<th scope="col">Outcome</th>
<th scope="col">Code</th>
<th scope="col">Dataset</th>
<th scope="col">License</th>
</tr>
</thead>
<tbody id="matrix-body"></tbody>
</table>
</div>
<div class="empty-state" id="empty-state" hidden>
<p>No artifact matches these filters.</p>
<button class="button quiet" type="button" id="empty-reset">Clear filters</button>
</div>
</section>
<section class="compare-section" id="compare" aria-labelledby="compare-title">
<div class="section-heading">
<div>
<p class="eyebrow">02 · Compare without flattening</p>
<h2 id="compare-title">Put two evidence boundaries side by side</h2>
</div>
<p id="compare-status" aria-live="polite">Choose up to two artifacts from the evidence cards.</p>
</div>
<div id="compare-grid" class="compare-grid">
<div class="compare-placeholder">Select an artifact</div>
<div class="compare-placeholder">Select a second artifact</div>
</div>
</section>
<section class="recipe-section" id="recipe" aria-labelledby="recipe-title">
<div class="section-heading">
<div>
<p class="eyebrow">03 · Make the evaluation reproducible</p>
<h2 id="recipe-title">Build an evaluation recipe</h2>
</div>
<p>Deterministic questions only. No generated vendor recommendation.</p>
</div>
<div class="recipe-layout">
<div class="recipe-builder">
<fieldset>
<legend>Capabilities in scope</legend>
<p class="field-help">Select one or more. The checklist updates immediately.</p>
<div id="recipe-targets" class="check-grid"></div>
</fieldset>
<label for="recipe-name">
<span>Evaluation name <small>(optional)</small></span>
<input id="recipe-name" type="text" maxlength="80" placeholder="e.g. Cross-session support agent">
</label>
<div class="export-actions">
<a class="button primary" id="download-markdown" href="#" download="agent-memory-evaluation.md">Download Markdown</a>
<a class="button quiet" id="download-json" href="#" download="agent-memory-evaluation.json">Download JSON</a>
</div>
</div>
<div class="recipe-output" aria-live="polite">
<div class="recipe-output-header">
<span>Evaluation checklist</span>
<span id="question-count">0 questions</span>
</div>
<ol id="recipe-questions"></ol>
</div>
</div>
</section>
<section class="method-note" aria-labelledby="method-title">
<p class="eyebrow">Interpretation guardrail</p>
<h2 id="method-title">Use the map to plan what to test.</h2>
<p>Reported outcomes remain attached to their original task, data, model, prompts, and system design. Follow the primary sources before citing or comparing a result.</p>
</section>
</main>
<footer>
<p>Public research map · source-check dates are shown on each card</p>
<p><a href="data/artifacts.json">Manifest</a> · <a href="data/schema.json">Schema</a> · <a href="SOURCES.md">Sources</a></p>
</footer>
<noscript>This map needs JavaScript for filtering, comparison, and recipe exports. The source manifest remains available at data/artifacts.json.</noscript>
</body>
</html>
|