Gde05 commited on
Commit
13532ce
·
verified ·
1 Parent(s): cd631b6

Stat band: the tile counts leaderboard arms, not an official run that does not exist

Browse files
Files changed (1) hide show
  1. index.html +270 -270
index.html CHANGED
@@ -1,270 +1,270 @@
1
- <!doctype html>
2
- <html lang="en">
3
- <head>
4
- <meta charset="utf-8">
5
- <meta name="viewport" content="width=device-width, initial-scale=1">
6
- <script>try{var t=localStorage.getItem("amb-theme")||(matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light");document.documentElement.setAttribute("data-theme",t)}catch(e){}</script>
7
- <title>agent-memory-bench — memory for coding agents, graded by execution</title>
8
- <meta name="description" content="A preregistered, execution-graded benchmark of pluggable memory layers for coding agents. Real tasks, real repositories, no LLM judge in the primary endpoint.">
9
- <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16'%3E%3Crect width='16' height='16' fill='%23131311'/%3E%3Crect x='3' y='3' width='4' height='4' fill='%23fbfbf9'/%3E%3C/svg%3E">
10
- <link rel="preconnect" href="https://fonts.googleapis.com">
11
- <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
12
- <link href="https://fonts.googleapis.com/css2?family=Newsreader:ital,opsz,wght@0,6..72,400..700;1,6..72,400..700&family=Spline+Sans+Mono:wght@400..700&display=swap" rel="stylesheet">
13
- <link rel="stylesheet" href="styles.css">
14
- </head>
15
- <body>
16
-
17
- <header class="masthead">
18
- <div class="masthead-inner">
19
- <a class="wordmark" href="index.html" aria-label="agent-memory-bench home">
20
- <span class="tick" aria-hidden="true"></span>
21
- <span><strong class="long">agent-memory-bench</strong><strong class="short">AMB</strong><span class="full"> / AMB</span></span>
22
- </a>
23
- <nav aria-label="Primary">
24
- <a href="index.html" aria-current="page">Overview</a>
25
- <a href="method.html">Method</a>
26
- <a href="leaderboard.html">Leaderboard</a>
27
- <a href="submit.html">Submit</a>
28
- <a href="https://github.com/GiulioDER/agent-memory-bench">GitHub&nbsp;&#8599;</a>
29
- <button class="theme-toggle" type="button" aria-label="Switch between light and dark"><span class="sw" aria-hidden="true"></span></button>
30
- </nav>
31
- </div>
32
- </header>
33
-
34
- <main class="sheet">
35
-
36
- <section class="hero">
37
- <span class="kicker reveal">A preregistered, execution-graded benchmark</span>
38
- <h1 class="reveal r2">Memory for coding agents, graded by <em>execution.</em></h1>
39
- <p class="dek reveal r3">Existing memory benchmarks ask a model questions about synthetic
40
- conversations and let an LLM judge the answers. This one gives a real agent real work in a
41
- real repository, where success depends on something learned in earlier sessions, and grades
42
- the artifact by execution: <strong>tests pass or they do not.</strong> No judge anywhere in
43
- the primary endpoint.</p>
44
- <div class="hero-cta reveal r4">
45
- <a class="btn btn-solid" href="method.html">Read the method</a>
46
- <a class="btn btn-ghost" href="leaderboard.html">Leaderboard</a>
47
- </div>
48
- </section>
49
-
50
- <section class="stat-band" aria-label="Benchmark at a glance">
51
- <div class="stat-grid">
52
- <div><div class="n">6</div><div class="l">arms in the official run</div></div>
53
- <div><div class="n">34</div><div class="l">executable tasks</div></div>
54
- <div><div class="n">5</div><div class="l">corpus conditions</div></div>
55
- <div><div class="n">0</div><div class="l">LLM judges in the endpoint</div></div>
56
- </div>
57
- </section>
58
-
59
- <div class="status-line" role="status">
60
- <span class="live">Phase 0 · instrument bring-up</span>
61
- <span>Retrieval was saturated on the feed every earlier run used: hit@10 was 1.000, so every
62
- memory arm found the governing session every time and the grid measured judgement rather than
63
- memory. The official run moves to a 4,900-document corpus where it does not.</span>
64
- <span>The leaderboard stays empty until a preregistered run publishes a summary.</span>
65
- <span><a href="#progress">What has been built, and what has not &#8594;</a></span>
66
- </div>
67
-
68
- <section class="pad-y" id="decisions">
69
- <div class="section-head">
70
- <span class="no">01</span>
71
- <h2>Design in six decisions</h2>
72
- <span class="aside">the whole benchmark, compressed</span>
73
- </div>
74
-
75
- <div class="decisions">
76
- <div class="decision">
77
- <span class="idx">D1</span>
78
- <div>
79
- <h3>Official integrations, frozen and vendor-reviewed</h3>
80
- <p>Every product enters through its own published Claude Code integration: plugin, MCP
81
- server, or lifecycle hooks. Each adapter's config is hash-pinned in
82
- <code>config.frozen.json</code>, and each vendor is publicly invited to review it before
83
- the run. The invitation, the response, or the documented silence is committed to the
84
- repository.</p>
85
- </div>
86
- </div>
87
- <div class="decision">
88
- <span class="idx">D2</span>
89
- <div>
90
- <h3>Each product carries its own shipped integration</h3>
91
- <p>Every memory arm is the same CLAUDE.md bundle plus that product, wired exactly as
92
- its vendor ships it: its own skills, its own MCP server, its own instruction text. The
93
- baseline is <code>claude_md</code>, not <code>bare</code>: nobody runs a coding agent
94
- memory-free, so nothing is measured against a strawman.</p>
95
- <p>The instruction is a treatment, not scaffolding. Equalising it across arms measures
96
- a denominator no vendor ships; letting each carry its own measures what a user installs.
97
- The official run does the second and publishes every arm's instruction size beside its
98
- result. The equalised variant exists as a separate, labelled ablation.</p>
99
- </div>
100
- </div>
101
- <div class="decision">
102
- <span class="idx">D3</span>
103
- <div>
104
- <h3>One neutral experience feed, each product's own write path</h3>
105
- <p>The corpus is verbatim recorded agent session transcripts. Every adapter ingests
106
- identical bytes; what its extraction pipeline keeps is part of what is measured.</p>
107
- </div>
108
- </div>
109
- <div class="decision">
110
- <span class="idx">D4</span>
111
- <div>
112
- <h3>Executable endpoints only</h3>
113
- <p>Checkers run the artifact against oracles the sandbox never contained. A do-nothing
114
- session scores zero. Every task ships a naive reference solution that must fail and an
115
- informed one that must pass, asserted in CI.</p>
116
- </div>
117
- </div>
118
- <div class="decision">
119
- <span class="idx">D5</span>
120
- <div>
121
- <h3>The admission gate</h3>
122
- <p>A grid cell is discarded, not scored, unless every arm can prove its treatment was
123
- applied: MCP tools listed at session init, lifecycle hooks demonstrably fired with
124
- output, sandbox files digest-verified, and no arm holding another arm's tools. Discard
125
- counts are published per arm.</p>
126
- <p>Only an arm with a memory surface can fail to wire, so the rule protects one class
127
- of arm's worst outcome and no other's. Every headline is published beside an
128
- intention-to-treat column. A timeout is an outcome, not a wiring fault, and is never
129
- retried.</p>
130
- </div>
131
- </div>
132
- <div class="decision">
133
- <span class="idx">D6</span>
134
- <div>
135
- <h3>Costs are end-to-end</h3>
136
- <p>Ingestion tokens and session tokens land in one per-arm ledger, alongside wall time
137
- and negative-transfer counts. Deltas below the preregistered minimum effect are
138
- reported as noise, not as findings.</p>
139
- </div>
140
- </div>
141
- </div>
142
- </section>
143
-
144
- <section class="pad-y-s" id="arms">
145
- <div class="section-head">
146
- <span class="no">02</span>
147
- <h2>The arms</h2>
148
- <span class="aside">same feed, same tasks, same gate</span>
149
- </div>
150
-
151
- <div class="arm-strip mt-s">
152
- <div class="arm-cell"><div class="arm-name">bare</div><div class="arm-type">no memory, no CLAUDE.md</div><span class="badge">floor</span></div>
153
- <div class="arm-cell"><div class="arm-name">placebo</div><div class="arm-type">inert prose, no memory content</div><span class="badge">control</span></div>
154
- <div class="arm-cell"><div class="arm-name">claude_md</div><div class="arm-type">curated CLAUDE.md bundle</div><span class="badge">baseline</span></div>
155
- <div class="arm-cell"><div class="arm-name">fs_grep</div><div class="arm-type">transcripts on disk plus grep</div><span class="badge">control</span></div>
156
- <div class="arm-cell"><div class="arm-name">recall</div><div class="arm-type">MCP server</div><span class="badge">product</span></div>
157
- <div class="arm-cell"><div class="arm-name">mempalace</div><div class="arm-type">MCP server</div><span class="badge">product</span></div>
158
- <div class="arm-cell"><div class="arm-name">protocol</div><div class="arm-type">the instruction, no memory behind it</div><span class="badge">reference</span></div>
159
- <div class="arm-cell"><div class="arm-name">recall_prefetch</div><div class="arm-type">harness-side retrieval</div><span class="badge">reference</span></div>
160
- </div>
161
-
162
- <p class="prose mt-m">Each arm exists to remove one explanation for a result.
163
- <code>bare</code> is the reference damage is defined against. <code>placebo</code> is
164
- project-shaped prose with no memory content, matched to the baseline bundle on line count and
165
- whitespace tokens, and it separates "memory helped" from "any extra context helped".
166
- <code>claude_md</code> is the honest competitor: a well-written static instruction file costs
167
- nothing per query and is what most teams actually have. A memory product that cannot beat it
168
- has not earned its tokens.
169
- <a href="method.html#arms">What each arm isolates, in full&nbsp;&#8594;</a></p>
170
-
171
- <p class="prose mt-m"><code>protocol</code> is the control two readers asked for, and it is
172
- the one that changed the question. It carries the complete memory instruction and no memory,
173
- so it separates <em>the memory</em> from <em>the telling</em>. Because every memory product
174
- requires that instruction, "does memory beat no memory" is not directly answerable; what is
175
- answerable is whether a product earns back the cost of asking for it.</p>
176
-
177
- <p class="prose mt-m dim"><code>fs_grep</code> and <code>recall_prefetch</code> bracket the
178
- product. The first is the cheap answer, the whole corpus on disk with grep over it; the second
179
- runs retrieval in the harness with the task prompt already in hand, which is the ceiling the
180
- live arm is trying to reach. Neither is ranked as a competitor.
181
- <a href="method.html#diagnostic">How they decompose the problem&nbsp;&#8594;</a></p>
182
-
183
- <p class="prose mt-m dim">One arm is <strong>not</strong> running, and its absence is a
184
- recorded choice: <code>oracle_memory</code> injects the exact evidence, so under the
185
- <code>absent</code> condition it would hand over an answer the corpus is defined not to
186
- contain. It returns when its bundles are condition-aware.</p>
187
- </section>
188
-
189
- <section class="pad-y-s" id="progress">
190
- <div class="section-head">
191
- <span class="no">03</span>
192
- <h2>Where this actually stands</h2>
193
- <span class="aside">2026-08-31</span>
194
- </div>
195
-
196
- <div class="table-scroll mt-s">
197
- <table>
198
- <thead><tr><th>piece</th><th>state</th></tr></thead>
199
- <tbody>
200
- <tr><td><span class="m">harness</span></td>
201
- <td>runs; sandbox, admission gate, paired statistics, cost ledger, MCP preflight and bounded retry</td></tr>
202
- <tr><td><span class="m">tasks</span></td>
203
- <td><strong>34</strong> executable tasks, each with a naive and an informed reference asserted in CI. Three of them need two sessions combined, which single-fact retrieval cannot do</td></tr>
204
- <tr><td><span class="m">harm suite</span></td>
205
- <td>five corpus conditions across <strong>73 task-conditions</strong>; eleven tasks carry all four damage conditions, above the threshold of eight for reporting one as a result</td></tr>
206
- <tr><td><span class="m">arms</span></td>
207
- <td><strong>eight in the approved run:</strong> <code>bare</code>, <code>placebo</code>, <code>claude_md</code>, <code>protocol</code>, <code>fs_grep</code>, <code>recall</code>, <code>mempalace</code>, <code>recall_prefetch</code>. Two products, each wired through its own published integration and pinned to a released version, and each handed the same instruction byte for byte</td></tr>
208
- <tr><td><span class="m">corpus</span></td>
209
- <td>4,900 documents per condition, up from 196. It was rebuilt because the old feed was too easy: <code>bm25</code> hit@1 fell 0.485 to 0.182 and <code>voyage</code> hit@10 fell 1.000 to 0.879 on the new one</td></tr>
210
- <tr><td><span class="m">runs</span></td>
211
- <td>every run so far is <strong>bring-up, not result</strong>: five pilots, a harm-suite first pass, a calibration, a diagnostic and one full grid. The grid is treated as calibration because it showed the feed could not separate the arms. No arm-level number from any of them is quoted</td></tr>
212
- <tr><td><span class="m">leaderboard</span></td>
213
- <td>empty by construction: a number reaches it only from a published run summary</td></tr>
214
- <tr><td><span class="m">reproducibility</span></td>
215
- <td><strong>checkable, not yet re-runnable.</strong> <code>python -m scripts.verify_run --all</code> re-derives the ledger, the endpoints and the discard set from the published sessions with no credentials and no money. Re-running is the gap: <code>bare</code>, <code>placebo</code>, <code>claude_md</code> and <code>fs_grep</code> need only the CLI and a model key, while <code>recall</code> needs a database, an embedding key and a built index that the compose stack does not start</td></tr>
216
- </tbody>
217
- </table>
218
- </div>
219
-
220
- <div class="callout mt-l">
221
- <span class="kicker">The long version</span>
222
- <div class="prose">
223
- <p>The dated status page in the repository carries the run-by-run table, the open
224
- blockers in the order they have to be cleared, and the command that re-derives every
225
- claim on this page:
226
- <a href="https://github.com/GiulioDER/agent-memory-bench/blob/master/docs/STATUS.md">docs/STATUS.md</a>.
227
- Every change to the instrument that moves a published number is recorded in
228
- <a href="https://github.com/GiulioDER/agent-memory-bench/tree/master/docs/audit">docs/audit/</a>.</p>
229
- </div>
230
- </div>
231
- </section>
232
-
233
- <section class="pad-y-s" id="disclosure">
234
- <div class="callout callout-invert">
235
- <span class="kicker">Disclosure</span>
236
- <p>This benchmark is built by the authors of <strong>recall</strong>, which competes in it.
237
- That is exactly why the methodology is preregistered, the harness is open, every adapter
238
- config is vendor-reviewable before any run, and all results are published, including the
239
- ones recall loses. The full run's protocol is committed under
240
- <code>preregistration/</code> before a single session starts.</p>
241
- </div>
242
- </section>
243
-
244
- </main>
245
-
246
- <footer>
247
- <div class="footer-inner">
248
- <div>
249
- <div class="foot-title">agent-memory-bench</div>
250
- <div class="dim">A preregistered, execution-graded benchmark of pluggable memory layers
251
- for coding agents. Apache-2.0. Built in the open; results published win or lose.</div>
252
- </div>
253
- <div>
254
- <div class="foot-title">Pages</div>
255
- <a href="method.html">Method</a><br>
256
- <a href="leaderboard.html">Leaderboard</a><br>
257
- <a href="submit.html">Submit &amp; reproduce</a>
258
- </div>
259
- <div>
260
- <div class="foot-title">Source</div>
261
- <a href="https://github.com/GiulioDER/agent-memory-bench">Repository</a><br>
262
- <a href="https://github.com/GiulioDER/agent-memory-bench/tree/master/preregistration">Preregistrations</a><br>
263
- <a href="https://github.com/GiulioDER/agent-memory-bench/blob/master/adapters/VENDOR_REVIEW_TEMPLATE.md">Vendor review</a>
264
- </div>
265
- </div>
266
- </footer>
267
-
268
- <script src="site.js"></script>
269
- </body>
270
- </html>
 
1
+ <!doctype html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1">
6
+ <script>try{var t=localStorage.getItem("amb-theme")||(matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light");document.documentElement.setAttribute("data-theme",t)}catch(e){}</script>
7
+ <title>agent-memory-bench — memory for coding agents, graded by execution</title>
8
+ <meta name="description" content="A preregistered, execution-graded benchmark of pluggable memory layers for coding agents. Real tasks, real repositories, no LLM judge in the primary endpoint.">
9
+ <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 16 16'%3E%3Crect width='16' height='16' fill='%23131311'/%3E%3Crect x='3' y='3' width='4' height='4' fill='%23fbfbf9'/%3E%3C/svg%3E">
10
+ <link rel="preconnect" href="https://fonts.googleapis.com">
11
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
12
+ <link href="https://fonts.googleapis.com/css2?family=Newsreader:ital,opsz,wght@0,6..72,400..700;1,6..72,400..700&family=Spline+Sans+Mono:wght@400..700&display=swap" rel="stylesheet">
13
+ <link rel="stylesheet" href="styles.css">
14
+ </head>
15
+ <body>
16
+
17
+ <header class="masthead">
18
+ <div class="masthead-inner">
19
+ <a class="wordmark" href="index.html" aria-label="agent-memory-bench home">
20
+ <span class="tick" aria-hidden="true"></span>
21
+ <span><strong class="long">agent-memory-bench</strong><strong class="short">AMB</strong><span class="full"> / AMB</span></span>
22
+ </a>
23
+ <nav aria-label="Primary">
24
+ <a href="index.html" aria-current="page">Overview</a>
25
+ <a href="method.html">Method</a>
26
+ <a href="leaderboard.html">Leaderboard</a>
27
+ <a href="submit.html">Submit</a>
28
+ <a href="https://github.com/GiulioDER/agent-memory-bench">GitHub&nbsp;&#8599;</a>
29
+ <button class="theme-toggle" type="button" aria-label="Switch between light and dark"><span class="sw" aria-hidden="true"></span></button>
30
+ </nav>
31
+ </div>
32
+ </header>
33
+
34
+ <main class="sheet">
35
+
36
+ <section class="hero">
37
+ <span class="kicker reveal">A preregistered, execution-graded benchmark</span>
38
+ <h1 class="reveal r2">Memory for coding agents, graded by <em>execution.</em></h1>
39
+ <p class="dek reveal r3">Existing memory benchmarks ask a model questions about synthetic
40
+ conversations and let an LLM judge the answers. This one gives a real agent real work in a
41
+ real repository, where success depends on something learned in earlier sessions, and grades
42
+ the artifact by execution: <strong>tests pass or they do not.</strong> No judge anywhere in
43
+ the primary endpoint.</p>
44
+ <div class="hero-cta reveal r4">
45
+ <a class="btn btn-solid" href="method.html">Read the method</a>
46
+ <a class="btn btn-ghost" href="leaderboard.html">Leaderboard</a>
47
+ </div>
48
+ </section>
49
+
50
+ <section class="stat-band" aria-label="Benchmark at a glance">
51
+ <div class="stat-grid">
52
+ <div><div class="n">6</div><div class="l">arms on the leaderboard</div></div>
53
+ <div><div class="n">34</div><div class="l">executable tasks</div></div>
54
+ <div><div class="n">5</div><div class="l">corpus conditions</div></div>
55
+ <div><div class="n">0</div><div class="l">LLM judges in the endpoint</div></div>
56
+ </div>
57
+ </section>
58
+
59
+ <div class="status-line" role="status">
60
+ <span class="live">Phase 0 · instrument bring-up</span>
61
+ <span>Retrieval was saturated on the feed every earlier run used: hit@10 was 1.000, so every
62
+ memory arm found the governing session every time and the grid measured judgement rather than
63
+ memory. The official run moves to a 4,900-document corpus where it does not.</span>
64
+ <span>The leaderboard stays empty until a preregistered run publishes a summary.</span>
65
+ <span><a href="#progress">What has been built, and what has not &#8594;</a></span>
66
+ </div>
67
+
68
+ <section class="pad-y" id="decisions">
69
+ <div class="section-head">
70
+ <span class="no">01</span>
71
+ <h2>Design in six decisions</h2>
72
+ <span class="aside">the whole benchmark, compressed</span>
73
+ </div>
74
+
75
+ <div class="decisions">
76
+ <div class="decision">
77
+ <span class="idx">D1</span>
78
+ <div>
79
+ <h3>Official integrations, frozen and vendor-reviewed</h3>
80
+ <p>Every product enters through its own published Claude Code integration: plugin, MCP
81
+ server, or lifecycle hooks. Each adapter's config is hash-pinned in
82
+ <code>config.frozen.json</code>, and each vendor is publicly invited to review it before
83
+ the run. The invitation, the response, or the documented silence is committed to the
84
+ repository.</p>
85
+ </div>
86
+ </div>
87
+ <div class="decision">
88
+ <span class="idx">D2</span>
89
+ <div>
90
+ <h3>Each product carries its own shipped integration</h3>
91
+ <p>Every memory arm is the same CLAUDE.md bundle plus that product, wired exactly as
92
+ its vendor ships it: its own skills, its own MCP server, its own instruction text. The
93
+ baseline is <code>claude_md</code>, not <code>bare</code>: nobody runs a coding agent
94
+ memory-free, so nothing is measured against a strawman.</p>
95
+ <p>The instruction is a treatment, not scaffolding. Equalising it across arms measures
96
+ a denominator no vendor ships; letting each carry its own measures what a user installs.
97
+ The official run does the second and publishes every arm's instruction size beside its
98
+ result. The equalised variant exists as a separate, labelled ablation.</p>
99
+ </div>
100
+ </div>
101
+ <div class="decision">
102
+ <span class="idx">D3</span>
103
+ <div>
104
+ <h3>One neutral experience feed, each product's own write path</h3>
105
+ <p>The corpus is verbatim recorded agent session transcripts. Every adapter ingests
106
+ identical bytes; what its extraction pipeline keeps is part of what is measured.</p>
107
+ </div>
108
+ </div>
109
+ <div class="decision">
110
+ <span class="idx">D4</span>
111
+ <div>
112
+ <h3>Executable endpoints only</h3>
113
+ <p>Checkers run the artifact against oracles the sandbox never contained. A do-nothing
114
+ session scores zero. Every task ships a naive reference solution that must fail and an
115
+ informed one that must pass, asserted in CI.</p>
116
+ </div>
117
+ </div>
118
+ <div class="decision">
119
+ <span class="idx">D5</span>
120
+ <div>
121
+ <h3>The admission gate</h3>
122
+ <p>A grid cell is discarded, not scored, unless every arm can prove its treatment was
123
+ applied: MCP tools listed at session init, lifecycle hooks demonstrably fired with
124
+ output, sandbox files digest-verified, and no arm holding another arm's tools. Discard
125
+ counts are published per arm.</p>
126
+ <p>Only an arm with a memory surface can fail to wire, so the rule protects one class
127
+ of arm's worst outcome and no other's. Every headline is published beside an
128
+ intention-to-treat column. A timeout is an outcome, not a wiring fault, and is never
129
+ retried.</p>
130
+ </div>
131
+ </div>
132
+ <div class="decision">
133
+ <span class="idx">D6</span>
134
+ <div>
135
+ <h3>Costs are end-to-end</h3>
136
+ <p>Ingestion tokens and session tokens land in one per-arm ledger, alongside wall time
137
+ and negative-transfer counts. Deltas below the preregistered minimum effect are
138
+ reported as noise, not as findings.</p>
139
+ </div>
140
+ </div>
141
+ </div>
142
+ </section>
143
+
144
+ <section class="pad-y-s" id="arms">
145
+ <div class="section-head">
146
+ <span class="no">02</span>
147
+ <h2>The arms</h2>
148
+ <span class="aside">same feed, same tasks, same gate</span>
149
+ </div>
150
+
151
+ <div class="arm-strip mt-s">
152
+ <div class="arm-cell"><div class="arm-name">bare</div><div class="arm-type">no memory, no CLAUDE.md</div><span class="badge">floor</span></div>
153
+ <div class="arm-cell"><div class="arm-name">placebo</div><div class="arm-type">inert prose, no memory content</div><span class="badge">control</span></div>
154
+ <div class="arm-cell"><div class="arm-name">claude_md</div><div class="arm-type">curated CLAUDE.md bundle</div><span class="badge">baseline</span></div>
155
+ <div class="arm-cell"><div class="arm-name">fs_grep</div><div class="arm-type">transcripts on disk plus grep</div><span class="badge">control</span></div>
156
+ <div class="arm-cell"><div class="arm-name">recall</div><div class="arm-type">MCP server</div><span class="badge">product</span></div>
157
+ <div class="arm-cell"><div class="arm-name">mempalace</div><div class="arm-type">MCP server</div><span class="badge">product</span></div>
158
+ <div class="arm-cell"><div class="arm-name">protocol</div><div class="arm-type">the instruction, no memory behind it</div><span class="badge">reference</span></div>
159
+ <div class="arm-cell"><div class="arm-name">recall_prefetch</div><div class="arm-type">harness-side retrieval</div><span class="badge">reference</span></div>
160
+ </div>
161
+
162
+ <p class="prose mt-m">Each arm exists to remove one explanation for a result.
163
+ <code>bare</code> is the reference damage is defined against. <code>placebo</code> is
164
+ project-shaped prose with no memory content, matched to the baseline bundle on line count and
165
+ whitespace tokens, and it separates "memory helped" from "any extra context helped".
166
+ <code>claude_md</code> is the honest competitor: a well-written static instruction file costs
167
+ nothing per query and is what most teams actually have. A memory product that cannot beat it
168
+ has not earned its tokens.
169
+ <a href="method.html#arms">What each arm isolates, in full&nbsp;&#8594;</a></p>
170
+
171
+ <p class="prose mt-m"><code>protocol</code> is the control two readers asked for, and it is
172
+ the one that changed the question. It carries the complete memory instruction and no memory,
173
+ so it separates <em>the memory</em> from <em>the telling</em>. Because every memory product
174
+ requires that instruction, "does memory beat no memory" is not directly answerable; what is
175
+ answerable is whether a product earns back the cost of asking for it.</p>
176
+
177
+ <p class="prose mt-m dim"><code>fs_grep</code> and <code>recall_prefetch</code> bracket the
178
+ product. The first is the cheap answer, the whole corpus on disk with grep over it; the second
179
+ runs retrieval in the harness with the task prompt already in hand, which is the ceiling the
180
+ live arm is trying to reach. Neither is ranked as a competitor.
181
+ <a href="method.html#diagnostic">How they decompose the problem&nbsp;&#8594;</a></p>
182
+
183
+ <p class="prose mt-m dim">One arm is <strong>not</strong> running, and its absence is a
184
+ recorded choice: <code>oracle_memory</code> injects the exact evidence, so under the
185
+ <code>absent</code> condition it would hand over an answer the corpus is defined not to
186
+ contain. It returns when its bundles are condition-aware.</p>
187
+ </section>
188
+
189
+ <section class="pad-y-s" id="progress">
190
+ <div class="section-head">
191
+ <span class="no">03</span>
192
+ <h2>Where this actually stands</h2>
193
+ <span class="aside">2026-08-31</span>
194
+ </div>
195
+
196
+ <div class="table-scroll mt-s">
197
+ <table>
198
+ <thead><tr><th>piece</th><th>state</th></tr></thead>
199
+ <tbody>
200
+ <tr><td><span class="m">harness</span></td>
201
+ <td>runs; sandbox, admission gate, paired statistics, cost ledger, MCP preflight and bounded retry</td></tr>
202
+ <tr><td><span class="m">tasks</span></td>
203
+ <td><strong>34</strong> executable tasks, each with a naive and an informed reference asserted in CI. Three of them need two sessions combined, which single-fact retrieval cannot do</td></tr>
204
+ <tr><td><span class="m">harm suite</span></td>
205
+ <td>five corpus conditions across <strong>73 task-conditions</strong>; eleven tasks carry all four damage conditions, above the threshold of eight for reporting one as a result</td></tr>
206
+ <tr><td><span class="m">arms</span></td>
207
+ <td><strong>eight in the approved run:</strong> <code>bare</code>, <code>placebo</code>, <code>claude_md</code>, <code>protocol</code>, <code>fs_grep</code>, <code>recall</code>, <code>mempalace</code>, <code>recall_prefetch</code>. Two products, each wired through its own published integration and pinned to a released version, and each handed the same instruction byte for byte</td></tr>
208
+ <tr><td><span class="m">corpus</span></td>
209
+ <td>4,900 documents per condition, up from 196. It was rebuilt because the old feed was too easy: <code>bm25</code> hit@1 fell 0.485 to 0.182 and <code>voyage</code> hit@10 fell 1.000 to 0.879 on the new one</td></tr>
210
+ <tr><td><span class="m">runs</span></td>
211
+ <td>every run so far is <strong>bring-up, not result</strong>: five pilots, a harm-suite first pass, a calibration, a diagnostic and one full grid. The grid is treated as calibration because it showed the feed could not separate the arms. No arm-level number from any of them is quoted</td></tr>
212
+ <tr><td><span class="m">leaderboard</span></td>
213
+ <td>empty by construction: a number reaches it only from a published run summary</td></tr>
214
+ <tr><td><span class="m">reproducibility</span></td>
215
+ <td><strong>checkable, not yet re-runnable.</strong> <code>python -m scripts.verify_run --all</code> re-derives the ledger, the endpoints and the discard set from the published sessions with no credentials and no money. Re-running is the gap: <code>bare</code>, <code>placebo</code>, <code>claude_md</code> and <code>fs_grep</code> need only the CLI and a model key, while <code>recall</code> needs a database, an embedding key and a built index that the compose stack does not start</td></tr>
216
+ </tbody>
217
+ </table>
218
+ </div>
219
+
220
+ <div class="callout mt-l">
221
+ <span class="kicker">The long version</span>
222
+ <div class="prose">
223
+ <p>The dated status page in the repository carries the run-by-run table, the open
224
+ blockers in the order they have to be cleared, and the command that re-derives every
225
+ claim on this page:
226
+ <a href="https://github.com/GiulioDER/agent-memory-bench/blob/master/docs/STATUS.md">docs/STATUS.md</a>.
227
+ Every change to the instrument that moves a published number is recorded in
228
+ <a href="https://github.com/GiulioDER/agent-memory-bench/tree/master/docs/audit">docs/audit/</a>.</p>
229
+ </div>
230
+ </div>
231
+ </section>
232
+
233
+ <section class="pad-y-s" id="disclosure">
234
+ <div class="callout callout-invert">
235
+ <span class="kicker">Disclosure</span>
236
+ <p>This benchmark is built by the authors of <strong>recall</strong>, which competes in it.
237
+ That is exactly why the methodology is preregistered, the harness is open, every adapter
238
+ config is vendor-reviewable before any run, and all results are published, including the
239
+ ones recall loses. The full run's protocol is committed under
240
+ <code>preregistration/</code> before a single session starts.</p>
241
+ </div>
242
+ </section>
243
+
244
+ </main>
245
+
246
+ <footer>
247
+ <div class="footer-inner">
248
+ <div>
249
+ <div class="foot-title">agent-memory-bench</div>
250
+ <div class="dim">A preregistered, execution-graded benchmark of pluggable memory layers
251
+ for coding agents. Apache-2.0. Built in the open; results published win or lose.</div>
252
+ </div>
253
+ <div>
254
+ <div class="foot-title">Pages</div>
255
+ <a href="method.html">Method</a><br>
256
+ <a href="leaderboard.html">Leaderboard</a><br>
257
+ <a href="submit.html">Submit &amp; reproduce</a>
258
+ </div>
259
+ <div>
260
+ <div class="foot-title">Source</div>
261
+ <a href="https://github.com/GiulioDER/agent-memory-bench">Repository</a><br>
262
+ <a href="https://github.com/GiulioDER/agent-memory-bench/tree/master/preregistration">Preregistrations</a><br>
263
+ <a href="https://github.com/GiulioDER/agent-memory-bench/blob/master/adapters/VENDOR_REVIEW_TEMPLATE.md">Vendor review</a>
264
+ </div>
265
+ </div>
266
+ </footer>
267
+
268
+ <script src="site.js"></script>
269
+ </body>
270
+ </html>