diff --git a/content/docs/memory-benchmark/beam.mdx b/content/docs/memory-benchmark/beam.mdx
index 8794ce2..3b6b177 100644
--- a/content/docs/memory-benchmark/beam.mdx
+++ b/content/docs/memory-benchmark/beam.mdx
@@ -71,8 +71,9 @@ of the 35 conversations (300 probes), uniform 96k budget.
 | abstention | 9/30 (30%) |
 | **overall** | **198/300 (66.0%)** |
 
-- **66.0% edges mem0's self-reported 62% at the matched bucket.** Caveats in
-  [How Kimetsu compares](/docs/memory-benchmark/comparison).
+- **Kimetsu scores 66.0%; mem0 reports 64.1% in the 1M bucket.** The readers
+  and conversation samples differ. Sources and test differences are recorded
+  in [How Kimetsu compares](/docs/memory-benchmark/comparison).
 - **Global and temporal abilities degrade with scale, as expected.** When the
   conversation is ~10x the budget, whole-arc tasks lose ground that local-fact
   tasks keep.
diff --git a/content/docs/memory-benchmark/comparison.mdx b/content/docs/memory-benchmark/comparison.mdx
index a0fed0a..7552e30 100644
--- a/content/docs/memory-benchmark/comparison.mdx
+++ b/content/docs/memory-benchmark/comparison.mdx
@@ -22,14 +22,15 @@ bill, or the cloud.**
 | LongMemEval (`_s`) | **83.0%** (200-q slice) · ~80.9% weighted | 94.4% (their reader + harness) | not reported |
 | LoCoMo (1,540 q) | **89.4%** | 92.5% | not reported |
 | BEAM 100K | **73.3%** (400 probes) | n/a | 79% |
-| BEAM **1M** | **66.0%** (300 probes) | 62% | not reported |
+| BEAM **1M** | **66.0%** (300 probes) | 64.1% (700 probes) | not reported |
 | BEAM 10M | future work | 48.6% | 67% |
 
 Caveats, because the table is not apples-to-apples:
 
-- **Only the 1M row is a matched bucket.** Our 66.0% edges mem0's 62%, but with
-  a different reader and 15 of 35 conversations: read it as at least on par,
-  not a decisive win.
+- **The 1M row uses the same token bucket, with different setups.** Kimetsu's
+  66.0% covers 15 of 35 conversations; mem0 reports 64.1% over 700 probes.
+  The readers and samples differ, so the score difference does not establish
+  a head-to-head win.
 - **Cognee leads at 100K/10M.** Our 73.3% matches the prior public state of the
   art on 100K (the 0.735 Cognee cites as the number it beat), model-free.
   Cognee needs an LLM key on both the write and read paths.
@@ -46,6 +47,9 @@ Cognee's [BEAM figures](https://github.com/topoteretes/cognee), the
 [LongMemEval](https://arxiv.org/abs/2410.10813) and
 [BEAM](https://github.com/mohammadtavakoli78/BEAM) papers.
 
+Mem0's BEAM 1M figure was checked on September 12, 2026. Its current reported
+64.1% replaces the 62% previously quoted here.
+
 ## What we do not yet claim
 
 - Multi-hop retrieval of obliquely relevant memories is v2.6 work; the
diff --git a/content/docs/memory-benchmark/index.mdx b/content/docs/memory-benchmark/index.mdx
index b410b1e..9abfa11 100644
--- a/content/docs/memory-benchmark/index.mdx
+++ b/content/docs/memory-benchmark/index.mdx
@@ -21,7 +21,7 @@ on v2.8.0.
 |-----------|--------|
 | LoCoMo | **89.4%** (1,540 questions, LLM-judged accuracy) |
 | BEAM 100K | **73.3%**, matching the prior public state of the art, model-free |
-| BEAM 1M | **66.0%**, ahead of mem0's self-reported 62% |
+| BEAM 1M | **66.0%** (300 probes, 15 of 35 conversations) |
 | LongMemEval (`_s`) | **83.0%** (200-question stratified slice) |
 | BrainBench quality index | **80.0%** (142 scenarios, reader-free) |
 | retrieval quality | recall@4 **0.949**, MRR **0.914** at ~138 ms |
diff --git a/src/app/(home)/_components/about-contact.tsx b/src/app/(home)/_components/about-contact.tsx
index 0eb19ac..1eec532 100644
--- a/src/app/(home)/_components/about-contact.tsx
+++ b/src/app/(home)/_components/about-contact.tsx
@@ -12,32 +12,25 @@ export function AboutContact() {
       >
         <div className="grid gap-8 md:grid-cols-[0.7fr_1.3fr]">
           <div>
-            <p className="km-eyebrow">About</p>
             <h2 id="about-title" className="km-heading">
-              Built for the next session.
+              About Kimetsu
             </h2>
           </div>
           <div className="max-w-2xl">
             <p className="text-lg leading-8 text-fd-muted-foreground">
-              Kimetsu is an open-source project created by{" "}
+              Created and maintained by{" "}
               <span className="font-medium text-fd-foreground">
                 Rodrigo Córdoba
               </span>
-              . It gives coding agents a local place to keep project decisions,
-              conventions, and fixes, so useful knowledge carries across
-              sessions.
-            </p>
-            <p className="mt-4 leading-7 text-fd-muted-foreground">
-              Built in Rust and backed by SQLite, Kimetsu works alongside the
-              tools you already use. The source, documentation, and benchmarks
-              are public, so you can inspect how it works and make it your own.
+              . Written in Rust and released under the MIT and Apache-2.0
+              licenses.
             </p>
             <div className="mt-6 flex flex-wrap gap-x-6 gap-y-3">
               <a href={links.github} className="km-text-link">
-                Explore the source →
+                Source code →
               </a>
-              <Link href="/docs" className="km-text-link">
-                Read the documentation →
+              <Link href="/projects" className="km-text-link">
+                Related projects →
               </Link>
             </div>
           </div>
@@ -50,13 +43,12 @@ export function AboutContact() {
       >
         <div className="grid items-center gap-8 rounded-2xl border border-fd-border bg-fd-card/40 p-6 sm:p-10 lg:grid-cols-[1fr_auto]">
           <div>
-            <p className="km-eyebrow">Contact</p>
             <h2 id="contact-title" className="km-heading">
-              Let’s talk about Kimetsu.
+              Contact
             </h2>
             <p className="mt-4 max-w-xl leading-7 text-fd-muted-foreground">
-              Have a question, an idea, or something you’d like to build
-              together? Get in touch with Rodrigo on LinkedIn.
+              For questions, feedback, or collaboration, contact Rodrigo on
+              LinkedIn.
             </p>
           </div>
           <a
diff --git a/src/app/(home)/_components/benchmark-results.tsx b/src/app/(home)/_components/benchmark-results.tsx
new file mode 100644
index 0000000..c5a39d9
--- /dev/null
+++ b/src/app/(home)/_components/benchmark-results.tsx
@@ -0,0 +1,102 @@
+import Link from "next/link";
+
+// Published runs: content/docs/memory-benchmark/{beam,index,longmemeval}.mdx.
+// Keep sample sizes beside the scores; these are separate benchmark protocols.
+export function BenchmarkResults() {
+  return (
+    <section
+      id="benchmarks"
+      aria-labelledby="benchmarks-title"
+      className="km-section km-benchmarks scroll-mt-24"
+    >
+      <div className="mb-6 flex flex-wrap items-baseline justify-between gap-3">
+        <h2 id="benchmarks-title" className="km-heading">
+          Benchmark results
+        </h2>
+        <Link href="/docs/memory-benchmark" className="km-text-link">
+          All results and methodology →
+        </Link>
+      </div>
+      <div className="grid overflow-hidden rounded-2xl border border-fd-border lg:grid-cols-3">
+        <article className="flex flex-col bg-fd-primary/5 p-6 sm:p-8">
+          <h3 className="font-mono text-sm font-semibold">BEAM 100K</h3>
+          <p className="km-benchmark-score text-fd-primary">73.3%</p>
+          <p className="text-sm text-fd-muted-foreground">
+            Accuracy · 400 probes · 20 conversations
+          </p>
+          <div
+            className="mt-6 space-y-3"
+            role="img"
+            aria-label="BEAM 100K accuracy on the same 400 probes: Kimetsu with graph retrieval, 73.3 percent; flat retrieval baseline, 62.3 percent. Bars use a zero to 100 percent scale."
+          >
+            <div aria-hidden>
+              <p className="mb-2 text-xs font-medium">
+                Kimetsu · graph retrieval
+              </p>
+              <div className="h-2 rounded-full bg-fd-primary/10">
+                <div className="h-full w-[73.3%] rounded-full bg-fd-primary" />
+              </div>
+            </div>
+            <div aria-hidden>
+              <div className="mb-2 flex justify-between gap-3 text-xs text-fd-muted-foreground">
+                <span>Flat retrieval baseline</span>
+                <span className="font-mono tabular-nums">62.3%</span>
+              </div>
+              <div className="h-2 rounded-full bg-fd-primary/10">
+                <div className="h-full w-[62.3%] rounded-full bg-fd-muted-foreground" />
+              </div>
+            </div>
+          </div>
+          <p className="mt-4 text-xs leading-5 text-fd-muted-foreground">
+            Both runs use the same test set.
+          </p>
+          <Link
+            href="/docs/memory-benchmark/beam"
+            className="km-text-link mt-auto pt-6"
+          >
+            BEAM test settings →
+          </Link>
+        </article>
+        <article className="flex flex-col border-t border-fd-border p-6 sm:p-8 lg:border-t-0 lg:border-l">
+          <h3 className="font-mono text-sm font-semibold">LoCoMo</h3>
+          <p className="km-benchmark-score">89.4%</p>
+          <p className="text-sm text-fd-muted-foreground">
+            Accuracy · 1,540 questions
+          </p>
+          <p className="mt-6 text-sm leading-6 text-fd-muted-foreground">
+            Questions about facts, events, and relationships across long
+            conversations.
+          </p>
+          <Link
+            href="/docs/memory-benchmark/comparison"
+            className="km-text-link mt-auto pt-6"
+          >
+            LoCoMo results and comparison →
+          </Link>
+        </article>
+        <article className="flex flex-col border-t border-fd-border p-6 sm:p-8 lg:border-t-0 lg:border-l">
+          <h3 className="font-mono text-sm font-semibold">LongMemEval S</h3>
+          <p className="km-benchmark-score">83.0%</p>
+          <p className="text-sm text-fd-muted-foreground">
+            Accuracy · 200-question stratified slice
+          </p>
+          <p className="mt-6 text-sm leading-6 text-fd-muted-foreground">
+            Sampled from the 500-question set, covering recall, changed facts,
+            and reasoning across sessions.
+          </p>
+          <Link
+            href="/docs/memory-benchmark/longmemeval"
+            className="km-text-link mt-auto pt-6"
+          >
+            LongMemEval test settings →
+          </Link>
+        </article>
+      </div>
+      <p className="mt-4 max-w-4xl text-xs leading-5 text-fd-muted-foreground">
+        Historical results from the linked runs. An LLM answers and grades the
+        questions; the memory pipeline uses local search, embeddings, and
+        reranking, with no LLM calls.
+      </p>
+    </section>
+  );
+}
diff --git a/src/app/(home)/_components/explore-section.tsx b/src/app/(home)/_components/explore-section.tsx
index e611b58..ba4e2ff 100644
--- a/src/app/(home)/_components/explore-section.tsx
+++ b/src/app/(home)/_components/explore-section.tsx
@@ -1,21 +1,17 @@
-import { Database, MessageSquare, Search } from "lucide-react";
 import Link from "next/link";
 
 const steps = [
   {
-    icon: Database,
-    title: "Keep the useful lesson",
-    body: "Save a project convention, a decision, or the command that finally worked. Memories live in your project’s SQLite database.",
+    title: "Store",
+    body: "Memories live in a SQLite database in your project. No hosted memory account is required.",
   },
   {
-    icon: Search,
-    title: "Recall it in context",
-    body: "Search by words or meaning. Kimetsu selects relevant memories within a delivery budget and brings them into the next task.",
+    title: "Retrieve",
+    body: "Start with keyword search. Add local embeddings and reranking for semantic search. Set a token budget for the context sent to your agent.",
   },
   {
-    icon: MessageSquare,
-    title: "Learn from the outcome",
-    body: "Citations and feedback help track which memories contributed. Corrections and lifecycle rules keep old advice from outliving its usefulness.",
+    title: "Update",
+    body: "Track changed facts and suppress outdated results. Export and import memories to move them between machines.",
   },
 ];
 
@@ -27,25 +23,22 @@ export function ExploreSection() {
       className="km-section scroll-mt-24"
     >
       <div className="mb-10 flex flex-wrap items-end justify-between gap-5">
-        <div className="max-w-2xl">
-          <p className="km-eyebrow">Across sessions, across agents</p>
-          <h2 id="workflow-title" className="km-heading">
-            The useful part of yesterday, ready today.
-          </h2>
-        </div>
+        <h2 id="workflow-title" className="km-heading">
+          How it works
+        </h2>
         <Link href="/docs/how-kimetsu-works" className="km-text-link">
-          Inside the memory loop →
+          Technical documentation →
         </Link>
       </div>
       <ol className="grid gap-6 md:grid-cols-3">
         {steps.map((step, index) => (
           <li key={step.title} className="border-t border-fd-border pt-6">
-            <div className="mb-5 flex items-center justify-between">
-              <step.icon className="size-6 text-fd-primary" aria-hidden />
-              <span className="font-mono text-sm text-fd-muted-foreground">
-                0{index + 1}
-              </span>
-            </div>
+            <span
+              className="mb-4 block font-mono text-sm text-fd-primary"
+              aria-hidden
+            >
+              0{index + 1}
+            </span>
             <h3 className="mb-3 text-lg font-semibold">{step.title}</h3>
             <p className="text-sm leading-6 text-fd-muted-foreground">
               {step.body}
@@ -53,22 +46,6 @@ export function ExploreSection() {
           </li>
         ))}
       </ol>
-      <div className="mt-10 flex flex-col justify-between gap-4 rounded-xl border border-fd-border bg-fd-card p-5 sm:flex-row sm:items-center">
-        <p className="max-w-2xl text-sm leading-6 text-fd-muted-foreground">
-          <strong className="text-fd-foreground">
-            Choose your compute budget.
-          </strong>{" "}
-          Start with lexical search. Add local embeddings and reranking when
-          your workload benefits from them. Delivered context still uses your
-          agent’s tokens.
-        </p>
-        <Link
-          href="/docs/how-kimetsu-works/retrieval-models"
-          className="km-text-link shrink-0"
-        >
-          Compare retrieval models →
-        </Link>
-      </div>
     </section>
   );
 }
diff --git a/src/app/(home)/_components/quick-start.tsx b/src/app/(home)/_components/quick-start.tsx
index a1f883d..1335369 100644
--- a/src/app/(home)/_components/quick-start.tsx
+++ b/src/app/(home)/_components/quick-start.tsx
@@ -35,13 +35,12 @@ export function QuickStart() {
     >
       <div className="grid gap-8 lg:grid-cols-[0.85fr_1.15fr] lg:items-center">
         <div>
-          <p className="km-eyebrow">Start with your agent</p>
           <h2 id="setup-title" className="km-heading">
-            Two commands. A memory that stays.
+            Install Kimetsu
           </h2>
           <p className="mt-4 max-w-md text-fd-muted-foreground">
-            Install the binary, then run setup from your project directory.
-            Choose the agent you already use.
+            Select your agent and run these commands from your project
+            directory. Available for Linux, macOS, and Windows.
           </p>
           <Link href="/docs/install" className="km-text-link mt-4 inline-block">
             All installation options →
@@ -96,7 +95,7 @@ export function QuickStart() {
                 ? feedback.ok
                   ? "Commands copied to clipboard."
                   : "Copy is unavailable. Select and copy the commands above."
-                : "Setup wires this project to your selected agent."}
+                : ""}
             </p>
           </div>
           <noscript>
diff --git a/src/app/(home)/page.tsx b/src/app/(home)/page.tsx
index ed0ce7d..d316782 100644
--- a/src/app/(home)/page.tsx
+++ b/src/app/(home)/page.tsx
@@ -1,293 +1,43 @@
-import { ArrowRight, Database, GitBranch, Lock, Terminal } from "lucide-react";
+import { ArrowRight } from "lucide-react";
 import Link from "next/link";
 import { links } from "@/lib/shared";
 import { AboutContact } from "./_components/about-contact";
+import { BenchmarkResults } from "./_components/benchmark-results";
 import { ExploreSection } from "./_components/explore-section";
-import { BrainSharing } from "./_components/home-visuals";
-import { ProjectsSection } from "./_components/projects-section";
 import { QuickStart } from "./_components/quick-start";
 
-const principles = [
-  {
-    icon: Database,
-    title: "Local by default",
-    body: "Project memory lives in SQLite. Start with lexical search or add local semantic models.",
-  },
-  {
-    icon: GitBranch,
-    title: "Portable knowledge",
-    body: "Keep project decisions with the project. Export and import memories when you change machines or collaborate.",
-  },
-  {
-    icon: Lock,
-    title: "No hosted memory account",
-    body: "The local memory path needs no cloud service or memory API key. Your agent keeps using its own provider.",
-  },
-];
-
-const questions = [
-  {
-    question: "Does remembering really cost zero tokens?",
-    answer:
-      "Local storage and lexical retrieval need no LLM calls. Local embeddings and reranking use your machine’s compute. Memory delivered to an agent still consumes context tokens; optional answer generation and model-assisted harvesting have separate costs.",
-  },
-  {
-    question: "Can I use it offline?",
-    answer:
-      "Local memory works offline. Installation and the first download of optional models need a connection. Whether the rest of your session works offline depends on the agent and model you use.",
-  },
-  {
-    question: "Which agents can use it?",
-    answer:
-      "Setup supports Claude Code, Codex, Cursor, Pi, and OpenClaw. Integration behavior varies: Cursor uses MCP and guidance rather than automatic prompt hooks. The installation guide covers each host.",
-  },
-  {
-    question: "What do the new benchmark numbers prove?",
-    answer:
-      "They measure delivery of stored evidence on a frozen synthetic fixture. They do not measure whether an agent gives a correct final answer. The v2.8.0 structured-fact guard is opt-in, and compound questions can still miss an attribute.",
-  },
-];
-
 export default function HomePage() {
   return (
-    <main id="main-content" tabIndex={-1} className="km-home flex-1">
-      <section className="km-hero">
-        <div className="km-hero-grid">
-          <div className="min-w-0">
-            <p className="km-eyebrow">
-              <span
-                className="mr-2 inline-block size-2 rounded-full bg-fd-primary"
-                aria-hidden
-              />
-              Local memory for coding agents
-            </p>
-            <h1 className="max-w-2xl font-mono text-[2.65rem] leading-[1.12] font-semibold tracking-[-0.055em] sm:text-6xl">
-              Your next session starts with what you learned.
-            </h1>
-            <p className="mt-6 max-w-xl text-lg leading-8 text-fd-muted-foreground">
-              Kimetsu remembers your project’s decisions, conventions, and
-              fixes, then brings relevant context into the next task. One Rust
-              binary, alongside the agent you already use.
-            </p>
-            <div className="mt-8 flex flex-wrap gap-3">
-              <a href="#get-started" className="km-button-primary">
-                Install Kimetsu <ArrowRight className="size-4" aria-hidden />
-              </a>
-              <a href="#how-it-works" className="km-button-secondary">
-                See how it works
-              </a>
-            </div>
-            <p className="mt-5 text-xs text-fd-muted-foreground">
-              Open source · MIT / Apache-2.0 · Linux, macOS & Windows
-            </p>
-          </div>
-          <figure
-            className="km-memory-example min-w-0"
-            aria-label="Illustrative memory workflow"
+    <div id="main-content" tabIndex={-1} className="km-home flex-1">
+      <section aria-labelledby="home-title" className="km-hero">
+        <div className="mx-auto max-w-3xl text-center">
+          <h1
+            id="home-title"
+            className="font-mono text-[2.25rem] leading-[1.15] font-semibold tracking-[-0.055em] sm:text-5xl lg:text-[3.5rem]"
           >
-            <div className="flex items-center justify-between gap-3 border-b border-fd-border px-5 py-4 text-xs text-fd-muted-foreground">
-              <span className="inline-flex items-center gap-2 font-mono">
-                <Terminal className="size-4" aria-hidden /> project / memory
-              </span>
-              <span>Illustrative workflow</span>
-            </div>
-            <div className="p-5 sm:p-7">
-              <div className="flex items-center gap-3 font-mono text-xs text-fd-muted-foreground">
-                <span className="km-step">01</span> A lesson from this session
-              </div>
-              <p className="mt-4 text-lg leading-7">
-                “Regenerate the API client after changing the schema.”
-              </p>
-              <div
-                className="my-6 ml-4 h-8 border-l border-dashed border-fd-primary/60"
-                aria-hidden
-              />
-              <div className="flex items-center gap-3 font-mono text-xs text-fd-muted-foreground">
-                <span className="km-step">02</span> Context for the next task
-              </div>
-              <p className="mt-4 text-sm text-fd-muted-foreground">
-                Your agent is about to edit the API.
-              </p>
-              <div className="mt-4 rounded-xl border border-fd-primary/30 bg-fd-primary/5 p-4">
-                <p className="mb-2 text-xs font-semibold text-fd-primary">
-                  Relevant project memory
-                </p>
-                <p className="text-sm leading-6">
-                  After changing the schema, run{" "}
-                  <code className="font-mono" translate="no">
-                    npm run generate:api
-                  </code>{" "}
-                  and commit the generated client.
-                </p>
-              </div>
-            </div>
-            <div className="border-t border-fd-border px-5 py-4 text-xs text-fd-muted-foreground">
-              Saved locally. Available across sessions.
-            </div>
-          </figure>
-        </div>
-      </section>
-      <div className="border-y border-fd-border bg-fd-card/40">
-        <div className="mx-auto flex max-w-6xl flex-wrap items-center justify-center gap-x-7 gap-y-3 px-6 py-5 text-sm">
-          <span className="text-fd-muted-foreground">Works alongside</span>
-          {["Claude Code", "Codex", "Cursor", "Pi", "OpenClaw"].map((host) => (
-            <span key={host} className="font-mono font-medium">
-              {host}
-            </span>
-          ))}
-          <Link href="/docs/install" className="km-text-link">
-            Host setup →
-          </Link>
-        </div>
-      </div>
-      <QuickStart />
-      <ExploreSection />
-      <section
-        id="evidence"
-        aria-labelledby="evidence-title"
-        className="km-section scroll-mt-24"
-      >
-        <div className="grid gap-10 lg:grid-cols-[0.85fr_1.15fr]">
-          <div>
-            <p className="km-eyebrow">Measured, with the limits included</p>
-            <h2 id="evidence-title" className="km-heading">
-              Better memory knows when evidence is missing.
-            </h2>
-            <p className="mt-4 leading-7 text-fd-muted-foreground">
-              The structured-answerability study for v2.8.0 reduced unwanted
-              injections while preserving positive retrieval hits.
-            </p>
-            <p className="mt-4 text-sm leading-6 text-fd-muted-foreground">
-              45 synthetic cases, two repeats. Evidence delivery, not
-              generated-answer accuracy. Exact metadata matched 36/45 cases in
-              each repeat.
-            </p>
-            <Link
-              href="/docs/memory-benchmark/answerability"
-              className="km-text-link mt-5 inline-block"
-            >
-              Inspect the results and remaining gaps →
-            </Link>
-          </div>
-          <div className="min-w-0 overflow-hidden rounded-2xl border border-fd-border bg-fd-card">
-            <div className="flex flex-wrap items-center justify-between gap-3 border-b border-fd-border p-5">
-              <h3 className="font-semibold">Structured fact guard</h3>
-              <span className="rounded-full border border-fd-border px-3 py-1 text-xs text-fd-muted-foreground">
-                v2.8.0 · Opt-in
-              </span>
-            </div>
-            <table className="w-full text-sm">
-              <caption className="sr-only">
-                Paired comparison on the frozen structured-answerability fixture
-              </caption>
-              <thead>
-                <tr className="text-xs text-fd-muted-foreground">
-                  <th scope="col" className="p-4 text-left font-medium">
-                    Measure
-                  </th>
-                  <th scope="col" className="p-4 text-right font-medium">
-                    Before
-                  </th>
-                  <th scope="col" className="p-4 text-right font-medium">
-                    After
-                  </th>
-                </tr>
-              </thead>
-              <tbody className="tabular-nums">
-                {[
-                  ["Unwanted injections ↓", "15/18", "3/18"],
-                  ["Positive retrieval hits", "24/27", "24/27"],
-                  ["Exact evidence metadata", "Not emitted", "36/45 (80%)"],
-                  ["P95 latency", "376.6 ms", "386.6 ms"],
-                  ["Mean response bytes", "613.5", "651.2"],
-                ].map(([label, before, after]) => (
-                  <tr key={label} className="border-t border-fd-border">
-                    <th scope="row" className="p-4 text-left font-normal">
-                      {label}
-                    </th>
-                    <td className="p-4 text-right text-fd-muted-foreground">
-                      {before}
-                    </td>
-                    <td className="p-4 text-right font-medium">{after}</td>
-                  </tr>
-                ))}
-              </tbody>
-            </table>
-            <p className="border-t border-fd-border p-5 text-xs leading-5 text-fd-muted-foreground">
-              80% fewer unwanted injections; p95 latency increased by about
-              2.7%. This feature remains disabled by default. Measurements use
-              the pre-release implementation; see the study for build
-              fingerprints and publication status.
-            </p>
-          </div>
-        </div>
-        <div className="mt-8 flex flex-wrap items-center justify-between gap-3 border-t border-fd-border pt-5 text-sm">
-          <p className="text-fd-muted-foreground">
-            Looking for LoCoMo, LongMemEval, or earlier BrainBench results?
+            Persistent memory for coding agents.
+          </h1>
+          <p className="mx-auto mt-5 max-w-2xl text-lg leading-8 text-fd-muted-foreground">
+            Keep project decisions, conventions, and fixes between sessions.
+            Kimetsu stores them locally and retrieves the context your agent
+            needs.
           </p>
-          <Link href="/docs/memory-benchmark" className="km-text-link">
-            Browse all benchmarks →
-          </Link>
-        </div>
-      </section>
-      <section aria-labelledby="ownership-title" className="km-section">
-        <p className="km-eyebrow">Small footprint, clear ownership</p>
-        <h2 id="ownership-title" className="km-heading mb-8">
-          Your project. Your memory.
-        </h2>
-        <div className="grid gap-5 md:grid-cols-3">
-          {principles.map((item) => (
-            <article
-              key={item.title}
-              className="rounded-xl border border-fd-border p-6"
-            >
-              <item.icon aria-hidden className="mb-5 size-6 text-fd-primary" />
-              <h3 className="mb-3 font-semibold">{item.title}</h3>
-              <p className="text-sm leading-6 text-fd-muted-foreground">
-                {item.body}
-              </p>
-            </article>
-          ))}
-        </div>
-      </section>
-      <BrainSharing />
-      <section aria-labelledby="questions-title" className="km-section">
-        <div className="grid gap-8 md:grid-cols-[0.7fr_1.3fr]">
-          <div>
-            <p className="km-eyebrow">Before you install</p>
-            <h2 id="questions-title" className="km-heading">
-              A few useful answers.
-            </h2>
-            <Link href="/docs" className="km-text-link mt-5 inline-block">
-              Read the documentation →
-            </Link>
-          </div>
-          <div>
-            {questions.map((item) => (
-              <details
-                key={item.question}
-                className="border-b border-fd-border py-5 first:border-t"
-              >
-                <summary className="cursor-pointer font-medium leading-6">
-                  {item.question}
-                </summary>
-                <p className="mt-4 text-sm leading-7 text-fd-muted-foreground">
-                  {item.answer}
-                </p>
-              </details>
-            ))}
+          <div className="mt-7 flex flex-wrap justify-center gap-3">
+            <a href="#get-started" className="km-button-primary">
+              Install Kimetsu <ArrowRight className="size-4" aria-hidden />
+            </a>
+            <a href="#benchmarks" className="km-button-secondary">
+              View benchmarks
+            </a>
           </div>
         </div>
       </section>
-      <ProjectsSection />
+      <BenchmarkResults />
+      <ExploreSection />
+      <QuickStart />
       <AboutContact />
-      <footer className="mx-auto flex max-w-6xl flex-col justify-between gap-5 px-6 py-10 text-sm sm:flex-row">
-        <p className="text-fd-muted-foreground">
-          <span className="font-mono font-semibold text-fd-foreground">
-            Kimetsu
-          </span>{" "}
-          · Knowledge that carries forward.
-        </p>
+      <footer className="mx-auto flex max-w-6xl flex-col justify-between gap-5 px-6 py-8 text-sm sm:flex-row">
+        <p className="font-mono font-semibold">Kimetsu</p>
         <nav aria-label="Footer" className="flex flex-wrap gap-5">
           <a href="#about" className="km-text-link">
             About
@@ -306,6 +56,6 @@ export default function HomePage() {
           </a>
         </nav>
       </footer>
-    </main>
+    </div>
   );
 }
diff --git a/src/app/global.css b/src/app/global.css
index 9ea187f..e07931d 100644
--- a/src/app/global.css
+++ b/src/app/global.css
@@ -61,7 +61,7 @@ html {
 }
 
 .km-hero {
-  padding: 5.5rem 1.5rem 5rem;
+  padding: 3.5rem 1.5rem 2.5rem;
   background-image: radial-gradient(
     var(--color-fd-border) 0.7px,
     transparent 0.7px
@@ -69,39 +69,25 @@ html {
   background-size: 24px 24px;
 }
 
-.km-hero-grid {
-  display: grid;
-  gap: 3.5rem;
+.km-section {
   max-width: 72rem;
   margin-inline: auto;
-  align-items: center;
-}
-
-.km-memory-example {
-  overflow: hidden;
-  border: 1px solid var(--color-fd-border);
-  border-radius: 1rem;
-  background: var(--color-fd-background);
-  box-shadow: 0 14px 45px -28px rgb(0 0 0 / 35%);
+  padding: 3.5rem 1.5rem;
+  border-bottom: 1px solid var(--color-fd-border);
 }
 
-.km-step {
-  display: inline-flex;
-  align-items: center;
-  justify-content: center;
-  width: 2rem;
-  height: 2rem;
-  flex-shrink: 0;
-  border: 1px solid var(--color-fd-border);
-  border-radius: 50%;
-  color: var(--color-fd-primary);
+.km-benchmarks {
+  padding-top: 1.5rem;
 }
 
-.km-section {
-  max-width: 72rem;
-  margin-inline: auto;
-  padding: 4.5rem 1.5rem;
-  border-bottom: 1px solid var(--color-fd-border);
+.km-benchmark-score {
+  margin-block: 1.25rem 0.75rem;
+  font-family: var(--font-mono);
+  font-size: clamp(3rem, 5vw, 4.25rem);
+  font-weight: 600;
+  line-height: 1;
+  letter-spacing: -0.06em;
+  font-variant-numeric: tabular-nums;
 }
 
 .km-eyebrow {
@@ -173,12 +159,6 @@ html {
   text-decoration: underline;
 }
 
-@media (min-width: 1024px) {
-  .km-hero-grid {
-    grid-template-columns: 1.15fr 0.85fr;
-  }
-}
-
 @media (max-width: 639px) {
   .km-hero {
     padding: 3rem 1.25rem;
@@ -188,6 +168,10 @@ html {
     padding: 3rem 1.25rem;
   }
 
+  .km-benchmarks {
+    padding-top: 0.5rem;
+  }
+
   .km-home table :is(th, td) {
     padding: 0.85rem 0.6rem;
   }
diff --git a/src/lib/layout.shared.tsx b/src/lib/layout.shared.tsx
index 1de209d..6daaf54 100644
--- a/src/lib/layout.shared.tsx
+++ b/src/lib/layout.shared.tsx
@@ -31,6 +31,10 @@ export function baseOptions(): BaseLayoutProps {
         url: links.github,
         external: true,
       },
+      {
+        text: "Benchmarks",
+        url: "/#benchmarks",
+      },
       {
         text: "Install",
         url: "/docs/install",
@@ -41,11 +45,6 @@ export function baseOptions(): BaseLayoutProps {
         url: "/docs",
         active: "nested-url",
       },
-      {
-        text: "Benchmarks",
-        url: "/docs/memory-benchmark",
-        active: "nested-url",
-      },
       {
         text: "Projects",
         url: "/projects",