Large World graph, agent platform, brain stack & dashboard rebuild

Frontend
- Large World: collapse org/company/team tiers into one expandable React Flow
  hierarchy (WorldFlow) with per-click expand, persisted node positions, a
  compact tree sidebar, wrench multi-select delete across levels, and a sized
  right slide-out (phone/tablet/full) showing an agent summary + drill button.
- Agent page: GitHub-style animated contribution grid (VitalsCard), collapsible
  System Prompt + Personality cards, restructured anatomy cards, bigger avatar
  with name/title header row, Markdown/JSON-aware rendering, brain registry +
  history, avatar generate/upload.
- User-icon menu (Infrastructure/Brains/Tools/Profile/Credits) + ToolPanel;
  Master Planner deploy wizard (Specialists/Swarm/Scheduled/Triggered);
  Team Runs view; reap-progress modal; dashboard is the single live interface.

Backend
- cm-brain crate (.brain as the agent definition) + brain apply/history.
- Hard-purge reap (FK-ordered) + sandbox release + SSE batch-delete.
- Swarm self-verifying loop, mode-aware planner, web.search tool, webhooks
  (migration 0013), org/company/team delete endpoints, scheduler sweeps.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

frontend/src/components/marketing/Faq.tsx

@@ -5,8 +5,8 @@ import { useState } from "react";
 
 const FAQS: { q: string; a: string }[] = [
   {
-    q: "What is a claw?",
-    a: "A claw is an AI coworker — an agent with a job, a chat, and its own sandboxed computer. Your team talks to it like a teammate, and it uses tools to get work done.",
+    q: "What is an agent?",
+    a: "An agent is an AI coworker — with a job, a chat, and its own sandboxed computer. Your team talks to it like a teammate, and it uses tools to get work done.",
   },
   {
     q: "How do you keep agents safe?",

frontend/src/components/marketing/HierarchyDiagram.tsx

@@ -76,9 +76,9 @@ export function HierarchyDiagram() {
   // node top-centers
   const orch = { x: 318, y: 16 };
   const tier1 = [
-    { x: 38, y: 168, title: "Marketing Claw", sub: "mid-level agent" },
-    { x: 318, y: 168, title: "Engineering Claw", sub: "mid-level agent", active: true },
-    { x: 598, y: 168, title: "Operations Claw", sub: "mid-level agent" },
+    { x: 38, y: 168, title: "Marketing Agent", sub: "mid-level agent" },
+    { x: 318, y: 168, title: "Engineering Agent", sub: "mid-level agent", active: true },
+    { x: 598, y: 168, title: "Operations Agent", sub: "mid-level agent" },
   ];
   const tier2 = [
     { x: 38, y: 326, title: "Send email", sub: "leaves sandbox", gated: true },

frontend/src/components/marketing/Landing.tsx

@@ -187,7 +187,7 @@ export function Landing() {
           <p className="mb-8 max-w-[480px] text-[18px] leading-relaxed text-[#a8a8b0]">
             Every unit of work is a{" "}
             <span className="font-semibold text-foreground">topology</span> — a graph of role-slots
-            bound to real AI agents. Compose and run agentic systems from a single claw up to a
+            bound to real AI agents. Compose and run agentic systems from a single agent up to a
             whole org, on a durable, crash-resumable runner.
           </p>
           <div className="mb-[30px] flex flex-wrap gap-3">
@@ -248,10 +248,10 @@ export function Landing() {
         </div>
         <div className="grid grid-cols-1 gap-4 sm:grid-cols-2 lg:grid-cols-4">
           {[
-            { n: "01 · SINGLE", t: "A claw", d: "One agent in a §15 sandbox. Chat with it, give it skills, point it at a task." },
-            { n: "02 · TEAM", t: "A team", d: "A topology of claws — lead, researchers, writer, critic — running one of 12 patterns." },
+            { n: "01 · SINGLE", t: "An agent", d: "One agent in a §15 sandbox. Chat with it, give it skills, point it at a task." },
+            { n: "02 · TEAM", t: "A team", d: "A topology of agents — lead, researchers, writer, critic — running one of 12 patterns." },
             { n: "03 · COMPANY", t: "A company", d: "Teams composed into a coordinating topology. Run the parent, run every child." },
-            { n: "04 · ORG", t: "A whole org", d: "Companies under one roof. Recursive execution all the way down to the leaf claws.", hot: true },
+            { n: "04 · ORG", t: "A whole org", d: "Companies under one roof. Recursive execution all the way down to the leaf agents.", hot: true },
           ].map((c) => (
             <div
               key={c.n}
@@ -265,7 +265,7 @@ export function Landing() {
                 {c.n}
               </div>
               <div className="mb-2 text-coral">
-                <MeshMark size={32} variant={c.t === "A claw" ? "team" : c.t === "A team" ? "team" : c.t === "A company" ? "company" : "org"} title="" />
+                <MeshMark size={32} variant={c.t === "An agent" ? "team" : c.t === "A team" ? "team" : c.t === "A company" ? "company" : "org"} title="" />
               </div>
               <div className="mb-1.5 text-[18px] font-bold">{c.t}</div>
               <div className="text-[13px] leading-relaxed text-[#8a8a92]">{c.d}</div>
@@ -308,7 +308,7 @@ export function Landing() {
               Run the parent, run everything beneath it.
             </h2>
             <p className="mb-[26px] text-[17px] leading-relaxed text-[#a8a8b0]">
-              Executing a node runs its entire sub-topology, all the way down to the leaf claws — on a
+              Executing a node runs its entire sub-topology, all the way down to the leaf agents — on a
               durable runner that checkpoints every step.
             </p>
             <div className="flex flex-col gap-3.5">
@@ -515,7 +515,7 @@ export function Landing() {
           }}
         >
           <h2 className="mb-4 text-[46px] font-bold tracking-[-0.035em] text-balance">
-            Deploy your first claw.
+            Deploy your first agent.
           </h2>
           <p className="mb-[30px] text-[18px] text-[#a8a8b0]">
             From one agent to a whole org — same model, same guarantees.