diff --git a/compose.yaml b/compose.yaml
index 8f1db21..b717a81 100644
--- a/compose.yaml
+++ b/compose.yaml
@@ -118,7 +118,7 @@ networks:
 
 # ── Volumes ───────────────────────────────────────────────────────────────────
 volumes:
-  open-webui-data:
+  anythingllm-data:
 
 # ==============================================================================
 services:
@@ -330,20 +330,27 @@ services:
   #   docker compose --profile <model> --profile webui up -d
   # Connects to whichever model is running via the llama-current DNS alias.
   # Open WebUI retries on startup so no depends_on needed.
-  openwebui:
-    image: ghcr.io/open-webui/open-webui:main
-    container_name: open_webui
+  # ── AnythingLLM (replaced open-webui 2026-07-10) ────────────────────────────
+  #   docker compose --profile webui up -d anythingllm
+  # Talks to the swap stack by service name; pick any model id from
+  # swap-stack/config.yaml (duo ids keep the resident pair loaded).
+  anythingllm:
+    image: mintplexlabs/anythingllm:latest
+    container_name: anythingllm
     profiles: [webui]
     environment:
-      - OPENAI_API_BASE_URL=http://llama-current:8080/v1
-      - OPENAI_API_KEY=sk-no-key-needed
-      - WEBUI_AUTH=false
+      - LLM_PROVIDER=generic-openai
+      - GENERIC_OPEN_AI_BASE_PATH=http://llama-swap-stack:8080/v1
+      - GENERIC_OPEN_AI_API_KEY=sk-no-key-needed
+      - GENERIC_OPEN_AI_MODEL_PREF=ornith-35b-duo
+      - GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=131072
+      - STORAGE_DIR=/app/server/storage
     ports:
-      - "3000:8080"
+      - "3001:3001"
     networks:
       - llama-net
     volumes:
-      - open-webui-data:/app/backend/data
+      - anythingllm-data:/app/server/storage
     restart: unless-stopped
 
   # ── BENCHMARKS ─────────────────────────────────────────────────────────────
diff --git a/swap-stack/config.yaml b/swap-stack/config.yaml
index ed07dc3..4b4851c 100644
--- a/swap-stack/config.yaml
+++ b/swap-stack/config.yaml
@@ -102,17 +102,6 @@ models:
       --cont-batching --parallel 1
     ttl: 300
 
-  "qwen36-35b":
-    name: "Qwen3.6-35B-A3B UD-IQ4_XS"
-    description: "35B/3B-active MoE, 17.7GB mmap > RAM. Stop heavy containers first"
-    cmd: |
-      ${server-base} ${moe-offload} ${q8-kv}
-      --model /models/Qwen3.6-35B-A3B-UD-IQ4_XS.gguf
-      --ctx-size 32768
-      --batch-size 1024 --ubatch-size 512
-      --cont-batching --parallel 1
-    ttl: 300
-
   "qwen36-35b-q2":
     name: "Qwen3.6-35B-A3B UD-Q2_K_XL"
     description: "DAILY DRIVER 35B: 23.0 tg / 36 pp. ds4 asymmetric recipe (dense high-bit, experts 2-bit), 12.3GB page-cache resident, last 3 expert layers in VRAM. Gates pass"
@@ -137,16 +126,9 @@ models:
       --cont-batching --parallel 1
     ttl: 300
 
-  "ornith-35b-iq4":
-    name: "Ornith-1.0-35B IQ4_XS"
-    description: "Quality-first variant, 18.8GB mmap > RAM = ~2.8 t/s thrash. Batch jobs only (or post-RAM-upgrade)"
-    cmd: |
-      ${server-base} ${moe-offload} ${q8-kv}
-      --model /models/deepreinforce-ai_Ornith-1.0-35B-IQ4_XS.gguf
-      --ctx-size 32768
-      --batch-size 1024 --ubatch-size 512
-      --cont-batching --parallel 1
-    ttl: 300
+  # (IQ4 variants of ornith-35b/qwen36-35b deleted 2026-07-10 — 36.5GB disk,
+  #  both were >RAM thrash-only until the 64GB upgrade. Re-download if needed:
+  #  bartowski Ornith-1.0-35B IQ4_XS, unsloth Qwen3.6-35B-A3B UD-IQ4_XS.)
 
   # ── Dense 9B (RAM-bandwidth-bound, ~4.4 t/s) ───────────────────────────────
   # (ik_llama / upstream-master A/B variants removed 2026-07-10 — questions