diff --git a/graph/edges/fix-partial-uuid-prefix-matchi--BUILDS_ON--cognitive-memory-v30-rich-edge-6100de.md b/graph/edges/fix-partial-uuid-prefix-matchi--BUILDS_ON--cognitive-memory-v30-rich-edge-6100de.md
new file mode 100644
index 00000000000..d61ed33ce23
--- /dev/null
+++ b/graph/edges/fix-partial-uuid-prefix-matchi--BUILDS_ON--cognitive-memory-v30-rich-edge-6100de.md
@@ -0,0 +1,13 @@
+---
+id: 6100de8d-c1dc-4ec9-8981-5c65a396da0e
+type: BUILDS_ON
+from_id: 89f32ef3-2d87-4b8c-aa6e-ce5a7f60566c
+from_title: "Fix: Partial UUID prefix matching in cognitive memory client (git-style)"
+to_id: 9ea72015-0b85-4a42-9ae1-144866f8d86f
+to_title: "Cognitive Memory v3.0: Rich Edges + Hybrid Embeddings + MCP Server"
+strength: 0.8
+created: "2026-02-28T06:03:25.212458+00:00"
+updated: "2026-02-28T06:03:25.212458+00:00"
+---
+
+Prefix matching is a UX improvement built on top of the v3.0 MCP server client architecture
diff --git a/graph/fixes/fix-partial-uuid-prefix-matching-in-cognitive-memory-client-89f32e.md b/graph/fixes/fix-partial-uuid-prefix-matching-in-cognitive-memory-client-89f32e.md
index 94fe91b6b18..851fe66c9ca 100644
--- a/graph/fixes/fix-partial-uuid-prefix-matching-in-cognitive-memory-client-89f32e.md
+++ b/graph/fixes/fix-partial-uuid-prefix-matching-in-cognitive-memory-client-89f32e.md
@@ -6,7 +6,13 @@ tags: [cognitive-memory, fix, uuid, mcp, client.py, claude-configs]
 importance: 0.8
 confidence: 0.8
 created: "2026-02-28T06:03:13.780326+00:00"
-updated: "2026-02-28T06:03:13.780326+00:00"
+updated: "2026-02-28T06:03:25.212458+00:00"
+relations:
+  - target: 9ea72015-0b85-4a42-9ae1-144866f8d86f
+    type: BUILDS_ON
+    direction: outgoing
+    strength: 0.8
+    edge_id: 6100de8d-c1dc-4ec9-8981-5c65a396da0e
 ---
 
 # Partial UUID Prefix Matching in CognitiveMemoryClient
diff --git a/graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md b/graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md
index f91cad67cd7..b5d0803df23 100644
--- a/graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md
+++ b/graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md
@@ -6,13 +6,18 @@ tags: [cognitive-memory, mcp, architecture, upgrade]
 importance: 0.9
 confidence: 0.8
 created: "2026-02-19T20:10:42.128691+00:00"
-updated: "2026-02-28T04:53:46.340559+00:00"
+updated: "2026-02-28T06:03:25.212458+00:00"
 relations:
   - target: dc6b6c6f-1319-47cf-a691-dd40751ff121
     type: BUILDS_ON
     direction: incoming
     strength: 0.85
     edge_id: 78728fca-82c7-4c30-b677-aadc663fb40b
+  - target: 89f32ef3-2d87-4b8c-aa6e-ce5a7f60566c
+    type: BUILDS_ON
+    direction: incoming
+    strength: 0.8
+    edge_id: 6100de8d-c1dc-4ec9-8981-5c65a396da0e
 ---
 
 Major upgrade to cognitive-memory skill. Phase 1: Rich edges as first-class markdown files in graph/edges/ with bidirectional frontmatter refs (edge_id field). relate() returns edge_id string instead of bool. Cascade deletion on memory delete. CLI: edge-get, edge-search, edge-update, edge-delete. Phase 2: Hybrid embedding providers (Ollama local + OpenAI optional) with automatic fallback chain. _config.json stores provider settings (gitignored). Dimension mismatch safety triggers re-embedding on provider switch. Phase 3: MCP server (mcp_server.py) with 18 tools via JSON-RPC 2.0 stdio protocol. Registered in ~/.claude.json. Phase 4: Updated SKILL.md, SCHEMA.md, feature.json to v3.0.0. Index version bumped from 1 to 2 (adds edges section). All stdlib-only, no external dependencies.