[2026-10-14] eagle: personal/projects/personal-os/autonomous-agent-safety.md personal/projects/personal-os/executor-orchestrator-redesign.md personal/projects/personal-os/executor-v2-redesign.md personal/projects/personal-os/hermes-cron-jobs.md personal/projects/personal-os/hermes-deployment-patterns.md personal/projects/personal-os/hermes-native-vs-docker.md personal/projects/personal-os/knowledge-lifecycle.md personal/projects/personal-os/multi-agent-design-patterns.md personal/projects/personal-os/multi-host-cron-topology.md personal/projects/personal-os/obsidian-vault-strategy.md

personal/projects/personal-os/multi-agent-design-patterns.md

@@ -1,7 +1,7 @@
 ---
 title: Multi-Agent Design Patterns
 created: '2026-05-25'
-updated: '2026-05-25'
+updated: '2026-10-14'
 type: concept
 namespace: work
 tags: [agent, architecture, system]
@@ -11,16 +11,16 @@ sources:
   - wiki/concepts/autonomous-agent-safety.md
   - wiki/concepts/agent-memory-architecture.md
 related:
-  - "[[concepts/executor-orchestrator]]"
-  - "[[concepts/autonomous-agent-safety]]"
-  - "[[concepts/agent-memory-architecture]]"
+  - "[[personal/projects/personal-os/executor-orchestrator-redesign]]"
+  - "[[personal/projects/personal-os/autonomous-agent-safety]]"
+  - "[[personal/projects/personal-os/agent-memory-architecture]]"
 ---
 
 # Multi-Agent Design Patterns
 
 Synthesis of recurring patterns across the personal-os multi-agent system
-and related agent architectures. Distilled from [[concepts/executor-orchestrator]],
-[[concepts/autonomous-agent-safety]], and [[concepts/agent-memory-architecture]].
+and related agent architectures. Distilled from [[personal/projects/personal-os/executor-orchestrator-redesign]],
+[[personal/projects/personal-os/autonomous-agent-safety]], and [[personal/projects/personal-os/agent-memory-architecture]].
 
 ## Pattern 1 — Orchestrator / Worker Split
 
@@ -42,7 +42,7 @@ orchestrator has the only escalation path to the human.
 require escalation. Publish the table explicitly.
 
 **Why:** Autonomous agents fail catastrophically when they expand scope
-unexpectedly (see [[concepts/executor-security-incident]]). Explicit tables
+unexpectedly (see [[personal/projects/personal-os/executor-security-analysis]]). Explicit tables
 make failure modes visible.
 
 **Implementation:** Message-type-based approval table. Unknown message types
@@ -64,7 +64,7 @@ knowledge (semantic memory) from immutable facts (procedural/episodic).
 fail to retain important session-to-session knowledge.
 
 **In personal-os:** status.md (working) / wiki pages (semantic) /
-SCHEMA.md + vault-filling-guide (procedural). See [[concepts/agent-memory-architecture]].
+SCHEMA.md + vault-filling-guide (procedural). See [[personal/projects/personal-os/agent-memory-architecture]].
 
 **Pattern rule:** Never update semantic memory from within an active session.
 Crystallize post-session. Never trust working memory as a source of truth
@@ -101,7 +101,7 @@ question in list" do not benefit from LLM reasoning and introduce failure modes.
 
 ## See Also
 
-- [[concepts/executor-orchestrator]] — concrete orchestrator/worker implementation
-- [[concepts/autonomous-agent-safety]] — safety checklist derived from incidents
-- [[concepts/agent-memory-architecture]] — memory taxonomy for LLM agents
-- [[entities/psychologist-app]] — dual-agent architecture (patterns 1 and 4)
+- [[personal/projects/personal-os/executor-orchestrator-redesign]] — concrete orchestrator/worker implementation
+- [[personal/projects/personal-os/autonomous-agent-safety]] — safety checklist derived from incidents
+- [[personal/projects/personal-os/agent-memory-architecture]] — memory taxonomy for LLM agents
+- [[personal/projects/psychologist-app/overview]] — dual-agent architecture (patterns 1 and 4)