pass 1 for ai readable

docs/en/ai/memory/examples.mdx

@@ -0,0 +1,11 @@
+---
+title: "Memory: Examples"
+description: "Runnable examples for scoped storage and semantic retrieval in CrewAI."
+icon: "rocket-launch"
+mode: "wide"
+---
+
+## Example links
+
+- [/en/concepts/memory](/en/concepts/memory)
+- [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)

docs/en/ai/memory/index.mdx

@@ -0,0 +1,24 @@
+---
+title: "Memory: Concepts"
+description: "Designing recall systems with scope boundaries and state-vs-memory separation."
+icon: "database"
+mode: "wide"
+---
+
+## When to use memory
+
+- You need semantic recall across runs.
+- You need long-term context outside immediate flow state.
+
+## When to use state instead
+
+- Data is only needed for current control flow.
+- Data must remain deterministic and explicit per step.
+
+## Canonical links
+
+- Reference: [/en/ai/memory/reference](/en/ai/memory/reference)
+- Patterns: [/en/ai/memory/patterns](/en/ai/memory/patterns)
+- Troubleshooting: [/en/ai/memory/troubleshooting](/en/ai/memory/troubleshooting)
+- Examples: [/en/ai/memory/examples](/en/ai/memory/examples)
+- Existing docs: [/en/concepts/memory](/en/concepts/memory)

docs/en/ai/memory/patterns.mdx

@@ -0,0 +1,17 @@
+---
+title: "Memory: Patterns"
+description: "Practical memory patterns for session recall, scoped retrieval, and hybrid flow-state designs."
+icon: "diagram-project"
+mode: "wide"
+---
+
+## Patterns
+
+1. Session-scoped recall (`/chat/{session_id}`)
+2. Project-scoped knowledge (`/project/{project_id}`)
+3. Hybrid pattern: flow state for control, memory for long-tail context
+
+## Reference
+
+- [/en/learn/flowstate-chat-history](/en/learn/flowstate-chat-history)
+- [/en/guides/flows/mastering-flow-state](/en/guides/flows/mastering-flow-state)

docs/en/ai/memory/reference.mdx

@@ -0,0 +1,23 @@
+---
+title: "Memory: Reference"
+description: "Reference for remember/recall contracts, scopes, and retrieval tuning."
+icon: "book"
+mode: "wide"
+---
+
+## API surface
+
+- `remember(content, scope=...)`
+- `recall(query, limit=...)`
+- `extract_memories(text)`
+- `scope(path)` and `subscope(name)`
+
+## Scope rules
+
+- use `/{entity_type}/{identifier}` paths
+- keep hierarchy shallow
+- isolate sessions by stable identifiers
+
+## Canonical source
+
+Primary API details live in [/en/concepts/memory](/en/concepts/memory).

docs/en/ai/memory/troubleshooting.mdx

@@ -0,0 +1,12 @@
+---
+title: "Memory: Troubleshooting"
+description: "Diagnose poor recall quality, scope leakage, and stale memory retrieval."
+icon: "circle-exclamation"
+mode: "wide"
+---
+
+## Common issues
+
+- Irrelevant recall: tighten scopes and query wording.
+- Missing recall: check scope path and recency weighting.
+- Scope leakage: avoid shared broad scopes for unrelated workflows.