diff --git a/lib/crewai-tools/pyproject.toml b/lib/crewai-tools/pyproject.toml
index a683b9967..8e0b6132a 100644
--- a/lib/crewai-tools/pyproject.toml
+++ b/lib/crewai-tools/pyproject.toml
@@ -8,12 +8,10 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "lancedb~=0.5.4",
     "pytube~=15.0.0",
     "requests~=2.32.5",
     "docker~=7.1.0",
     "crewai==1.9.3",
-    "lancedb~=0.5.4",
     "tiktoken~=0.8.0",
     "beautifulsoup4~=4.13.4",
     "python-docx~=1.2.0",
diff --git a/lib/crewai/pyproject.toml b/lib/crewai/pyproject.toml
index b4b3e2ecc..30e370072 100644
--- a/lib/crewai/pyproject.toml
+++ b/lib/crewai/pyproject.toml
@@ -42,7 +42,7 @@ dependencies = [
     "mcp~=1.26.0",
     "uv~=0.9.13",
     "aiosqlite~=0.21.0",
-    "lancedb>=0.4.0",
+    "lancedb>=0.29.2",
 ]
 
 [project.urls]
diff --git a/lib/crewai/src/crewai/agent/core.py b/lib/crewai/src/crewai/agent/core.py
index 22b5a24ca..e121a9771 100644
--- a/lib/crewai/src/crewai/agent/core.py
+++ b/lib/crewai/src/crewai/agent/core.py
@@ -384,10 +384,10 @@ class Agent(BaseAgent):
                 )
                 if unified_memory is not None:
                     query = task.description
-                    matches = unified_memory.recall(query, limit=10)
+                    matches = unified_memory.recall(query, limit=5)
                     if matches:
                         memory = "Relevant memories:\n" + "\n".join(
-                            f"- {m.record.content}" for m in matches
+                            m.format() for m in matches
                         )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
@@ -622,10 +622,10 @@ class Agent(BaseAgent):
                 )
                 if unified_memory is not None:
                     query = task.description
-                    matches = unified_memory.recall(query, limit=10)
+                    matches = unified_memory.recall(query, limit=5)
                     if matches:
                         memory = "Relevant memories:\n" + "\n".join(
-                            f"- {m.record.content}" for m in matches
+                            m.format() for m in matches
                         )
                 if memory.strip() != "":
                     task_prompt += self.i18n.slice("memory").format(memory=memory)
@@ -1811,11 +1811,11 @@ class Agent(BaseAgent):
                     ),
                 )
                 start_time = time.time()
-                matches = agent_memory.recall(formatted_messages, limit=10)
+                matches = agent_memory.recall(formatted_messages, limit=5)
                 memory_block = ""
                 if matches:
                     memory_block = "Relevant memories:\n" + "\n".join(
-                        f"- {m.record.content}" for m in matches
+                        m.format() for m in matches
                     )
                 if memory_block:
                     formatted_messages += "\n\n" + self.i18n.slice("memory").format(
diff --git a/lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py b/lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
index b36595ec9..1abfb6e5a 100644
--- a/lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
+++ b/lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
@@ -30,7 +30,7 @@ class CrewAgentExecutorMixin:
         memory = getattr(self.agent, "memory", None) or (
             getattr(self.crew, "_memory", None) if self.crew else None
         )
-        if memory is None or not self.task:
+        if memory is None or not self.task or getattr(memory, "_read_only", False):
             return
         if (
             f"Action: {sanitize_tool_name('Delegate work to coworker')}"
diff --git a/lib/crewai/src/crewai/cli/memory_tui.py b/lib/crewai/src/crewai/cli/memory_tui.py
index 98576670d..9dd91a42c 100644
--- a/lib/crewai/src/crewai/cli/memory_tui.py
+++ b/lib/crewai/src/crewai/cli/memory_tui.py
@@ -290,13 +290,20 @@ class MemoryTUI(App[None]):
         if self._memory is None:
             panel.update(self._init_error or "No memory loaded.")
             return
+        display_limit = 1000
         info = self._memory.info(path)
         self._last_scope_info = info
-        self._entries = self._memory.list_records(scope=path, limit=200)
+        self._entries = self._memory.list_records(scope=path, limit=display_limit)
         panel.update(_format_scope_info(info))
         panel.border_title = "Detail"
         entry_list = self.query_one("#entry-list", OptionList)
-        entry_list.border_title = f"Entries ({len(self._entries)})"
+        capped = info.record_count > display_limit
+        count_label = (
+            f"Entries (showing {display_limit} of {info.record_count} — display limit)"
+            if capped
+            else f"Entries ({len(self._entries)})"
+        )
+        entry_list.border_title = count_label
         self._populate_entry_list()
 
     def on_option_list_option_highlighted(
@@ -376,6 +383,11 @@ class MemoryTUI(App[None]):
                 return
 
             info_lines: list[str] = []
+            info_lines.append(
+                "[dim italic]Searched the full dataset"
+                + (f" within [bold]{scope}[/]" if scope else "")
+                + " using the recall flow (semantic + recency + importance).[/]\n"
+            )
             if not self._custom_embedder:
                 info_lines.append(
                     "[dim italic]Note: Using default OpenAI embedder. "
diff --git a/lib/crewai/src/crewai/lite_agent.py b/lib/crewai/src/crewai/lite_agent.py
index 5b7725a3b..66b710890 100644
--- a/lib/crewai/src/crewai/lite_agent.py
+++ b/lib/crewai/src/crewai/lite_agent.py
@@ -599,8 +599,8 @@ class LiteAgent(FlowTrackable, BaseModel):
             )
 
     def _save_to_memory(self, output_text: str) -> None:
-        """Extract discrete memories from the run and remember each. No-op if _memory is None."""
-        if self._memory is None:
+        """Extract discrete memories from the run and remember each. No-op if _memory is None or read-only."""
+        if self._memory is None or getattr(self._memory, "_read_only", False):
             return
         input_str = self._get_last_user_content() or "User request"
         try:
diff --git a/lib/crewai/src/crewai/memory/memory_scope.py b/lib/crewai/src/crewai/memory/memory_scope.py
index b828e3faf..705ec07de 100644
--- a/lib/crewai/src/crewai/memory/memory_scope.py
+++ b/lib/crewai/src/crewai/memory/memory_scope.py
@@ -145,7 +145,7 @@ class MemoryScope:
 
 
 class MemorySlice:
-    """View over multiple scopes: recall searches all, remember requires explicit scope unless read_only."""
+    """View over multiple scopes: recall searches all, remember is a no-op when read_only."""
 
     def __init__(
         self,
@@ -160,7 +160,7 @@ class MemorySlice:
             memory: The underlying Memory instance.
             scopes: List of scope paths to include.
             categories: Optional category filter for recall.
-            read_only: If True, remember() raises PermissionError.
+            read_only: If True, remember() is a silent no-op.
         """
         self._memory = memory
         self._scopes = [s.rstrip("/") or "/" for s in scopes]
@@ -176,10 +176,10 @@ class MemorySlice:
         importance: float | None = None,
         source: str | None = None,
         private: bool = False,
-    ) -> MemoryRecord:
-        """Remember into an explicit scope. Required when read_only=False."""
+    ) -> MemoryRecord | None:
+        """Remember into an explicit scope. No-op when read_only=True."""
         if self._read_only:
-            raise PermissionError("This MemorySlice is read-only")
+            return None
         return self._memory.remember(
             content,
             scope=scope,
diff --git a/lib/crewai/src/crewai/memory/storage/lancedb_storage.py b/lib/crewai/src/crewai/memory/storage/lancedb_storage.py
index d40999985..e514edcac 100644
--- a/lib/crewai/src/crewai/memory/storage/lancedb_storage.py
+++ b/lib/crewai/src/crewai/memory/storage/lancedb_storage.py
@@ -53,6 +53,7 @@ class LanceDBStorage:
         path: str | Path | None = None,
         table_name: str = "memories",
         vector_dim: int | None = None,
+        compact_every: int = 100,
     ) -> None:
         """Initialize LanceDB storage.
 
@@ -64,6 +65,10 @@ class LanceDBStorage:
             vector_dim: Dimensionality of the embedding vector. When ``None``
                   (default), the dimension is auto-detected from the existing
                   table schema or from the first saved embedding.
+            compact_every: Number of ``save()`` calls between automatic
+                  background compactions.  Each ``save()`` creates one new
+                  fragment file; compaction merges them, keeping query
+                  performance consistent.  Set to 0 to disable.
         """
         if path is None:
             storage_dir = os.environ.get("CREWAI_STORAGE_DIR")
@@ -78,6 +83,22 @@ class LanceDBStorage:
         self._table_name = table_name
         self._db = lancedb.connect(str(self._path))
 
+        # On macOS and Linux the default per-process open-file limit is 256.
+        # A LanceDB table stores one file per fragment (one fragment per save()
+        # call by default).  With hundreds of fragments, a single full-table
+        # scan opens all of them simultaneously, exhausting the limit.
+        # Raise it proactively so scans on large tables never hit OS error 24.
+        try:
+            import resource
+            soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
+            if soft < 4096:
+                resource.setrlimit(resource.RLIMIT_NOFILE, (min(hard, 4096), hard))
+        except Exception:  # noqa: S110
+            pass  # Windows or already at the max hard limit — safe to ignore
+
+        self._compact_every = compact_every
+        self._save_count = 0
+
         # Get or create a shared write lock for this database path.
         resolved = str(self._path.resolve())
         with LanceDBStorage._path_locks_guard:
@@ -91,6 +112,11 @@ class LanceDBStorage:
         try:
             self._table: lancedb.table.Table | None = self._db.open_table(self._table_name)
             self._vector_dim: int = self._infer_dim_from_table(self._table)
+            # Best-effort: create the scope index if it doesn't exist yet.
+            self._ensure_scope_index()
+            # Compact in the background if the table has accumulated many
+            # fragments from previous runs (each save() creates one).
+            self._compact_if_needed()
         except Exception:
             self._table = None
             self._vector_dim = vector_dim or 0  # 0 = not yet known
@@ -178,6 +204,56 @@ class LanceDBStorage:
         table.delete("id = '__schema_placeholder__'")
         return table
 
+    def _ensure_scope_index(self) -> None:
+        """Create a BTREE scalar index on the ``scope`` column if not present.
+
+        A scalar index lets LanceDB skip a full table scan when filtering by
+        scope prefix, which is the hot path for ``list_records``,
+        ``get_scope_info``, and ``list_scopes``.  The call is best-effort:
+        if the table is empty or the index already exists the exception is
+        swallowed silently.
+        """
+        if self._table is None:
+            return
+        try:
+            self._table.create_scalar_index("scope", index_type="BTREE", replace=False)
+        except Exception:  # noqa: S110
+            pass  # index already exists, table empty, or unsupported version
+
+    # ------------------------------------------------------------------
+    # Automatic background compaction
+    # ------------------------------------------------------------------
+
+    def _compact_if_needed(self) -> None:
+        """Spawn a background compaction on startup.
+
+        Called whenever an existing table is opened so that fragments
+        accumulated in previous sessions are silently merged before the
+        first query.  ``optimize()`` returns quickly when the table is
+        already compact, so the cost is negligible in the common case.
+        """
+        if self._table is None or self._compact_every <= 0:
+            return
+        self._compact_async()
+
+    def _compact_async(self) -> None:
+        """Fire-and-forget: compact the table in a daemon background thread."""
+        threading.Thread(
+            target=self._compact_safe,
+            daemon=True,
+            name="lancedb-compact",
+        ).start()
+
+    def _compact_safe(self) -> None:
+        """Run ``table.optimize()`` in a background thread, absorbing errors."""
+        try:
+            if self._table is not None:
+                self._table.optimize()
+                # Refresh the scope index so new fragments are covered.
+                self._ensure_scope_index()
+        except Exception:
+            _logger.debug("LanceDB background compaction failed", exc_info=True)
+
     def _ensure_table(self, vector_dim: int | None = None) -> lancedb.table.Table:
         """Return the table, creating it lazily if needed.
 
@@ -239,6 +315,7 @@ class LanceDBStorage:
             if r.embedding and len(r.embedding) > 0:
                 dim = len(r.embedding)
                 break
+        is_new_table = self._table is None
         with self._write_lock:
             self._ensure_table(vector_dim=dim)
             rows = [self._record_to_row(r) for r in records]
@@ -246,6 +323,13 @@ class LanceDBStorage:
                 if r["vector"] is None or len(r["vector"]) != self._vector_dim:
                     r["vector"] = [0.0] * self._vector_dim
             self._retry_write("add", rows)
+        # Create the scope index on the first save so it covers the initial dataset.
+        if is_new_table:
+            self._ensure_scope_index()
+        # Auto-compact every N saves so fragment files don't pile up.
+        self._save_count += 1
+        if self._compact_every > 0 and self._save_count % self._compact_every == 0:
+            self._compact_async()
 
     def update(self, record: MemoryRecord) -> None:
         """Update a record by ID. Preserves created_at, updates last_accessed."""
@@ -261,6 +345,10 @@ class LanceDBStorage:
     def touch_records(self, record_ids: list[str]) -> None:
         """Update last_accessed to now for the given record IDs.
 
+        Uses a single batch ``table.update()`` call instead of N
+        delete-and-re-add cycles, which is both faster and avoids
+        unnecessary write amplification.
+
         Args:
             record_ids: IDs of records to touch.
         """
@@ -268,25 +356,20 @@ class LanceDBStorage:
             return
         with self._write_lock:
             now = datetime.utcnow().isoformat()
-            for rid in record_ids:
-                safe_id = str(rid).replace("'", "''")
-                rows = (
-                    self._table.search([0.0] * self._vector_dim)
-                    .where(f"id = '{safe_id}'")
-                    .limit(1)
-                    .to_list()
-                )
-                if rows:
-                    rows[0]["last_accessed"] = now
-                    self._retry_write("delete", f"id = '{safe_id}'")
-                    self._retry_write("add", [rows[0]])
+            safe_ids = [str(rid).replace("'", "''") for rid in record_ids]
+            ids_expr = ", ".join(f"'{rid}'" for rid in safe_ids)
+            self._retry_write(
+                "update",
+                where=f"id IN ({ids_expr})",
+                values={"last_accessed": now},
+            )
 
     def get_record(self, record_id: str) -> MemoryRecord | None:
         """Return a single record by ID, or None if not found."""
         if self._table is None:
             return None
         safe_id = str(record_id).replace("'", "''")
-        rows = self._table.search([0.0] * self._vector_dim).where(f"id = '{safe_id}'").limit(1).to_list()
+        rows = self._table.search().where(f"id = '{safe_id}'").limit(1).to_list()
         if not rows:
             return None
         return self._row_to_record(rows[0])
@@ -374,13 +457,31 @@ class LanceDBStorage:
             self._retry_write("delete", where_expr)
             return before - self._table.count_rows()
 
-    def _scan_rows(self, scope_prefix: str | None = None, limit: int = _SCAN_ROWS_LIMIT) -> list[dict[str, Any]]:
-        """Scan rows optionally filtered by scope prefix."""
+    def _scan_rows(
+        self,
+        scope_prefix: str | None = None,
+        limit: int = _SCAN_ROWS_LIMIT,
+        columns: list[str] | None = None,
+    ) -> list[dict[str, Any]]:
+        """Scan rows optionally filtered by scope prefix.
+
+        Uses a full table scan (no vector query) so the limit is applied after
+        the scope filter, not to ANN candidates before filtering.
+
+        Args:
+            scope_prefix: Optional scope path prefix to filter by.
+            limit: Maximum number of rows to return (applied after filtering).
+            columns: Optional list of column names to fetch.  Pass only the
+                columns you need for metadata operations to avoid reading the
+                heavy ``vector`` column unnecessarily.
+        """
         if self._table is None:
             return []
-        q = self._table.search([0.0] * self._vector_dim)
+        q = self._table.search()
         if scope_prefix is not None and scope_prefix.strip("/"):
             q = q.where(f"scope LIKE '{scope_prefix.rstrip('/')}%'")
+        if columns is not None:
+            q = q.select(columns)
         return q.limit(limit).to_list()
 
     def list_records(
@@ -406,7 +507,10 @@ class LanceDBStorage:
         prefix = scope if scope != "/" else ""
         if prefix and not prefix.startswith("/"):
             prefix = "/" + prefix
-        rows = self._scan_rows(prefix or None)
+        rows = self._scan_rows(
+            prefix or None,
+            columns=["scope", "categories_str", "created_at"],
+        )
         if not rows:
             return ScopeInfo(
                 path=scope or "/",
@@ -453,7 +557,7 @@ class LanceDBStorage:
     def list_scopes(self, parent: str = "/") -> list[str]:
         parent = parent.rstrip("/") or ""
         prefix = (parent + "/") if parent else "/"
-        rows = self._scan_rows(prefix if prefix != "/" else None)
+        rows = self._scan_rows(prefix if prefix != "/" else None, columns=["scope"])
         children: set[str] = set()
         for row in rows:
             sc = str(row.get("scope", ""))
@@ -465,7 +569,7 @@ class LanceDBStorage:
         return sorted(children)
 
     def list_categories(self, scope_prefix: str | None = None) -> dict[str, int]:
-        rows = self._scan_rows(scope_prefix)
+        rows = self._scan_rows(scope_prefix, columns=["categories_str"])
         counts: dict[str, int] = {}
         for row in rows:
             cat_str = row.get("categories_str") or "[]"
@@ -498,6 +602,21 @@ class LanceDBStorage:
         if prefix:
             self._table.delete(f"scope >= '{prefix}' AND scope < '{prefix}/\uFFFF'")
 
+    def optimize(self) -> None:
+        """Compact the table synchronously and refresh the scope index.
+
+        Under normal usage this is called automatically in the background
+        (every ``compact_every`` saves and on startup when the table is
+        fragmented).  Call this explicitly only when you need the compaction
+        to be complete before the next operation — for example immediately
+        after a large bulk import, before a latency-sensitive recall.
+        It is a no-op if the table does not exist.
+        """
+        if self._table is None:
+            return
+        self._table.optimize()
+        self._ensure_scope_index()
+
     async def asave(self, records: list[MemoryRecord]) -> None:
         self.save(records)
 
diff --git a/lib/crewai/src/crewai/memory/types.py b/lib/crewai/src/crewai/memory/types.py
index e67ad163f..929e10092 100644
--- a/lib/crewai/src/crewai/memory/types.py
+++ b/lib/crewai/src/crewai/memory/types.py
@@ -87,6 +87,22 @@ class MemoryMatch(BaseModel):
         description="Information the system looked for but could not find.",
     )
 
+    def format(self) -> str:
+        """Format this match as a human-readable string including metadata.
+
+        Returns:
+            A multi-line string with score, content, categories, and non-empty
+            metadata fields.
+        """
+        lines = [f"- (score={self.score:.2f}) {self.record.content}"]
+        if self.record.categories:
+            lines.append(f"  categories: {', '.join(self.record.categories)}")
+        if self.record.metadata:
+            for key, value in self.record.metadata.items():
+                if value is not None:
+                    lines.append(f"  {key}: {value}")
+        return "\n".join(lines)
+
 
 class ScopeInfo(BaseModel):
     """Information about a scope in the memory hierarchy."""
@@ -291,7 +307,7 @@ def embed_text(embedder: Any, text: str) -> list[float]:
         return []
     first = result[0]
     if hasattr(first, "tolist"):
-        return first.tolist()
+        return list(first.tolist())
     if isinstance(first, list):
         return [float(x) for x in first]
     return list(first)
diff --git a/lib/crewai/src/crewai/memory/unified_memory.py b/lib/crewai/src/crewai/memory/unified_memory.py
index a15f77afd..531a91208 100644
--- a/lib/crewai/src/crewai/memory/unified_memory.py
+++ b/lib/crewai/src/crewai/memory/unified_memory.py
@@ -88,6 +88,10 @@ class Memory:
         # Queries shorter than this skip LLM analysis (saving ~1-3s).
         # Longer queries (full task descriptions) benefit from LLM distillation.
         query_analysis_threshold: int = 200,
+        # When True, all write operations (remember, remember_many) are silently
+        # skipped. Useful for sharing a read-only view of memory across agents
+        # without any of them persisting new memories.
+        read_only: bool = False,
     ) -> None:
         """Initialize Memory.
 
@@ -107,7 +111,9 @@ class Memory:
             complex_query_threshold: For complex queries, explore deeper below this confidence.
             exploration_budget: Number of LLM-driven exploration rounds during deep recall.
             query_analysis_threshold: Queries shorter than this skip LLM analysis during deep recall.
+            read_only: If True, remember() and remember_many() are silent no-ops.
         """
+        self._read_only = read_only
         self._config = MemoryConfig(
             recency_weight=recency_weight,
             semantic_weight=semantic_weight,
@@ -130,10 +136,13 @@ class Memory:
         self._llm_instance: BaseLLM | None = None if isinstance(llm, str) else llm
         self._embedder_config: Any = embedder
         self._embedder_instance: Any = (
-            embedder if (embedder is not None and not isinstance(embedder, dict)) else None
+            embedder
+            if (embedder is not None and not isinstance(embedder, dict))
+            else None
         )
 
         # Storage is initialized eagerly (local, no API key needed).
+        self._storage: StorageBackend
         if storage == "lancedb":
             self._storage = LanceDBStorage()
         elif isinstance(storage, str):
@@ -160,12 +169,17 @@ class Memory:
             from crewai.llm import LLM
 
             try:
-                self._llm_instance = LLM(model=self._llm_config)
+                model_name = (
+                    self._llm_config
+                    if isinstance(self._llm_config, str)
+                    else str(self._llm_config)
+                )
+                self._llm_instance = LLM(model=model_name)
             except Exception as e:
                 raise RuntimeError(
                     f"Memory requires an LLM for analysis but initialization failed: {e}\n\n"
                     "To fix this, do one of the following:\n"
-                    '  - Set OPENAI_API_KEY for the default model (gpt-4o-mini)\n'
+                    "  - Set OPENAI_API_KEY for the default model (gpt-4o-mini)\n"
                     '  - Pass a different model: Memory(llm="anthropic/claude-3-haiku-20240307")\n'
                     '  - Pass any LLM instance: Memory(llm=LLM(model="your-model"))\n'
                     "  - To skip LLM analysis, pass all fields explicitly to remember()\n"
@@ -182,7 +196,7 @@ class Memory:
                 if isinstance(self._embedder_config, dict):
                     from crewai.rag.embeddings.factory import build_embedder
 
-                    self._embedder_instance = build_embedder(self._embedder_config)
+                    self._embedder_instance = build_embedder(self._embedder_config)  # type: ignore[call-overload]
                 else:
                     self._embedder_instance = _default_embedder()
             except Exception as e:
@@ -317,7 +331,7 @@ class Memory:
         source: str | None = None,
         private: bool = False,
         agent_role: str | None = None,
-    ) -> MemoryRecord:
+    ) -> MemoryRecord | None:
         """Store a single item in memory (synchronous).
 
         Routes through the same serialized save pool as ``remember_many``
@@ -335,11 +349,13 @@ class Memory:
             agent_role: Optional agent role for event metadata.
 
         Returns:
-            The created MemoryRecord.
+            The created MemoryRecord, or None if this memory is read-only.
 
         Raises:
             Exception: On save failure (events emitted).
         """
+        if self._read_only:
+            return None
         _source_type = "unified_memory"
         try:
             crewai_event_bus.emit(
@@ -356,7 +372,13 @@ class Memory:
             # then immediately wait for the result.
             future = self._submit_save(
                 self._encode_batch,
-                [content], scope, categories, metadata, importance, source, private,
+                [content],
+                scope,
+                categories,
+                metadata,
+                importance,
+                source,
+                private,
             )
             records = future.result()
             record = records[0] if records else None
@@ -420,13 +442,19 @@ class Memory:
         Returns:
             Empty list (records are not available until the background save completes).
         """
-        if not contents:
+        if not contents or self._read_only:
             return []
 
         self._submit_save(
             self._background_encode_batch,
-            contents, scope, categories, metadata,
-            importance, source, private, agent_role,
+            contents,
+            scope,
+            categories,
+            metadata,
+            importance,
+            source,
+            private,
+            agent_role,
         )
         return []
 
@@ -566,14 +594,13 @@ class Memory:
                     # Privacy filter
                     if not include_private:
                         raw = [
-                            (r, s) for r, s in raw
+                            (r, s)
+                            for r, s in raw
                             if not r.private or r.source == source
                         ]
                     results = []
                     for r, s in raw:
-                        composite, reasons = compute_composite_score(
-                            r, s, self._config
-                        )
+                        composite, reasons = compute_composite_score(r, s, self._config)
                         results.append(
                             MemoryMatch(
                                 record=r,
@@ -739,7 +766,9 @@ class Memory:
             limit: Maximum number of records to return.
             offset: Number of records to skip (for pagination).
         """
-        return self._storage.list_records(scope_prefix=scope, limit=limit, offset=offset)
+        return self._storage.list_records(
+            scope_prefix=scope, limit=limit, offset=offset
+        )
 
     def info(self, path: str = "/") -> ScopeInfo:
         """Return scope info for path."""
@@ -781,7 +810,7 @@ class Memory:
         importance: float | None = None,
         source: str | None = None,
         private: bool = False,
-    ) -> MemoryRecord:
+    ) -> MemoryRecord | None:
         """Async remember: delegates to sync for now."""
         return self.remember(
             content,
diff --git a/lib/crewai/src/crewai/tools/memory_tools.py b/lib/crewai/src/crewai/tools/memory_tools.py
index 5c98a9892..f088fef73 100644
--- a/lib/crewai/src/crewai/tools/memory_tools.py
+++ b/lib/crewai/src/crewai/tools/memory_tools.py
@@ -20,14 +20,6 @@ class RecallMemorySchema(BaseModel):
             "or multiple items to search for several things at once."
         ),
     )
-    scope: str | None = Field(
-        default=None,
-        description="Optional scope to narrow the search (e.g. /project/alpha)",
-    )
-    depth: str = Field(
-        default="shallow",
-        description="'shallow' for fast vector search, 'deep' for LLM-analyzed retrieval",
-    )
 
 
 class RecallMemoryTool(BaseTool):
@@ -41,32 +33,27 @@ class RecallMemoryTool(BaseTool):
     def _run(
         self,
         queries: list[str] | str,
-        scope: str | None = None,
-        depth: str = "shallow",
         **kwargs: Any,
     ) -> str:
         """Search memory for relevant information.
 
         Args:
             queries: One or more search queries (string or list of strings).
-            scope: Optional scope prefix to narrow the search.
-            depth: "shallow" for fast vector search, "deep" for LLM-analyzed retrieval.
 
         Returns:
             Formatted string of matching memories, or a message if none found.
         """
         if isinstance(queries, str):
             queries = [queries]
-        actual_depth = depth if depth in ("shallow", "deep") else "shallow"
 
         all_lines: list[str] = []
         seen_ids: set[str] = set()
         for query in queries:
-            matches = self.memory.recall(query, scope=scope, limit=5, depth=actual_depth)
+            matches = self.memory.recall(query)
             for m in matches:
                 if m.record.id not in seen_ids:
                     seen_ids.add(m.record.id)
-                    all_lines.append(f"- (score={m.score:.2f}) {m.record.content}")
+                    all_lines.append(m.format())
 
         if not all_lines:
             return "No relevant memories found."
@@ -117,20 +104,28 @@ class RememberTool(BaseTool):
 def create_memory_tools(memory: Any) -> list[BaseTool]:
     """Create Recall and Remember tools for the given memory instance.
 
+    When memory is read-only (``_read_only=True``), only the RecallMemoryTool
+    is returned — the RememberTool is omitted so agents are never offered a
+    save capability they cannot use.
+
     Args:
         memory: A Memory, MemoryScope, or MemorySlice instance.
 
     Returns:
-        List containing a RecallMemoryTool and a RememberTool.
+        List containing a RecallMemoryTool and, if not read-only, a RememberTool.
     """
     i18n = get_i18n()
-    return [
+    tools: list[BaseTool] = [
         RecallMemoryTool(
             memory=memory,
             description=i18n.tools("recall_memory"),
         ),
-        RememberTool(
-            memory=memory,
-            description=i18n.tools("save_to_memory"),
-        ),
     ]
+    if not getattr(memory, "_read_only", False):
+        tools.append(
+            RememberTool(
+                memory=memory,
+                description=i18n.tools("save_to_memory"),
+            )
+        )
+    return tools
diff --git a/lib/crewai/tests/agents/test_lite_agent.py b/lib/crewai/tests/agents/test_lite_agent.py
index 761a12b23..c99b5c534 100644
--- a/lib/crewai/tests/agents/test_lite_agent.py
+++ b/lib/crewai/tests/agents/test_lite_agent.py
@@ -1136,6 +1136,7 @@ def test_lite_agent_memory_instance_recall_and_save_called():
         successful_requests=1,
     )
     mock_memory = Mock()
+    mock_memory._read_only = False
     mock_memory.recall.return_value = []
     mock_memory.extract_memories.return_value = ["Fact one.", "Fact two."]
 
diff --git a/lib/crewai/tests/memory/test_unified_memory.py b/lib/crewai/tests/memory/test_unified_memory.py
index 5b25b8077..26e2a1929 100644
--- a/lib/crewai/tests/memory/test_unified_memory.py
+++ b/lib/crewai/tests/memory/test_unified_memory.py
@@ -218,14 +218,15 @@ def test_memory_slice_recall(tmp_path: Path, mock_embedder: MagicMock) -> None:
     assert isinstance(matches, list)
 
 
-def test_memory_slice_remember_raises_when_read_only(tmp_path: Path, mock_embedder: MagicMock) -> None:
+def test_memory_slice_remember_is_noop_when_read_only(tmp_path: Path, mock_embedder: MagicMock) -> None:
     from crewai.memory.unified_memory import Memory
     from crewai.memory.memory_scope import MemorySlice
 
     mem = Memory(storage=str(tmp_path / "db7"), llm=MagicMock(), embedder=mock_embedder)
     sl = MemorySlice(mem, ["/a"], read_only=True)
-    with pytest.raises(PermissionError):
-        sl.remember("x", scope="/a")
+    result = sl.remember("x", scope="/a")
+    assert result is None
+    assert mem.list_records() == []
 
 
 # --- Flow memory ---
@@ -318,6 +319,7 @@ def test_executor_save_to_memory_calls_extract_then_remember_per_item() -> None:
     from crewai.agents.parser import AgentFinish
 
     mock_memory = MagicMock()
+    mock_memory._read_only = False
     mock_memory.extract_memories.return_value = ["Fact A.", "Fact B."]
 
     mock_agent = MagicMock()
@@ -358,6 +360,7 @@ def test_executor_save_to_memory_skips_delegation_output() -> None:
     from crewai.utilities.string_utils import sanitize_tool_name
 
     mock_memory = MagicMock()
+    mock_memory._read_only = False
     mock_agent = MagicMock()
     mock_agent.memory = mock_memory
     mock_agent._logger = MagicMock()
diff --git a/uv.lock b/uv.lock
index ea4af006f..dba6ab30c 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1204,7 +1204,7 @@ requires-dist = [
     { name = "json-repair", specifier = "~=0.25.2" },
     { name = "json5", specifier = "~=0.10.0" },
     { name = "jsonref", specifier = "~=1.1.0" },
-    { name = "lancedb", specifier = ">=0.4.0" },
+    { name = "lancedb", specifier = ">=0.29.2" },
     { name = "litellm", marker = "extra == 'litellm'", specifier = ">=1.74.9,<3" },
     { name = "mcp", specifier = "~=1.26.0" },
     { name = "mem0ai", marker = "extra == 'mem0'", specifier = "~=0.1.94" },
@@ -1286,7 +1286,6 @@ dependencies = [
     { name = "beautifulsoup4" },
     { name = "crewai" },
     { name = "docker" },
-    { name = "lancedb" },
     { name = "pymupdf" },
     { name = "python-docx" },
     { name = "pytube" },
@@ -1428,7 +1427,6 @@ requires-dist = [
     { name = "firecrawl-py", marker = "extra == 'firecrawl-py'", specifier = ">=1.8.0" },
     { name = "gitpython", marker = "extra == 'github'", specifier = "==3.1.38" },
     { name = "hyperbrowser", marker = "extra == 'hyperbrowser'", specifier = ">=0.18.0" },
-    { name = "lancedb", specifier = "~=0.5.4" },
     { name = "langchain-apify", marker = "extra == 'apify'", specifier = ">=0.1.2,<1.0.0" },
     { name = "linkup-sdk", marker = "extra == 'linkup-sdk'", specifier = ">=0.2.2" },
     { name = "lxml", marker = "extra == 'rag'", specifier = ">=5.3.0,<5.4.0" },
@@ -3226,27 +3224,54 @@ wheels = [
 ]
 
 [[package]]
-name = "lancedb"
-version = "0.5.7"
+name = "lance-namespace"
+version = "0.5.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "lance-namespace-urllib3-client" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/2b/c6/aec0d7752e15536564b50cf9a8926f0e5d7780aa3ab8ce8bca46daa55659/lance_namespace-0.5.2.tar.gz", hash = "sha256:566cc33091b5631793ab411f095d46c66391db0a62343cd6b4470265bb04d577", size = 10274, upload-time = "2026-02-20T03:14:31.777Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d6/3d/737c008d8fb2861e7ce260e2ffab0d5058eae41556181f80f1a1c3b52ef5/lance_namespace-0.5.2-py3-none-any.whl", hash = "sha256:6ccaf5649bf6ee6aa92eed9c535a114b7b4eb08e89f40426f58bc1466cbcffa3", size = 12087, upload-time = "2026-02-20T03:14:35.261Z" },
+]
+
+[[package]]
+name = "lance-namespace-urllib3-client"
+version = "0.5.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "attrs" },
-    { name = "cachetools" },
-    { name = "click" },
-    { name = "deprecation" },
-    { name = "overrides" },
     { name = "pydantic" },
-    { name = "pylance" },
-    { name = "pyyaml" },
-    { name = "ratelimiter" },
-    { name = "requests" },
-    { name = "retry" },
-    { name = "semver" },
+    { name = "python-dateutil" },
+    { name = "typing-extensions" },
+    { name = "urllib3", version = "1.26.20", source = { registry = "https://pypi.org/simple" }, marker = "platform_python_implementation == 'PyPy'" },
+    { name = "urllib3", version = "2.6.3", source = { registry = "https://pypi.org/simple" }, marker = "platform_python_implementation != 'PyPy'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e9/64/51622c93ec8c164483c83b68764e5e76e52286c0137a8247bc6a7fac25f4/lance_namespace_urllib3_client-0.5.2.tar.gz", hash = "sha256:8a3a238006e6eabc01fc9d385ac3de22ba933aef0ae8987558f3c3199c9b3799", size = 172578, upload-time = "2026-02-20T03:14:33.031Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/10/f86d994498b37f7f35d0b8c2f7626a16fe4cb1949b518c1e5d5052ecf95f/lance_namespace_urllib3_client-0.5.2-py3-none-any.whl", hash = "sha256:83cefb6fd6e5df0b99b5e866ee3d46300d375b75e8af32c27bc16fbf7c1a5978", size = 300351, upload-time = "2026-02-20T03:14:34.236Z" },
+]
+
+[[package]]
+name = "lancedb"
+version = "0.29.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "deprecation" },
+    { name = "lance-namespace" },
+    { name = "numpy" },
+    { name = "overrides", marker = "python_full_version < '3.12'" },
+    { name = "packaging" },
+    { name = "pyarrow" },
+    { name = "pydantic" },
     { name = "tqdm" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/14/1b/f87a2b6420f6f55ea64e5f8f18f231450cc602a0854739bcf946cebc080a/lancedb-0.5.7.tar.gz", hash = "sha256:878914b493f91d09a77b14f1528104741f273234cbdd6671be705f447701fd51", size = 102890, upload-time = "2024-02-22T20:11:29.988Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/01/21/ecb191feff512640a59e17fe1737bd9c33970bc857c59a77fa61d5e314d9/lancedb-0.5.7-py3-none-any.whl", hash = "sha256:6169966f715ef530be545950e1aaf9f3f160967e4ba7456cd67c9f30f678095d", size = 115104, upload-time = "2024-02-22T20:11:25.726Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/77/fbb25946a234928958e016c5448343fd314bd601315f9587568321591a17/lancedb-0.29.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:bc1faf2e12addb9585569d0fb114ecc25ec3867e4e1aa6934e9343cfb5265ee4", size = 42341708, upload-time = "2026-02-09T06:21:31.677Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/95/d3a7b6d0237e343ad5b2afef2bdb99423746d5c3e882a9cab68dc041c2d0/lancedb-0.29.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fec19cfc52a5b9d98e060bd2f02a1c9df6a0bfd15b36021b6017327a41893a3", size = 44147347, upload-time = "2026-02-09T06:31:02.567Z" },
+    { url = "https://files.pythonhosted.org/packages/66/21/153a42294279c5b66d763f357808dde0899b71c5c8e41ad5ecbeeb8728df/lancedb-0.29.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:636939ab9225d435020ba17c231f5eaba15312a07813bcebcd71128204cc039f", size = 47186355, upload-time = "2026-02-09T06:34:47.726Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/f7/f7041ae7d7730332b2754fe7adc2e0bd496f92bf526ac710b7eb3caf1d0a/lancedb-0.29.2-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:f79b32083fcab139009db521d2f7fcd6afe4cca98a78c06c5940ff00a170cc1a", size = 44172354, upload-time = "2026-02-09T06:31:03.834Z" },
+    { url = "https://files.pythonhosted.org/packages/72/6f/c152497c18cea0f36b523fc03b8e0a48be2b120276cc15a86d79b8b83cde/lancedb-0.29.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:991043a28c1f49f14df2479b554a95c759a85666dc58573cc86c1b9df05db794", size = 47228009, upload-time = "2026-02-09T06:34:40.872Z" },
+    { url = "https://files.pythonhosted.org/packages/66/50/bd47bca59a87a88a4ca291a0718291422440750d84b34318048c70a537c2/lancedb-0.29.2-cp39-abi3-win_amd64.whl", hash = "sha256:101eb0ac018bb0b643dd9ea22065f6f2102e9d44c9ac58a197477ccbfbc0b9fa", size = 52028768, upload-time = "2026-02-09T07:00:02.272Z" },
 ]
 
 [[package]]
@@ -5414,15 +5439,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/80/2d/1bb683f64737bbb1f86c82b7359db1eb2be4e2c0c13b947f80efefa7d3e5/psycopg2_binary-2.9.11-cp313-cp313-win_amd64.whl", hash = "sha256:efff12b432179443f54e230fdf60de1f6cc726b6c832db8701227d089310e8aa", size = 2714215, upload-time = "2025-10-10T11:13:07.14Z" },
 ]
 
-[[package]]
-name = "py"
-version = "1.11.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/98/ff/fec109ceb715d2a6b4c4a85a61af3b40c723a961e8828319fbcb15b868dc/py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719", size = 207796, upload-time = "2021-11-04T17:17:01.377Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f6/f0/10642828a8dfb741e5f3fbaac830550a518a775c7fff6f04a007259b0548/py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378", size = 98708, upload-time = "2021-11-04T17:17:00.152Z" },
-]
-
 [[package]]
 name = "py-rust-stemmers"
 version = "0.1.5"
@@ -5916,22 +5932,6 @@ crypto = [
     { name = "cryptography" },
 ]
 
-[[package]]
-name = "pylance"
-version = "0.9.18"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-    { name = "pyarrow" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/ca/b8/15d4d380f0858dde46d42891776017e3bf9eb40129b3fe222637eecf8f43/pylance-0.9.18-cp38-abi3-macosx_10_15_x86_64.whl", hash = "sha256:fe2445d922c594d90e89111385106f6b152caab27996217db7bb4b8947eb0bea", size = 20319043, upload-time = "2024-02-19T07:36:11.206Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/f8/69f927a215d415362300d14a50b3cbc6575fd640ca5e632d488e022d3af1/pylance-0.9.18-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:a2c424c50f5186edbbcc5a26f34063ed09d9a7390e28033395728ce02b5658f0", size = 18780426, upload-time = "2024-02-19T07:30:10.963Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/b8/991e4544cfa21de2c7de5dd6bd8410df454fec5b374680fa96cd8698763b/pylance-0.9.18-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10af06edfde3e8451bf2251381d3980a0a164eab9d4c3d4dc8b6318969e958a6", size = 21584420, upload-time = "2024-02-19T07:32:30.283Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/5e/ff80f31d995315790393cbe599565f55d03eb717654cfeb65b701803e887/pylance-0.9.18-cp38-abi3-manylinux_2_24_aarch64.whl", hash = "sha256:d8bb9045d7163cc966b9fe34a917044192be37a90915475b77461e5b7d89e442", size = 19960982, upload-time = "2024-02-19T07:32:49.686Z" },
-    { url = "https://files.pythonhosted.org/packages/2d/e5/c0e0a6cad08ab86a9c0bce7e8caef8f666337bb7950e2ab151ea4f88242d/pylance-0.9.18-cp38-abi3-win_amd64.whl", hash = "sha256:5ea80b7bf70d992f3fe63bce2d2f064f742124c04eaedeb76baca408ded85a2c", size = 22089079, upload-time = "2024-02-19T07:42:43.262Z" },
-]
-
 [[package]]
 name = "pylatexenc"
 version = "2.10"
@@ -6629,15 +6629,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e0/fd/0d025466f0f84552634f2a94c018df34568fe55cc97184a6bb2c719c5b3a/rapidocr-3.6.0-py3-none-any.whl", hash = "sha256:d16b43872fc4dfa1e60996334dcd0dc3e3f1f64161e2332bc1873b9f65754e6b", size = 15067340, upload-time = "2026-01-28T14:45:04.271Z" },
 ]
 
-[[package]]
-name = "ratelimiter"
-version = "1.2.0.post0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/5b/e0/b36010bddcf91444ff51179c076e4a09c513674a56758d7cfea4f6520e29/ratelimiter-1.2.0.post0.tar.gz", hash = "sha256:5c395dcabdbbde2e5178ef3f89b568a3066454a6ddc223b76473dac22f89b4f7", size = 9182, upload-time = "2017-12-12T00:33:38.783Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/51/80/2164fa1e863ad52cc8d870855fba0fbb51edd943edffd516d54b5f6f8ff8/ratelimiter-1.2.0.post0-py3-none-any.whl", hash = "sha256:a52be07bc0bb0b3674b4b304550f10c769bbb00fead3072e035904474259809f", size = 6642, upload-time = "2017-12-12T00:33:37.505Z" },
-]
-
 [[package]]
 name = "redis"
 version = "7.1.0"
@@ -6794,19 +6785,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3f/51/d4db610ef29373b879047326cbf6fa98b6c1969d6f6dc423279de2b1be2c/requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06", size = 54481, upload-time = "2023-05-01T04:11:28.427Z" },
 ]
 
-[[package]]
-name = "retry"
-version = "0.9.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "decorator" },
-    { name = "py" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/9d/72/75d0b85443fbc8d9f38d08d2b1b67cc184ce35280e4a3813cda2f445f3a4/retry-0.9.2.tar.gz", hash = "sha256:f8bfa8b99b69c4506d6f5bd3b0aabf77f98cdb17f3c9fc3f5ca820033336fba4", size = 6448, upload-time = "2016-05-11T13:58:51.541Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/4b/0d/53aea75710af4528a25ed6837d71d117602b01946b307a3912cb3cfcbcba/retry-0.9.2-py2.py3-none-any.whl", hash = "sha256:ccddf89761fa2c726ab29391837d4327f819ea14d244c232a1d24c67a2f98606", size = 7986, upload-time = "2016-05-11T13:58:39.925Z" },
-]
-
 [[package]]
 name = "rich"
 version = "14.3.2"