diff --git a/llama_stack/templates/hf-serverless/hf_serverless.py b/llama_stack/templates/hf-serverless/hf_serverless.py
index 51e16c3db..788faa986 100644
--- a/llama_stack/templates/hf-serverless/hf_serverless.py
+++ b/llama_stack/templates/hf-serverless/hf_serverless.py
@@ -100,6 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
diff --git a/llama_stack/templates/hf-serverless/run.yaml b/llama_stack/templates/hf-serverless/run.yaml
index f91e45fb6..f04213533 100644
--- a/llama_stack/templates/hf-serverless/run.yaml
+++ b/llama_stack/templates/hf-serverless/run.yaml
@@ -104,4 +104,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/meta-reference-gpu/meta_reference.py b/llama_stack/templates/meta-reference-gpu/meta_reference.py
index 1477b31ff..7364ee422 100644
--- a/llama_stack/templates/meta-reference-gpu/meta_reference.py
+++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py
@@ -105,6 +105,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
diff --git a/llama_stack/templates/meta-reference-gpu/run.yaml b/llama_stack/templates/meta-reference-gpu/run.yaml
index cc22a514b..ecde69fdf 100644
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@@ -105,4 +105,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/nvidia/nvidia.py b/llama_stack/templates/nvidia/nvidia.py
index 9daf9c50c..cfa86dbe7 100644
--- a/llama_stack/templates/nvidia/nvidia.py
+++ b/llama_stack/templates/nvidia/nvidia.py
@@ -8,10 +8,9 @@ from pathlib import Path
 
 from llama_models.sku_list import all_registered_models
 
-from llama_stack.distribution.datatypes import ModelInput, Provider
+from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.nvidia import _MODEL_ALIASES
-
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
 
@@ -50,6 +49,20 @@ def get_distribution_template() -> DistributionTemplate:
         )
         for m in _MODEL_ALIASES
     ]
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::memory",
+            provider_id="memory-runtime",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::code_interpreter",
+            provider_id="code-interpreter",
+        ),
+    ]
 
     return DistributionTemplate(
         name="nvidia",
@@ -65,6 +78,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "inference": [inference_provider],
                 },
                 default_models=default_models,
+                default_tool_groups=default_tool_groups,
             ),
         },
         run_config_env_vars={
diff --git a/llama_stack/templates/nvidia/run.yaml b/llama_stack/templates/nvidia/run.yaml
index 1887a55d0..578f70c9d 100644
--- a/llama_stack/templates/nvidia/run.yaml
+++ b/llama_stack/templates/nvidia/run.yaml
@@ -137,4 +137,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/ollama/ollama.py b/llama_stack/templates/ollama/ollama.py
index a9a23c1c4..0473f8692 100644
--- a/llama_stack/templates/ollama/ollama.py
+++ b/llama_stack/templates/ollama/ollama.py
@@ -101,6 +101,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
diff --git a/llama_stack/templates/ollama/run.yaml b/llama_stack/templates/ollama/run.yaml
index aa7b54a87..2c69296fc 100644
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@@ -103,4 +103,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml
index 1743793a8..c35694d73 100644
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@@ -80,4 +80,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/remote-vllm/vllm.py b/llama_stack/templates/remote-vllm/vllm.py
index 8693d70d3..9dcaf2414 100644
--- a/llama_stack/templates/remote-vllm/vllm.py
+++ b/llama_stack/templates/remote-vllm/vllm.py
@@ -99,6 +99,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
diff --git a/llama_stack/templates/tgi/run.yaml b/llama_stack/templates/tgi/run.yaml
index 9cfba37aa..e9696c584 100644
--- a/llama_stack/templates/tgi/run.yaml
+++ b/llama_stack/templates/tgi/run.yaml
@@ -103,4 +103,10 @@ memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-tool_groups: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
diff --git a/llama_stack/templates/tgi/tgi.py b/llama_stack/templates/tgi/tgi.py
index 37ed2751b..b62e7719e 100644
--- a/llama_stack/templates/tgi/tgi.py
+++ b/llama_stack/templates/tgi/tgi.py
@@ -103,6 +103,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={