Rename builtin::memory -> builtin::rag

docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb

@@ -513,8 +513,8 @@
               "    provider_id: code-interpreter\n",
               "    provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::c</span>ode-interpreter\n",
               "  - config: <span style=\"font-weight: bold\">{}</span>\n",
-              "    provider_id: memory-runtime\n",
+              "    provider_id: rag-runtime\n",
-              "    provider_type: inline::memory-runtime\n",
+              "    provider_type: inline::rag-runtime\n",
               "scoring_fns: <span style=\"font-weight: bold\">[]</span>\n",
               "shields:\n",
               "- params: null\n",
@@ -528,8 +528,8 @@
               "  toolgroup_id: builtin::websearch\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
-              "  provider_id: memory-runtime\n",
+              "  provider_id: rag-runtime\n",
-              "  toolgroup_id: builtin::memory\n",
+              "  toolgroup_id: builtin::rag\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
               "  provider_id: code-interpreter\n",
@@ -694,8 +694,8 @@
               "    provider_id: code-interpreter\n",
               "    provider_type: inlin\u001b[1;92me::c\u001b[0mode-interpreter\n",
               "  - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
-              "    provider_id: memory-runtime\n",
+              "    provider_id: rag-runtime\n",
-              "    provider_type: inline::memory-runtime\n",
+              "    provider_type: inline::rag-runtime\n",
               "scoring_fns: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
               "shields:\n",
               "- params: null\n",
@@ -709,8 +709,8 @@
               "  toolgroup_id: builtin::websearch\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
-              "  provider_id: memory-runtime\n",
+              "  provider_id: rag-runtime\n",
-              "  toolgroup_id: builtin::memory\n",
+              "  toolgroup_id: builtin::rag\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
               "  provider_id: code-interpreter\n",

docs/notebooks/Llama_Stack_Building_AI_Applications.ipynb

@@ -884,8 +884,8 @@
               "    provider_id: code-interpreter\n",
               "    provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::c</span>ode-interpreter\n",
               "  - config: <span style=\"font-weight: bold\">{}</span>\n",
-              "    provider_id: memory-runtime\n",
+              "    provider_id: rag-runtime\n",
-              "    provider_type: inline::memory-runtime\n",
+              "    provider_type: inline::rag-runtime\n",
               "  - config: <span style=\"font-weight: bold\">{}</span>\n",
               "    provider_id: model-context-protocol\n",
               "    provider_type: remote::model-context-protocol\n",
@@ -910,8 +910,8 @@
               "  toolgroup_id: builtin::websearch\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
-              "  provider_id: memory-runtime\n",
+              "  provider_id: rag-runtime\n",
-              "  toolgroup_id: builtin::memory\n",
+              "  toolgroup_id: builtin::rag\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
               "  provider_id: code-interpreter\n",
@@ -1068,8 +1068,8 @@
               "    provider_id: code-interpreter\n",
               "    provider_type: inlin\u001b[1;92me::c\u001b[0mode-interpreter\n",
               "  - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
-              "    provider_id: memory-runtime\n",
+              "    provider_id: rag-runtime\n",
-              "    provider_type: inline::memory-runtime\n",
+              "    provider_type: inline::rag-runtime\n",
               "  - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
               "    provider_id: model-context-protocol\n",
               "    provider_type: remote::model-context-protocol\n",
@@ -1094,8 +1094,8 @@
               "  toolgroup_id: builtin::websearch\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
-              "  provider_id: memory-runtime\n",
+              "  provider_id: rag-runtime\n",
-              "  toolgroup_id: builtin::memory\n",
+              "  toolgroup_id: builtin::rag\n",
               "- args: null\n",
               "  mcp_endpoint: null\n",
               "  provider_id: code-interpreter\n",
@@ -1804,9 +1804,9 @@
           "data": {
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">ToolGroup</span><span style=\"font-weight: bold\">(</span>\n",
-              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">identifier</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::memory'</span>,\n",
+              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">identifier</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::rag'</span>,\n",
-              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'memory-runtime'</span>,\n",
+              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'rag-runtime'</span>,\n",
-              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_resource_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::memory'</span>,\n",
+              "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_resource_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::rag'</span>,\n",
               "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">type</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'tool_group'</span>,\n",
               "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">args</span>=<span style=\"color: #800080; text-decoration-color: #800080; font-style: italic\">None</span>,\n",
               "<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│   </span><span style=\"color: #808000; text-decoration-color: #808000\">mcp_endpoint</span>=<span style=\"color: #800080; text-decoration-color: #800080; font-style: italic\">None</span>\n",
@@ -1815,9 +1815,9 @@
             ],
             "text/plain": [
               "\u001b[1;35mToolGroup\u001b[0m\u001b[1m(\u001b[0m\n",
-              "\u001b[2;32m│   \u001b[0m\u001b[33midentifier\u001b[0m=\u001b[32m'builtin::memory'\u001b[0m,\n",
+              "\u001b[2;32m│   \u001b[0m\u001b[33midentifier\u001b[0m=\u001b[32m'builtin::rag'\u001b[0m,\n",
-              "\u001b[2;32m│   \u001b[0m\u001b[33mprovider_id\u001b[0m=\u001b[32m'memory-runtime'\u001b[0m,\n",
+              "\u001b[2;32m│   \u001b[0m\u001b[33mprovider_id\u001b[0m=\u001b[32m'rag-runtime'\u001b[0m,\n",
-              "\u001b[2;32m│   \u001b[0m\u001b[33mprovider_resource_id\u001b[0m=\u001b[32m'builtin::memory'\u001b[0m,\n",
+              "\u001b[2;32m│   \u001b[0m\u001b[33mprovider_resource_id\u001b[0m=\u001b[32m'builtin::rag'\u001b[0m,\n",
               "\u001b[2;32m│   \u001b[0m\u001b[33mtype\u001b[0m=\u001b[32m'tool_group'\u001b[0m,\n",
               "\u001b[2;32m│   \u001b[0m\u001b[33margs\u001b[0m=\u001b[3;35mNone\u001b[0m,\n",
               "\u001b[2;32m│   \u001b[0m\u001b[33mmcp_endpoint\u001b[0m=\u001b[3;35mNone\u001b[0m\n",
@@ -2118,7 +2118,7 @@
         "    enable_session_persistence=False,\n",
         "    toolgroups = [\n",
         "        {\n",
-        "          \"name\": \"builtin::memory\",\n",
+        "          \"name\": \"builtin::rag\",\n",
         "          \"args\" : {\n",
         "            \"vector_db_ids\": [vector_db_id],\n",
         "          }\n",

docs/source/distributions/remote_hosted_distro/nvidia.md

@@ -11,7 +11,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss` |
 
 

docs/source/distributions/self_hosted_distro/bedrock.md

@@ -18,7 +18,7 @@ The `llamastack/distribution-bedrock` distribution consists of the following pro
 | safety | `remote::bedrock` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/cerebras.md

@@ -11,7 +11,7 @@ The `llamastack/distribution-cerebras` distribution consists of the following pr
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/fireworks.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-fireworks` distribution consists of the following p
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/ollama.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -20,7 +20,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/tgi.md

@@ -22,7 +22,7 @@ The `llamastack/distribution-tgi` distribution consists of the following provide
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

docs/source/distributions/self_hosted_distro/together.md

@@ -21,7 +21,7 @@ The `llamastack/distribution-together` distribution consists of the following pr
 | safety | `inline::llama-guard` |
 | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 

llama_stack/distribution/ui/page/playground/rag.py

@@ -135,7 +135,7 @@ def rag_chat_page():
         },
         toolgroups=[
             dict(
-                name="builtin::memory",
+                name="builtin::rag",
                 args={
                     "vector_db_ids": [
                         vector_db_id for vector_db_id in selected_vector_dbs

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -81,7 +81,7 @@ def make_random_string(length: int = 8):
 TOOLS_ATTACHMENT_KEY_REGEX = re.compile(r"__tools_attachment__=(\{.*?\})")
 MEMORY_QUERY_TOOL = "query_from_memory"
 WEB_SEARCH_TOOL = "web_search"
-MEMORY_GROUP = "builtin::memory"
+RAG_TOOL_GROUP = "builtin::rag"
 
 
 class ChatAgent(ShieldRunnerMixin):
@@ -391,7 +391,7 @@ class ChatAgent(ShieldRunnerMixin):
                 session_id, documents, input_messages, tool_defs
             )
 
-        if MEMORY_GROUP in toolgroups and len(input_messages) > 0:
+        if RAG_TOOL_GROUP in toolgroups and len(input_messages) > 0:
             with tracing.span(MEMORY_QUERY_TOOL) as span:
                 step_id = str(uuid.uuid4())
                 yield AgentTurnResponseStreamChunk(
@@ -403,7 +403,7 @@ class ChatAgent(ShieldRunnerMixin):
                     )
                 )
 
-                args = toolgroup_args.get(MEMORY_GROUP, {})
+                args = toolgroup_args.get(RAG_TOOL_GROUP, {})
                 vector_db_ids = args.get("vector_db_ids", [])
                 query_config = args.get("query_config")
                 if query_config:
@@ -509,7 +509,7 @@ class ChatAgent(ShieldRunnerMixin):
                     tools=[
                         tool
                         for tool in tool_defs.values()
-                        if tool_to_group.get(tool.tool_name, None) != MEMORY_GROUP
+                        if tool_to_group.get(tool.tool_name, None) != RAG_TOOL_GROUP
                     ],
                     tool_prompt_format=self.agent_config.tool_prompt_format,
                     stream=True,
@@ -756,7 +756,7 @@ class ChatAgent(ShieldRunnerMixin):
             for tool_def in tools.data:
                 if (
                     toolgroup_name.startswith("builtin")
-                    and toolgroup_name != MEMORY_GROUP
+                    and toolgroup_name != RAG_TOOL_GROUP
                 ):
                     tool_name = tool_def.identifier
                     built_in_type = BuiltinTool.brave_search

llama_stack/providers/inline/agents/meta_reference/tests/test_chat_agent.py

@@ -152,7 +152,7 @@ class MockToolGroupsAPI:
                     toolgroup_id=MEMORY_TOOLGROUP,
                     tool_host=ToolHost.client,
                     description="Mock tool",
-                    provider_id="builtin::memory",
+                    provider_id="builtin::rag",
                     parameters=[],
                 )
             ]
@@ -260,7 +260,7 @@ async def get_chat_agent(get_agents_impl):
     return await impl.get_agent(response.agent_id)
 
 
-MEMORY_TOOLGROUP = "builtin::memory"
+MEMORY_TOOLGROUP = "builtin::rag"
 CODE_INTERPRETER_TOOLGROUP = "builtin::code_interpreter"
 
 

llama_stack/providers/registry/tool_runtime.py

@@ -19,7 +19,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.tool_runtime,
-            provider_type="inline::memory-runtime",
+            provider_type="inline::rag-runtime",
             pip_packages=[],
             module="llama_stack.providers.inline.tool_runtime.memory",
             config_class="llama_stack.providers.inline.tool_runtime.memory.config.MemoryToolRuntimeConfig",

llama_stack/providers/tests/agents/test_agents.py

@@ -184,7 +184,7 @@ class TestAgents:
         agent_config = AgentConfig(
             **{
                 **common_params,
-                "toolgroups": ["builtin::memory"],
+                "toolgroups": ["builtin::rag"],
                 "tool_choice": ToolChoice.auto,
             }
         )

llama_stack/providers/tests/tools/fixtures.py

@@ -22,8 +22,8 @@ def tool_runtime_memory_and_search() -> ProviderFixture:
     return ProviderFixture(
         providers=[
             Provider(
-                provider_id="memory-runtime",
+                provider_id="rag-runtime",
-                provider_type="inline::memory-runtime",
+                provider_type="inline::rag-runtime",
                 config={},
             ),
             Provider(
@@ -47,8 +47,8 @@ def tool_runtime_memory_and_search() -> ProviderFixture:
 @pytest.fixture(scope="session")
 def tool_group_input_memory() -> ToolGroupInput:
     return ToolGroupInput(
-        toolgroup_id="builtin::memory",
+        toolgroup_id="builtin::rag",
-        provider_id="memory-runtime",
+        provider_id="rag-runtime",
     )
 
 

llama_stack/templates/bedrock/bedrock.py

@@ -29,7 +29,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -58,8 +58,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/bedrock/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/bedrock/run.yaml

@@ -78,8 +78,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -111,7 +111,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/cerebras/build.yaml

@@ -27,5 +27,5 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
 image_type: conda

llama_stack/templates/cerebras/cerebras.py

@@ -33,7 +33,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
         ],
     }
 
@@ -79,8 +79,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/cerebras/run.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
 metadata_store:
   type: sqlite
@@ -113,7 +113,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/fireworks/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/fireworks/fireworks.py

@@ -38,7 +38,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -86,8 +86,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/fireworks/run-with-safety.yaml

@@ -89,8 +89,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -168,7 +168,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/fireworks/run.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -157,7 +157,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/hf-endpoint/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -33,7 +33,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -76,8 +76,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -88,8 +88,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -120,7 +120,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/hf-endpoint/run.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -110,7 +110,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/hf-serverless/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -33,7 +33,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -77,8 +77,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -88,8 +88,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -120,7 +120,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/hf-serverless/run.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -110,7 +110,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/meta-reference-gpu/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -37,7 +37,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -83,8 +83,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -90,8 +90,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -122,7 +122,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -84,8 +84,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -111,7 +111,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -32,7 +32,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -42,8 +42,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -86,8 +86,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -113,7 +113,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/nvidia/build.yaml

@@ -25,6 +25,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/nvidia/nvidia.py

@@ -28,7 +28,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -56,8 +56,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/nvidia/run.yaml

@@ -80,8 +80,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -143,7 +143,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/ollama/build.yaml

@@ -27,5 +27,5 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
 image_type: conda

llama_stack/templates/ollama/ollama.py

@@ -35,7 +35,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
         ],
     }
     name = "ollama"
@@ -77,8 +77,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/ollama/run-with-safety.yaml

@@ -85,8 +85,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
 metadata_store:
   type: sqlite
@@ -117,7 +117,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/ollama/run.yaml

@@ -82,8 +82,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
 metadata_store:
   type: sqlite
@@ -106,7 +106,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/remote-vllm/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -90,8 +90,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -122,7 +122,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/remote-vllm/run.yaml

@@ -84,8 +84,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -111,7 +111,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/remote-vllm/vllm.py

@@ -35,7 +35,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -80,8 +80,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/tgi/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/tgi/run-with-safety.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -110,7 +110,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/tgi/run.yaml

@@ -82,8 +82,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -109,7 +109,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/tgi/tgi.py

@@ -35,7 +35,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -80,8 +80,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/together/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/together/run-with-safety.yaml

@@ -89,8 +89,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -163,7 +163,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/together/run.yaml

@@ -83,8 +83,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -152,7 +152,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/together/together.py

@@ -38,7 +38,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -76,8 +76,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

llama_stack/templates/vllm-gpu/build.yaml

@@ -27,6 +27,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
     - remote::model-context-protocol
 image_type: conda

llama_stack/templates/vllm-gpu/run.yaml

@@ -86,8 +86,8 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
+  - provider_id: rag-runtime
-    provider_type: inline::memory-runtime
+    provider_type: inline::rag-runtime
     config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
@@ -113,7 +113,7 @@ eval_tasks: []
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search
-- toolgroup_id: builtin::memory
+- toolgroup_id: builtin::rag
-  provider_id: memory-runtime
+  provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter

llama_stack/templates/vllm-gpu/vllm.py

@@ -32,7 +32,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::code-interpreter",
-            "inline::memory-runtime",
+            "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
     }
@@ -72,8 +72,8 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="tavily-search",
         ),
         ToolGroupInput(
-            toolgroup_id="builtin::memory",
+            toolgroup_id="builtin::rag",
-            provider_id="memory-runtime",
+            provider_id="rag-runtime",
         ),
         ToolGroupInput(
             toolgroup_id="builtin::code_interpreter",

tests/client-sdk/agents/test_agents.py

@@ -292,7 +292,7 @@ def test_rag_agent(llama_stack_client, agent_config):
         **agent_config,
         "toolgroups": [
             dict(
-                name="builtin::memory",
+                name="builtin::rag",
                 args={
                     "vector_db_ids": [vector_db_id],
                 },