diff --git a/distributions/dependencies.json b/distributions/dependencies.json
index 4e66a85da..a2393cdea 100644
--- a/distributions/dependencies.json
+++ b/distributions/dependencies.json
@@ -16,6 +16,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -45,6 +47,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -75,6 +79,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -103,6 +109,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -133,6 +141,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -164,6 +174,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -194,6 +206,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -226,6 +240,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -262,6 +278,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -292,6 +310,8 @@
     "matplotlib",
     "nltk",
     "numpy",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -323,6 +343,8 @@
     "numpy",
     "ollama",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
@@ -354,6 +376,8 @@
     "nltk",
     "numpy",
     "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
     "pandas",
     "pillow",
     "psycopg2-binary",
diff --git a/llama_stack/__init__.py b/llama_stack/__init__.py
index 756f351d8..34b866692 100644
--- a/llama_stack/__init__.py
+++ b/llama_stack/__init__.py
@@ -3,3 +3,5 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+#
+# from .distribution.library_client import LlamaStackAsLibraryClient, AsyncLlamaStackAsLibraryClient
diff --git a/llama_stack/cli/stack/build.py b/llama_stack/cli/stack/build.py
index 00d62bd73..f19c6e798 100644
--- a/llama_stack/cli/stack/build.py
+++ b/llama_stack/cli/stack/build.py
@@ -73,7 +73,7 @@ class StackBuild(Subcommand):
             "--image-type",
             type=str,
             help="Image Type to use for the build. This can be either conda or docker. If not specified, will use the image type from the template config.",
-            choices=["conda", "docker"],
+            choices=["conda", "docker", "venv"],
             default="conda",
         )
 
@@ -124,8 +124,8 @@ class StackBuild(Subcommand):
             image_type = prompt(
                 "> Enter the image type you want your Llama Stack to be built as (docker or conda): ",
                 validator=Validator.from_callable(
-                    lambda x: x in ["docker", "conda"],
-                    error_message="Invalid image type, please enter conda or docker",
+                    lambda x: x in ["docker", "conda", "venv"],
+                    error_message="Invalid image type, please enter conda or docker or venv",
                 ),
                 default="conda",
             )
diff --git a/llama_stack/distribution/build.py b/llama_stack/distribution/build.py
index 3349a7d50..bdda0349f 100644
--- a/llama_stack/distribution/build.py
+++ b/llama_stack/distribution/build.py
@@ -38,6 +38,7 @@ SERVER_DEPENDENCIES = [
 class ImageType(Enum):
     docker = "docker"
     conda = "conda"
+    venv = "venv"
 
 
 class ApiInput(BaseModel):
@@ -120,7 +121,7 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
             str(BUILDS_BASE_DIR / ImageType.docker.value),
             " ".join(normal_deps),
         ]
-    else:
+    elif build_config.image_type == ImageType.conda.value:
         script = pkg_resources.resource_filename(
             "llama_stack", "distribution/build_conda_env.sh"
         )
@@ -130,6 +131,16 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
             str(build_file_path),
             " ".join(normal_deps),
         ]
+    elif build_config.image_type == ImageType.venv.value:
+        script = pkg_resources.resource_filename(
+            "llama_stack", "distribution/build_venv.sh"
+        )
+        args = [
+            script,
+            build_config.name,
+            str(build_file_path),
+            " ".join(normal_deps),
+        ]
 
     if special_deps:
         args.append("#".join(special_deps))
diff --git a/llama_stack/distribution/build_venv.sh b/llama_stack/distribution/build_venv.sh
new file mode 100755
index 000000000..8136e3120
--- /dev/null
+++ b/llama_stack/distribution/build_venv.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+# TODO: combine this with build_conda_env.sh since it is almost identical
+# the only difference is that we don't do any conda-specific setup
+
+LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
+LLAMA_STACK_DIR=${LLAMA_STACK_DIR:-}
+TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
+
+if [ -n "$LLAMA_STACK_DIR" ]; then
+  echo "Using llama-stack-dir=$LLAMA_STACK_DIR"
+fi
+if [ -n "$LLAMA_MODELS_DIR" ]; then
+  echo "Using llama-models-dir=$LLAMA_MODELS_DIR"
+fi
+
+if [ "$#" -lt 3 ]; then
+  echo "Usage: $0 <distribution_type> <build_name> <build_file_path> <pip_dependencies> [<special_pip_deps>]" >&2
+  echo "Example: $0 <distribution_type> mybuild ./my-stack-build.yaml 'numpy pandas scipy'" >&2
+  exit 1
+fi
+
+special_pip_deps="$4"
+
+set -euo pipefail
+
+build_name="$1"
+env_name="llamastack-$build_name"
+build_file_path="$2"
+pip_dependencies="$3"
+
+# Define color codes
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+NC='\033[0m' # No Color
+
+# this is set if we actually create a new conda in which case we need to clean up
+ENVNAME=""
+
+SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
+source "$SCRIPT_DIR/common.sh"
+
+run() {
+  local env_name="$1"
+  local pip_dependencies="$2"
+  local special_pip_deps="$3"
+
+  if [ -n "$TEST_PYPI_VERSION" ]; then
+    # these packages are damaged in test-pypi, so install them first
+    pip install fastapi libcst
+    pip install --extra-index-url https://test.pypi.org/simple/ \
+      llama-models==$TEST_PYPI_VERSION llama-stack==$TEST_PYPI_VERSION \
+      $pip_dependencies
+    if [ -n "$special_pip_deps" ]; then
+      IFS='#' read -ra parts <<<"$special_pip_deps"
+      for part in "${parts[@]}"; do
+        echo "$part"
+        pip install $part
+      done
+    fi
+  else
+    # Re-installing llama-stack in the new conda environment
+    if [ -n "$LLAMA_STACK_DIR" ]; then
+      if [ ! -d "$LLAMA_STACK_DIR" ]; then
+        printf "${RED}Warning: LLAMA_STACK_DIR is set but directory does not exist: $LLAMA_STACK_DIR${NC}\n" >&2
+        exit 1
+      fi
+
+      printf "Installing from LLAMA_STACK_DIR: $LLAMA_STACK_DIR\n"
+      pip install --no-cache-dir -e "$LLAMA_STACK_DIR"
+    else
+      pip install --no-cache-dir llama-stack
+    fi
+
+    if [ -n "$LLAMA_MODELS_DIR" ]; then
+      if [ ! -d "$LLAMA_MODELS_DIR" ]; then
+        printf "${RED}Warning: LLAMA_MODELS_DIR is set but directory does not exist: $LLAMA_MODELS_DIR${NC}\n" >&2
+        exit 1
+      fi
+
+      printf "Installing from LLAMA_MODELS_DIR: $LLAMA_MODELS_DIR\n"
+      pip uninstall -y llama-models
+      pip install --no-cache-dir -e "$LLAMA_MODELS_DIR"
+    fi
+
+    # Install pip dependencies
+    printf "Installing pip dependencies\n"
+    pip install $pip_dependencies
+    if [ -n "$special_pip_deps" ]; then
+      IFS='#' read -ra parts <<<"$special_pip_deps"
+      for part in "${parts[@]}"; do
+        echo "$part"
+        pip install $part
+      done
+    fi
+  fi
+}
+
+run "$env_name" "$pip_dependencies" "$special_pip_deps"
diff --git a/llama_stack/distribution/datatypes.py b/llama_stack/distribution/datatypes.py
index c2bff4eed..1159372d4 100644
--- a/llama_stack/distribution/datatypes.py
+++ b/llama_stack/distribution/datatypes.py
@@ -165,5 +165,5 @@ class BuildConfig(BaseModel):
     )
     image_type: str = Field(
         default="conda",
-        description="Type of package to build (conda | container)",
+        description="Type of package to build (conda | docker | venv)",
     )
diff --git a/llama_stack/distribution/library_client.py b/llama_stack/distribution/library_client.py
index 4de06ae08..64cd343d4 100644
--- a/llama_stack/distribution/library_client.py
+++ b/llama_stack/distribution/library_client.py
@@ -6,6 +6,7 @@
 
 import asyncio
 import inspect
+import os
 import queue
 import threading
 from concurrent.futures import ThreadPoolExecutor
@@ -32,6 +33,18 @@ from llama_stack.distribution.stack import (
 T = TypeVar("T")
 
 
+def is_jupyter():
+    """Check if we're running in a Jupyter notebook"""
+    try:
+        shell = get_ipython().__class__.__name__  # type: ignore
+        if shell == "ZMQInteractiveShell":  # Jupyter notebook or qtconsole
+            return True
+        else:
+            return False
+    except NameError:  # Probably standard Python interpreter
+        return False
+
+
 def stream_across_asyncio_run_boundary(
     async_gen_maker,
     pool_executor: ThreadPoolExecutor,
@@ -102,7 +115,12 @@ class LlamaStackAsLibraryClient(LlamaStackClient):
         self.pool_executor = ThreadPoolExecutor(max_workers=4)
 
     def initialize(self):
-        asyncio.run(self.async_client.initialize())
+        if is_jupyter():
+            import nest_asyncio
+
+            nest_asyncio.apply()
+
+        return asyncio.run(self.async_client.initialize())
 
     def get(self, *args, **kwargs):
         if kwargs.get("stream"):
@@ -131,6 +149,10 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
     ):
         super().__init__()
 
+        # when using the library client, we should not log to console since many
+        # of our logs are intended for server-side usage
+        os.environ["TELEMETRY_SINKS"] = "sqlite"
+
         if config_path_or_template_name.endswith(".yaml"):
             config_path = Path(config_path_or_template_name)
             if not config_path.exists():
@@ -150,13 +172,19 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
             self.impls = await construct_stack(
                 self.config, self.custom_provider_registry
             )
-        except ModuleNotFoundError as e:
+        except ModuleNotFoundError as _e:
             cprint(
                 "Using llama-stack as a library requires installing dependencies depending on the template (providers) you choose.\n",
                 "yellow",
             )
-            print_pip_install_help(self.config.providers)
-            raise e
+            if self.config_path_or_template_name.endswith(".yaml"):
+                print_pip_install_help(self.config.providers)
+            else:
+                cprint(
+                    f"Please run:\n\nllama stack build --template {self.config_path_or_template_name} --image-type venv\n\n",
+                    "yellow",
+                )
+            return False
 
         console = Console()
         console.print(f"Using config [blue]{self.config_path_or_template_name}[/blue]:")
@@ -171,6 +199,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
                 endpoint_impls[endpoint.route] = func
 
         self.endpoint_impls = endpoint_impls
+        return True
 
     async def get(
         self,
diff --git a/llama_stack/distribution/tests/library_client_test.py b/llama_stack/distribution/tests/library_client_test.py
index 8381f5470..5e7b997f3 100644
--- a/llama_stack/distribution/tests/library_client_test.py
+++ b/llama_stack/distribution/tests/library_client_test.py
@@ -17,7 +17,8 @@ from llama_stack_client.types.agent_create_params import AgentConfig
 
 def main(config_path: str):
     client = LlamaStackAsLibraryClient(config_path)
-    client.initialize()
+    if not client.initialize():
+        return
 
     models = client.models.list()
     print("\nModels:")
diff --git a/llama_stack/providers/inline/telemetry/meta_reference/__init__.py b/llama_stack/providers/inline/telemetry/meta_reference/__init__.py
index 38871a7e4..2905e2f6a 100644
--- a/llama_stack/providers/inline/telemetry/meta_reference/__init__.py
+++ b/llama_stack/providers/inline/telemetry/meta_reference/__init__.py
@@ -7,12 +7,13 @@
 from typing import Any, Dict
 
 from .config import TelemetryConfig, TelemetrySink
-from .telemetry import TelemetryAdapter
 
-__all__ = ["TelemetryConfig", "TelemetryAdapter", "TelemetrySink"]
+__all__ = ["TelemetryConfig", "TelemetrySink"]
 
 
 async def get_provider_impl(config: TelemetryConfig, deps: Dict[str, Any]):
+    from .telemetry import TelemetryAdapter
+
     impl = TelemetryAdapter(config, deps)
     await impl.initialize()
     return impl
diff --git a/llama_stack/providers/inline/telemetry/meta_reference/config.py b/llama_stack/providers/inline/telemetry/meta_reference/config.py
index 4aaa368d1..41d62c268 100644
--- a/llama_stack/providers/inline/telemetry/meta_reference/config.py
+++ b/llama_stack/providers/inline/telemetry/meta_reference/config.py
@@ -7,7 +7,7 @@
 from enum import Enum
 from typing import Any, Dict, List
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator
 
 from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
 
@@ -36,10 +36,23 @@ class TelemetryConfig(BaseModel):
         description="The path to the SQLite database to use for storing traces",
     )
 
+    @field_validator("sinks", mode="before")
     @classmethod
-    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
+    def validate_sinks(cls, v):
+        if isinstance(v, str):
+            return [TelemetrySink(sink.strip()) for sink in v.split(",")]
+        return v
+
+    @classmethod
+    def sample_run_config(
+        cls, __distro_dir__: str = "runtime", db_name: str = "trace_store.db"
+    ) -> Dict[str, Any]:
         return {
             "service_name": "${env.OTEL_SERVICE_NAME:llama-stack}",
-            "sinks": "${env.TELEMETRY_SINKS:['console', 'sqlite']}",
-            "sqlite_db_path": "${env.SQLITE_DB_PATH:${runtime.base_dir}/trace_store.db}",
+            "sinks": "${env.TELEMETRY_SINKS:console,sqlite}",
+            "sqlite_db_path": "${env.SQLITE_DB_PATH:~/.llama/"
+            + __distro_dir__
+            + "/"
+            + db_name
+            + "}",
         }
diff --git a/llama_stack/templates/bedrock/run.yaml b/llama_stack/templates/bedrock/run.yaml
index 77d4f2248..db0ee9d85 100644
--- a/llama_stack/templates/bedrock/run.yaml
+++ b/llama_stack/templates/bedrock/run.yaml
@@ -39,7 +39,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/bedrock/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/cerebras/run.yaml b/llama_stack/templates/cerebras/run.yaml
index 0b41f5b76..451e2b076 100644
--- a/llama_stack/templates/cerebras/run.yaml
+++ b/llama_stack/templates/cerebras/run.yaml
@@ -38,7 +38,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
 metadata_store:
   namespace: null
   type: sqlite
diff --git a/llama_stack/templates/fireworks/run.yaml b/llama_stack/templates/fireworks/run.yaml
index 9296be28f..c75db478d 100644
--- a/llama_stack/templates/fireworks/run.yaml
+++ b/llama_stack/templates/fireworks/run.yaml
@@ -41,7 +41,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/hf-endpoint/run-with-safety.yaml b/llama_stack/templates/hf-endpoint/run-with-safety.yaml
index bd625ffc5..678857201 100644
--- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml
+++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml
@@ -46,7 +46,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/hf-endpoint/run.yaml b/llama_stack/templates/hf-endpoint/run.yaml
index bf0697bba..c062c6c98 100644
--- a/llama_stack/templates/hf-endpoint/run.yaml
+++ b/llama_stack/templates/hf-endpoint/run.yaml
@@ -41,7 +41,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/hf-serverless/run-with-safety.yaml b/llama_stack/templates/hf-serverless/run-with-safety.yaml
index f5ead14d4..4a14ba093 100644
--- a/llama_stack/templates/hf-serverless/run-with-safety.yaml
+++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml
@@ -46,7 +46,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/hf-serverless/run.yaml b/llama_stack/templates/hf-serverless/run.yaml
index 13e2d7789..268efddc4 100644
--- a/llama_stack/templates/hf-serverless/run.yaml
+++ b/llama_stack/templates/hf-serverless/run.yaml
@@ -41,7 +41,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
index d0fa05e96..963679665 100644
--- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
@@ -48,7 +48,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/meta-reference-gpu/run.yaml b/llama_stack/templates/meta-reference-gpu/run.yaml
index 3675f4a58..a74cde768 100644
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@@ -42,7 +42,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
index 081af0f59..5aada0fe6 100644
--- a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
@@ -44,7 +44,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-quantized-gpu/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/ollama/run-with-safety.yaml b/llama_stack/templates/ollama/run-with-safety.yaml
index dc282f996..2ab0f78f0 100644
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@@ -40,7 +40,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/ollama/run.yaml b/llama_stack/templates/ollama/run.yaml
index ab8e12839..c5206c2d0 100644
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@@ -40,7 +40,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/remote-vllm/run-with-safety.yaml b/llama_stack/templates/remote-vllm/run-with-safety.yaml
index c0849e2d0..ac8cf6f4a 100644
--- a/llama_stack/templates/remote-vllm/run-with-safety.yaml
+++ b/llama_stack/templates/remote-vllm/run-with-safety.yaml
@@ -45,7 +45,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
 metadata_store:
   namespace: null
   type: sqlite
diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml
index 3457afdd6..27c5df53c 100644
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@@ -39,7 +39,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
 metadata_store:
   namespace: null
   type: sqlite
diff --git a/llama_stack/templates/tgi/run-with-safety.yaml b/llama_stack/templates/tgi/run-with-safety.yaml
index 2ee82ddc3..ecd03c36a 100644
--- a/llama_stack/templates/tgi/run-with-safety.yaml
+++ b/llama_stack/templates/tgi/run-with-safety.yaml
@@ -44,7 +44,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/tgi/run.yaml b/llama_stack/templates/tgi/run.yaml
index c45e114ee..b93f09042 100644
--- a/llama_stack/templates/tgi/run.yaml
+++ b/llama_stack/templates/tgi/run.yaml
@@ -40,7 +40,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml
index a9f96a099..381557816 100644
--- a/llama_stack/templates/together/run.yaml
+++ b/llama_stack/templates/together/run.yaml
@@ -41,7 +41,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
diff --git a/llama_stack/templates/vllm-gpu/run.yaml b/llama_stack/templates/vllm-gpu/run.yaml
index ea188777f..1442273f4 100644
--- a/llama_stack/templates/vllm-gpu/run.yaml
+++ b/llama_stack/templates/vllm-gpu/run.yaml
@@ -44,7 +44,10 @@ providers:
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/vllm-gpu/trace_store.db}
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference