diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..0c79747
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,37 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    name: pytest (py${{ matrix.python-version }})
+    runs-on: ubuntu-latest
+    # A hang must fail LOUDLY and fast, not sit burning runner time until the
+    # 6h default -- a job stuck at "in_progress" reads as "not done yet"
+    # rather than "broken", which is how a false green gets merged.
+    timeout-minutes: 10
+    strategy:
+      fail-fast: false
+      matrix:
+        # requires-python = ">=3.11" -- cover the floor and a current minor.
+        python-version: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --all-extras --dev
+
+      - name: Run test suite
+        # Deselects tests marked `live`: the inherited
+        # test_list_models_returns_list makes a real network call to
+        # the configured vLLM/OpenAI-compatible endpoint. Run locally
+        # against a real server to validate.
+        run: uv run pytest -q -m "not live"
diff --git a/pyproject.toml b/pyproject.toml
index 91f7c41..5239b49 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -45,6 +45,9 @@ allow-direct-references = true
 testpaths = ["tests"]
 addopts = "--import-mode=importlib"
 asyncio_mode = "strict"
+markers = [
+    "live: requires a reachable vLLM/OpenAI-compatible server; deselected in CI via `-m \"not live\"`",
+]
 
 [dependency-groups]
 dev = [
diff --git a/tests/test_behavioral.py b/tests/test_behavioral.py
index 25788a5..5151583 100644
--- a/tests/test_behavioral.py
+++ b/tests/test_behavioral.py
@@ -3,6 +3,8 @@
 Inherits authoritative tests from amplifier-core.
 """
 
+import pytest
+
 from amplifier_core.validation.behavioral import ProviderBehaviorTests
 
 
@@ -12,3 +14,17 @@ class TestVllmProviderBehavior(ProviderBehaviorTests):
     All tests from ProviderBehaviorTests run automatically.
     Add module-specific tests below if needed.
     """
+
+    @pytest.mark.live
+    @pytest.mark.asyncio
+    async def test_list_models_returns_list(self, provider_module):
+        """Override to mark this inherited test 'live'.
+
+        ProviderBehaviorTests.test_list_models_returns_list calls
+        provider_module.list_models(), which makes a real network call
+        to the configured vLLM/OpenAI-compatible endpoint -- it cannot
+        pass in CI without a reachable server. Deselected in CI via
+        `-m "not live"`; run locally against a real vLLM server to
+        validate.
+        """
+        await super().test_list_models_returns_list(provider_module)