diff --git a/.github/workflows/integration-tests.yml b/.github/workflows/integration-tests.yml
new file mode 100644
index 000000000..af268e728
--- /dev/null
+++ b/.github/workflows/integration-tests.yml
@@ -0,0 +1,80 @@
+name: Integration tests
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  ollama:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          python-version: "3.10"
+
+      - name: Install Ollama
+        run: |
+          curl -fsSL https://ollama.com/install.sh | sh
+
+      - name: Pull Ollama image
+        run: |
+          ollama pull llama3.2:3b-instruct-fp16
+
+      - name: Start Ollama in background
+        run: |
+          nohup ollama run llama3.2:3b-instruct-fp16 > ollama.log 2>&1 &
+
+      - name: Set Up Environment and Install Dependencies
+        run: |
+          uv sync --extra dev --extra test
+          uv pip install ollama faiss-cpu
+          uv pip install -e .
+
+      - name: Wait for Ollama to start
+        run: |
+          echo "Waiting for Ollama..."
+          for i in {1..30}; do
+            if curl -s http://localhost:11434 | grep -q "Ollama is running"; then
+              echo "Ollama is running!"
+              exit 0
+            fi
+            sleep 1
+          done
+          echo "Ollama failed to start"
+          ollama ps
+          ollama.log
+          exit 1
+
+      - name: Start Llama Stack server in background
+        env:
+          INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
+        run: |
+          source .venv/bin/activate
+          # TODO: use "llama stack run"
+          nohup uv run python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml > server.log 2>&1 &
+
+      - name: Wait for Llama Stack server to be ready
+        run: |
+          echo "Waiting for Llama Stack server..."
+          for i in {1..30}; do
+            if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
+              echo " Llama Stack server is up!"
+              exit 0
+            fi
+            sleep 1
+          done
+          echo " Llama Stack server failed to start"
+          cat server.log
+          exit 1
+
+      - name: Run Inference Integration Tests
+        env:
+          INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
+        run: |
+          uv run pytest -v tests/integration/inference --stack-config=ollama --text-model="meta-llama/Llama-3.2-3B-Instruct" --embedding-model=all-MiniLM-L6-v2