diff --git a/.github/workflows/dependency-check.yml b/.github/workflows/dependency-check.yml
new file mode 100644
index 000000000..90a9fac19
--- /dev/null
+++ b/.github/workflows/dependency-check.yml
@@ -0,0 +1,53 @@
+name: Dependency Check
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  dependency-check:
+    name: Dependency Vulnerability Check
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Run Dependency Review
+        uses: actions/dependency-review-action@v4
+        with:
+          fail-on-severity: low
+          allow-licenses: MIT, Apache-2.0, BSD-2-Clause, BSD-3-Clause, ISC
+
+  dependency-graph:
+    name: Dependency Graph Validation
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+
+      - name: Generate dependency summary
+        run: |
+          echo "## Dependency Summary" >> $GITHUB_STEP_SUMMARY
+          echo "Checking dependency files..." >> $GITHUB_STEP_SUMMARY
+          
+          if [ -f "package.json" ]; then
+            echo "### npm dependencies" >> $GITHUB_STEP_SUMMARY
+            npm list --depth=0 --json 2>/dev/null | jq -r '.dependencies | to_entries[] | "- \(.key)@\(.value.version)"' >> $GITHUB_STEP_SUMMARY || echo "No npm dependencies" >> $GITHUB_STEP_SUMMARY
+          fi
+          
+          if [ -f "requirements.txt" ]; then
+            echo "### Python dependencies" >> $GITHUB_STEP_SUMMARY
+            cat requirements.txt >> $GITHUB_STEP_SUMMARY
+          fi
+          
+          if [ -f "pyproject.toml" ]; then
+            echo "### Python project dependencies" >> $GITHUB_STEP_SUMMARY
+            grep -A 50 '\[tool.poetry.dependencies\]' pyproject.toml 2>/dev/null || echo "No poetry dependencies" >> $GITHUB_STEP_SUMMARY
+          fi
\ No newline at end of file
diff --git a/README.md b/README.md
index ddc80314e..c9d30a857 100644
--- a/README.md
+++ b/README.md
@@ -224,6 +224,57 @@ To address this, we introduced PageIndex OCR — the first long-context OCR mode
 
 ---
 
+# 🛠️ Development Guide
+
+Contributions are welcome! To set up a local development environment:
+
+### 1. Clone the repository
+
+```bash
+git clone https://github.com/VectifyAI/PageIndex.git
+cd PageIndex
+```
+
+### 2. Create a feature branch
+
+```bash
+git checkout -b docs/add-development-guide
+```
+
+### 3. Install dependencies
+
+```bash
+pip3 install --upgrade -r requirements.txt
+```
+
+### 4. Set up environment variables
+
+Create a `.env` file in the root directory:
+
+```bash
+OPENAI_API_KEY=your_openai_key_here
+```
+
+### 5. Run tests (if available)
+
+```bash
+pytest tests/
+```
+
+### 6. Make your changes and commit
+
+```bash
+git add .
+git commit -m "your descriptive commit message"
+git push origin docs/add-development-guide
+```
+
+### 7. Open a pull request
+
+Submit a PR against the `main` branch of `VectifyAI/PageIndex`.
+
+---
+
 # 📈 Case Study: PageIndex Leads Finance QA Benchmark
 
 [Mafin 2.5](https://vectify.ai/mafin) is a reasoning-based RAG system for financial document analysis, powered by **PageIndex**. It achieved a state-of-the-art [**98.7% accuracy**](https://vectify.ai/blog/Mafin2.5) on the [FinanceBench](https://arxiv.org/abs/2311.11944) benchmark, significantly outperforming traditional vector-based RAG systems.