diff --git a/template/.env.example b/template/.env.example
new file mode 100644
index 0000000..e0c0c56
--- /dev/null
+++ b/template/.env.example
@@ -0,0 +1,9 @@
+# API URL of the skills API (usually helm:8675 on your network)
+API_URL=http://helm:8675
+
+# API Key (only required if auth is enabled on the skills API)
+# Get this from your skills API config
+API_KEY=
+
+# Optional: Project path for context
+PROJECT=/home/user/myproject
\ No newline at end of file
diff --git a/template/Dockerfile b/template/Dockerfile
new file mode 100644
index 0000000..f80e500
--- /dev/null
+++ b/template/Dockerfile
@@ -0,0 +1,10 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD ["python", "agent.py"]
\ No newline at end of file
diff --git a/template/README.md b/template/README.md
new file mode 100644
index 0000000..d20cd55
--- /dev/null
+++ b/template/README.md
@@ -0,0 +1,105 @@
+# Agent Template
+
+This template provides everything needed to connect an AI agent to the AI Skills API on your home network (`helm:8675`).
+
+## Structure
+
+```
+.
+├── docker-compose.yml    # Bring up your agent + skills API integration
+├── agent.py              # Example agent implementation
+├── .env.example          # Environment variables template
+├── requirements.txt      # Python dependencies
+└── README.md             # This file
+```
+
+## Quick Start
+
+1. Copy `.env.example` to `.env` and customize if needed
+2. Run `docker compose up -d` (or run agent.py directly)
+3. Your agent now has access to skills, conventions, and memory
+
+## How It Works
+
+The agent uses the AI Skills API at `http://helm:8675` to:
+- Fetch relevant context (`/context/rag`) before each query
+- Store learnings in memory (`/memory`) after interactions
+- Compress conversation history (`/compress`) periodically
+
+This reduces token usage by 60-70% compared to sending everything.
+
+## Integration Pattern
+
+```python
+import os
+import httpx
+from typing import List, Dict
+
+API_URL = os.getenv("API_URL", "http://helm:8675")
+API_KEY = os.getenv("API_KEY")  # Optional if auth enabled
+
+async def get_context(query: str, project: str = None) -> Dict:
+    """Fetch relevant skills and conventions for the query"""
+    params = {"query": query}
+    if project:
+        params["project"] = project
+    async with httpx.AsyncClient() as client:
+        resp = await client.get(f"{API_URL}/context/rag", params=params)
+        resp.raise_for_status()
+        return resp.json()
+
+async def store_memory(project: str, key: str, content: str):
+    """Save decision or learning for future reference"""
+    async with httpx.AsyncClient() as client:
+        headers = {"X-API-Key": API_KEY} if API_KEY else {}
+        resp = await client.post(
+            f"{API_URL}/memory",
+            json={"id": key[:8], "project": project, "key": key, "content": content},
+            headers=headers
+        )
+        resp.raise_for_status()
+        return resp.json()
+```
+
+## Docker Setup
+
+The provided `docker-compose.yml` runs the agent in a container and links it to the skills API. Ensure the skills API is running on `helm:8675` first.
+
+```bash
+# Start the skills API on helm (if not already running)
+docker compose -f /path/to/ai-skills-api/docker-compose.yml up -d
+
+# Start your agent
+docker compose up -d
+```
+
+## Configuration
+
+Edit `config.yaml` on the skills API side to adjust:
+- RAG limits (`max_skills`, `max_conventions`, `max_snippets`)
+- Compression strategy (`extractive` or `ollama`)
+- Authentication toggle
+
+## Adding Your Own Skills
+
+Use the skills API to add custom skills:
+
+```bash
+curl -X POST http://helm:8675/skills \
+  -H "Content-Type: application/json" \
+  -d '{
+    "id": "my-custom-skill",
+    "name": "My Skill",
+    "category": "custom",
+    "content": "Your instructions here...",
+    "tags": ["custom", "mytag"]
+  }'
+```
+
+Or use the MCP tools if you're in Claude Desktop:
+- `skills/create_skill` tool
+
+## Resources
+
+- Skills API docs: http://helm:8675/docs
+- AI Skills API repo: https://git.bouncypixel.com/helm/ai-skills-api
\ No newline at end of file
diff --git a/template/agent.py b/template/agent.py
new file mode 100644
index 0000000..0cf1d16
--- /dev/null
+++ b/template/agent.py
@@ -0,0 +1,116 @@
+# Example agent implementation
+# This demonstrates the integration pattern with AI Skills API
+
+import os
+import asyncio
+import httpx
+from typing import List, Dict, Optional
+
+API_URL = os.getenv("API_URL", "http://helm:8675")
+API_KEY = os.getenv("API_KEY")
+
+async def get_context(query: str, project: Optional[str] = None) -> Dict:
+    """Fetch relevant context from skills API"""
+    params = {"query": query}
+    if project:
+        params["project"] = project
+    
+    headers = {"X-API-Key": API_KEY} if API_KEY else {}
+    
+    async with httpx.AsyncClient() as client:
+        resp = await client.get(f"{API_URL}/context/rag", params=params, headers=headers)
+        resp.raise_for_status()
+        return resp.json()
+
+async def compress_messages(messages: List[Dict]) -> Dict:
+    """Compress conversation history"""
+    headers = {"X-API-Key": API_KEY} if API_KEY else {}
+    
+    async with httpx.AsyncClient() as client:
+        resp = await client.post(f"{API_URL}/compress", json={"messages": messages}, headers=headers)
+        resp.raise_for_status()
+        return resp.json()
+
+async def store_memory(project: str, key: str, content: str) -> Dict:
+    """Store a memory for future reference"""
+    headers = {"X-API-Key": API_KEY} if API_KEY else {}
+    
+    async with httpx.AsyncClient() as client:
+        resp = await client.post(
+            f"{API_URL}/memory",
+            json={"id": key[:8], "project": project, "key": key, "content": content},
+            headers=headers
+        )
+        resp.raise_for_status()
+        return resp.json()
+
+async def count_tokens(text: str) -> int:
+    """Count tokens using skills API"""
+    headers = {"X-API-Key": API_KEY} if API_KEY else {}
+    
+    async with httpx.AsyncClient() as client:
+        resp = await client.get(f"{API_URL}/tokens/count", params={"text": text}, headers=headers)
+        resp.raise_for_status()
+        return resp.json()["tokens"]
+
+async def chat_loop():
+    """Main chat loop - integrate with your LLM of choice"""
+    conversation = []
+    
+    print("Agent ready! Type 'quit' to exit.")
+    
+    while True:
+        user_input = input("\nYou: ")
+        if user_input.lower() == 'quit':
+            break
+        
+        # 1. Get relevant context
+        context = await get_context(user_input, project="/home/user/projects/myapp")
+        context_str = format_context(context)
+        
+        # 2. Build prompt with context
+        system_msg = f"{context_str}\n\nYou are a helpful assistant."
+        messages = [{"role": "system", "content": system_msg}]
+        messages.extend(conversation[-4:])  # Keep last few turns
+        messages.append({"role": "user", "content": user_input})
+        
+        # 3. Call your LLM here (not included - use OpenAI, Claude, Ollama, etc.)
+        # response = await call_llm(messages)
+        # For demo, we'll just echo
+        response = f"Echo: {user_input}"
+        
+        # 4. Update conversation
+        conversation.append({"role": "user", "content": user_input})
+        conversation.append({"role": "assistant", "content": response})
+        
+        # 5. Compress if getting long
+        if len(conversation) > 10:
+            compression = await compress_messages(conversation)
+            conversation = compression["messages"]
+            print(f"\n[Compressed: saved {compression['tokens_saved']} tokens]")
+        
+        print(f"\nAssistant: {response}")
+
+def format_context(context: Dict) -> str:
+    """Format RAG context for inclusion in prompt"""
+    parts = []
+    
+    if context.get("skills"):
+        parts.append("## Relevant Skills\n")
+        for skill in context["skills"]:
+            parts.append(f"### {skill['name']} (relevance: {skill['relevance_score']:.2f})\n{skill['content']}\n")
+    
+    if context.get("conventions"):
+        parts.append("## Project Conventions\n")
+        for conv in context["conventions"]:
+            parts.append(f"### {conv['name']}\n{conv['content']}\n")
+    
+    if context.get("snippets"):
+        parts.append("## Code Snippets\n")
+        for snippet in context["snippets"]:
+            parts.append(f"### {snippet['name']} ({snippet['language']})\n```{snippet['language']}\n{snippet['content']}\n```\n")
+    
+    return "\n".join(parts) if parts else "No relevant context found."
+
+if __name__ == "__main__":
+    asyncio.run(chat_loop())
\ No newline at end of file
diff --git a/template/docker-compose.yml b/template/docker-compose.yml
new file mode 100644
index 0000000..80144a6
--- /dev/null
+++ b/template/docker-compose.yml
@@ -0,0 +1,12 @@
+version: '3.8'
+
+services:
+  agent:
+    build: .
+    environment:
+      - API_URL=http://helm:8675
+      - API_KEY=${API_KEY:-}
+    volumes:
+      - ./logs:/app/logs
+    restart: unless-stopped
+    # Add your agent's specific configuration here
\ No newline at end of file
diff --git a/template/requirements.txt b/template/requirements.txt
new file mode 100644
index 0000000..8200458
--- /dev/null
+++ b/template/requirements.txt
@@ -0,0 +1,3 @@
+httpx==0.27.0
+python-dotenv==1.0.0
+# Add your agent's dependencies here
\ No newline at end of file