diff --git a/.clinerules b/.clinerules
new file mode 100644
index 0000000..da8e3fb
--- /dev/null
+++ b/.clinerules
@@ -0,0 +1,83 @@
+# === ROLE ===
+You are an Open Source Mentor Bot helping users work with an AOSSIE project template.
+
+# === PRIMARY BEHAVIOR ===
+- Always ask at least 1 clarifying question before answering (unless trivial)
+- Guide users step-by-step instead of dumping full answers
+- Help fill TODO sections in project templates
+
+# === CONTEXT AWARENESS ===
+You are working with a GitHub template repo that includes:
+- README with TODO sections (project name, description, user flow)
+- Setup instructions (install, run, env config)
+- Contribution guidelines
+
+# === QUESTION STRATEGY ===
+When user asks something:
+1. Ask what exactly they want to build
+2. Ask their tech stack (Node / Python / Flutter etc.)
+3. Ask their goal (GSoC / learning / hackathon / production)
+
+Examples:
+- "What are you building using this template?"
+- "Which tech stack are you planning to use?"
+- "Is this for GSoC or a personal project?"
+
+# === TASK-SPECIFIC BEHAVIOR ===
+
+## If user says "setup"
+- Ask:
+  - "Which language/framework are you using?"
+- Then guide:
+  - Clone repo
+  - Install dependencies
+  - Setup .env
+  - Run dev server
+
+## If user says "README"
+- Ask:
+  - "What is your project idea?"
+- Then help fill:
+  - Project name
+  - Description
+  - User flow
+  - Features
+
+## If user says "contribute"
+- Ask:
+  - "Are you contributing or creating your own project?"
+- Then guide:
+  - Fork repo
+  - Create branch
+  - Follow CONTRIBUTING.md
+
+## If user says "error"
+- Ask:
+  - "What error are you getting?"
+  - "Share logs/code snippet"
+- Then debug step-by-step
+
+# === RESPONSE STYLE ===
+- Keep answers short (max 6 lines)
+- Prefer bullet points
+- Ask → then guide → then suggest next step
+
+# === EXAMPLES ===
+
+User: "help me setup"
+Bot:
+- "Which tech stack are you using?"
+- Then guide setup steps
+
+User: "write README"
+Bot:
+- "What is your project idea?"
+- Then generate structured README
+
+# === RESTRICTIONS ===
+- Do not assume missing info
+- Always ask before generating full solutions
+- Avoid long explanations unless asked
+
+# === GOAL ===
+Act like a mentor helping users complete an AOSSIE template repo step-by-step.
\ No newline at end of file
diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..598b488
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,4 @@
+DISCORD_TOKEN=your_discord_bot_token_here
+DISCORD_CHANNEL_ID=your_channel_id_here
+OLLAMA_MODEL=llama3.2
+SKILL_FILE_PATH=.clinerules
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index 9308a4b..8b4e782 100644
--- a/.gitignore
+++ b/.gitignore
@@ -324,3 +324,6 @@ TSWLatexianTemp*
 # option is specified. Footnotes are the stored in a file with suffix Notes.bib.
 # Uncomment the next line to have this generated file ignored.
 #*Notes.bib
+
+venv/
+.env
\ No newline at end of file
diff --git a/bot.py b/bot.py
new file mode 100644
index 0000000..e576997
--- /dev/null
+++ b/bot.py
@@ -0,0 +1,163 @@
+import os
+import logging
+import discord
+import httpx
+import asyncio
+from dotenv import load_dotenv
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger('aossie-bot')
+
+# Load environment variables
+load_dotenv()
+
+DISCORD_TOKEN = os.getenv('DISCORD_TOKEN')
+DISCORD_CHANNEL_ID = os.getenv('DISCORD_CHANNEL_ID')
+DISCORD_CHANNEL_ID_INT = None
+OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'llama3.2')
+SKILL_FILE_PATH = os.getenv('SKILL_FILE_PATH', '.clinerules')
+OLLAMA_URL = "http://localhost:11434/api/generate"
+
+# Initialize bot with intents
+intents = discord.Intents.default()
+intents.message_content = True
+client = discord.Client(intents=intents)
+
+# Lock to prevent Ollama requests from clashing
+ollama_lock = asyncio.Lock()
+
+def load_skill_context() -> str:
+    """Load context from the local skill file."""
+    try:
+        if os.path.exists(SKILL_FILE_PATH):
+            with open(SKILL_FILE_PATH, 'r', encoding='utf-8') as f:
+                return f.read()
+    except Exception as e:
+        logger.error(f"Error loading skill file {SKILL_FILE_PATH}: {e}")
+    return ""
+
+async def generate_ollama_response(prompt: str, context: str) -> str:
+    """Send prompt to local Ollama instance and return the response."""
+    if context:
+        system_prompt = f"You are a helpful contributor assistant for AOSSIE.\n\nContext guidelines:\n{context}"
+    else:
+        system_prompt = "You are a helpful contributor assistant for AOSSIE."
+
+    payload = {
+        "model": OLLAMA_MODEL,
+        "prompt": prompt,
+        "system": system_prompt,
+        "stream": False
+    }
+
+    try:
+        async with httpx.AsyncClient(timeout=120.0) as http_client:
+            response = await http_client.post(OLLAMA_URL, json=payload)
+            response.raise_for_status()
+            data = response.json()
+            return data.get("response", "Error: No response text found in Ollama reply.")
+    except httpx.TimeoutException:
+        logger.error("Ollama request timed out.")
+        return "I'm sorry, the local AI model timed out while thinking. Please try again later."
+    except httpx.RequestError as e:
+        logger.error(f"Ollama request error: {e}")
+        return f"I'm sorry, I couldn't reach the local AI engine. Ensure Ollama is running at localhost:11434."
+    except Exception as e:
+        logger.error(f"Unexpected error during Ollama generation: {e}")
+        return "An unexpected error occurred while generating the response."
+
+async def process_message(message: discord.Message):
+    """Process a single message and generate a reply safely."""
+    if message.author.bot or message.channel.id != DISCORD_CHANNEL_ID_INT:
+        return
+
+    # Use lock to ensure only one message is processed by Ollama at a time
+    async with ollama_lock:
+        async with message.channel.typing():
+            skill_context = load_skill_context()
+            response_text = await generate_ollama_response(message.content, skill_context)
+            
+            if len(response_text) > 1900:
+                response_text = response_text[:1896] + "..."
+
+            await message.reply(response_text)
+
+async def wait_for_ollama():
+    """Wait until Ollama is up and responding."""
+    logger.info("Waiting for Ollama to be ready...")
+    while True:
+        try:
+            async with httpx.AsyncClient(timeout=5.0) as http_client:
+                response = await http_client.get("http://localhost:11434/")
+                if response.status_code == 200:
+                    logger.info("Ollama is ready!")
+                    return
+        except httpx.RequestError:
+            pass
+        logger.info("Ollama not reachable yet. Retrying in 10 seconds...")
+        await asyncio.sleep(10)
+
+@client.event
+async def on_ready():
+    logger.info(f"Logged in as {client.user.name} ({client.user.id})")
+    
+    # Wait for Ollama to be ready before processing the backlog
+    await wait_for_ollama()
+    
+    logger.info("Checking for missed messages...")
+    
+    try:
+        channel = await client.fetch_channel(DISCORD_CHANNEL_ID_INT)
+        
+        # Find the last message sent by the bot
+        last_bot_msg = None
+        async for msg in channel.history(limit=50):
+            if msg.author.id == client.user.id:
+                last_bot_msg = msg
+                break
+        
+        messages_to_process = []
+        if last_bot_msg:
+            # Fetch messages after the bot's last message
+            async for msg in channel.history(after=last_bot_msg, oldest_first=True):
+                if not msg.author.bot:
+                    messages_to_process.append(msg)
+        else:
+            # If no bot message found, just process the last 5 user messages
+            async for msg in channel.history(limit=5, oldest_first=True):
+                if not msg.author.bot:
+                    messages_to_process.append(msg)
+                    
+        logger.info(f"Found {len(messages_to_process)} missed messages. Processing...")
+        for msg in messages_to_process:
+            await process_message(msg)
+            
+    except Exception as e:
+        logger.error(f"Error fetching missed messages: {e}")
+
+    logger.info("AOSSIE Contributor Assistant MVP is fully ready.")
+
+@client.event
+async def on_message(message: discord.Message):
+    await process_message(message)
+
+if __name__ == "__main__":
+    if not DISCORD_TOKEN:
+        logger.critical("DISCORD_TOKEN is missing from environment. Exiting.")
+        exit(1)
+
+    if not DISCORD_CHANNEL_ID:
+        logger.critical("DISCORD_CHANNEL_ID is missing from environment. Exiting.")
+        exit(1)
+
+    try:
+        DISCORD_CHANNEL_ID_INT = int(DISCORD_CHANNEL_ID)
+    except ValueError:
+        logger.critical(
+            f"DISCORD_CHANNEL_ID '{DISCORD_CHANNEL_ID}' is not a valid integer. Exiting."
+        )
+        exit(1)
+
+    logger.info("Starting bot...")
+    client.run(DISCORD_TOKEN)
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..66958f5
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+discord.py==2.3.2
+httpx==0.27.0
+python-dotenv==1.2.2
+idna==3.15
\ No newline at end of file