🔁 Add AutoExec AI full application files for Hugging Face Space

.streamlit/secrets.toml

@@ -0,0 +1,2 @@
+GEMINI_API_KEY = "your-gemini-api-key"
+OPENAI_API_KEY = "your-openai-api-key"

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.10
+
+WORKDIR /code
+
+COPY requirements.txt .
+RUN apt-get update && apt-get install -y redis-server && pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD service redis-server start &&     uvicorn app.main:app --host 0.0.0.0 --port 7860 &     celery -A celery_worker worker --loglevel=info &     streamlit run app.py --server.port 7861

README.md

@@ -1,10 +1,34 @@
----
-title: AICEO
-emoji: 🐢
-colorFrom: red
-colorTo: indigo
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🚀 AutoExec AI: Full Stack AI Business Launcher (Streamlit + FastAPI + Celery + LangGraph)
+
+## Overview
+
+This Hugging Face Docker Space contains a unified AI-powered platform to generate and optimize digital businesses autonomously using LLMs.
+
+### What's Inside
+- Streamlit UI
+- FastAPI backend
+- Celery worker (auto-task scheduling)
+- Redis server
+- SQLite memory DB
+- LangGraph JSON config
+- Dashboard for agent logs
+
+## Running Locally
+
+```bash
+uvicorn app.main:app --reload
+streamlit run dashboard.py
+celery -A celery_worker worker --loglevel=info
+```
+
+## Hugging Face Space
+
+Upload the full repo to a **Docker Space** and Hugging Face will build and run it for you.
+
+Make sure to set secrets for:
+```
+GEMINI_API_KEY
+OPENAI_API_KEY
+```
+
+Streamlit runs on port 7861. FastAPI on port 7860.

agents/strategy_agent.py

@@ -0,0 +1,2 @@
+def run_strategy(niche, business_type):
+    return f"LangGraph: StrategyAgent generating ideas for {niche} in {business_type} niche."

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+import requests
+import time
+
+# Gemini + GPT-4 fallback support
+GEMINI_API_KEY = st.secrets.get("GEMINI_API_KEY", "your-gemini-api-key")
+OPENAI_API_KEY = st.secrets.get("OPENAI_API_KEY", "your-openai-api-key")
+
+GEMINI_ENDPOINT = "https://generativelanguage.googleapis.com/v1/models/gemini-1.5-pro:generateContent"
+
+import openai
+openai.api_key = OPENAI_API_KEY
+
+def call_openai(prompt):
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-4",
+            messages=[{"role": "user", "content": prompt}],
+            temperature=0.7
+        )
+        return response['choices'][0]['message']['content']
+    except Exception as e:
+        return f"OpenAI Error: {str(e)}"
+
+def call_gemini(prompt):
+    headers = {"Content-Type": "application/json"}
+    params = {"key": GEMINI_API_KEY}
+    payload = {"contents": [{"parts": [{"text": prompt}]}]}
+    response = requests.post(GEMINI_ENDPOINT, headers=headers, params=params, json=payload)
+    if response.status_code == 200:
+        return response.json()['candidates'][0]['content']['parts'][0]['text']
+    else:
+        return call_openai(prompt)
+
+st.set_page_config(page_title="AutoExec AI", layout="wide")
+st.title("🚀 AutoExec AI: Autonomous AI Business Launcher")
+
+st.sidebar.header("Business Setup")
+niche = st.sidebar.text_input("Niche (e.g. fitness, pets)")
+ad_budget = st.sidebar.slider("Ad Budget per Day", 5, 100, 10)
+business_type = st.sidebar.selectbox("Business Type", ["Dropshipping", "Print-on-Demand", "Newsletter", "Course"])
+platforms = st.sidebar.multiselect("E-Commerce Platforms", ["Shopify", "Gumroad", "WooCommerce"])
+run = st.sidebar.button("Launch")
+
+if run:
+    strategy = call_gemini(f"Give me a viral business idea in the {niche} niche using {business_type}")
+    st.subheader("📈 Strategy")
+    st.markdown(strategy)
+
+    copy = call_gemini(f"Write a product description and landing page for a {niche} {business_type}")
+    st.subheader("📋 Copy")
+    st.markdown(copy)
+
+    ads = call_gemini(f"Create a $ {ad_budget}/day ad campaign for a {niche} product.")
+    st.subheader("💸 Ad Campaign")
+    st.markdown(ads)
+
+    st.success("Business Ready to Deploy")

app/main.py

@@ -0,0 +1,5 @@
+from fastapi import FastAPI
+from app.routes.loopagent import router as loop_router
+
+app = FastAPI(title="AutoExec AI Backend")
+app.include_router(loop_router, prefix="/loopagent", tags=["LoopAgent"])

app/routes/loopagent.py

@@ -0,0 +1,21 @@
+from fastapi import APIRouter
+from datetime import datetime
+from agents.strategy_agent import run_strategy
+from memory.database import init_db, log_action
+
+router = APIRouter()
+
+@router.on_event("startup")
+def startup_event():
+    init_db()
+
+@router.get("/run")
+def run_loopagent():
+    result = run_strategy("fitness", "dropshipping")
+    log_action("StrategyAgent", "generate_business", result)
+    return {
+        "status": "Executed",
+        "agent": "StrategyAgent",
+        "result": result,
+        "timestamp": datetime.utcnow().isoformat()
+    }

celery_worker.py

@@ -0,0 +1,11 @@
+from celery import Celery
+from agents.strategy_agent import run_strategy
+from memory.database import log_action
+
+app = Celery("autoexec_ai", broker="redis://localhost:6379/0")
+
+@app.task
+def scheduled_loop():
+    result = run_strategy("fitness", "dropshipping")
+    log_action("StrategyAgent", "scheduled_run", result)
+    return result

dashboard.py

@@ -0,0 +1,12 @@
+import streamlit as st
+import sqlite3
+import pandas as pd
+
+st.title("🧠 Agent Memory Log Dashboard")
+
+conn = sqlite3.connect("memory.db")
+query = "SELECT * FROM agent_logs ORDER BY timestamp DESC"
+df = pd.read_sql(query, conn)
+conn.close()
+
+st.dataframe(df)

langgraph_config.json

@@ -0,0 +1,54 @@
+{
+  "nodes": {
+    "StrategyAgent": {
+      "type": "llm-tool",
+      "tool": "agents.strategy_agent.run_strategy",
+      "inputs": [
+        "niche",
+        "business_type"
+      ]
+    },
+    "CopyAgent": {
+      "type": "llm-tool",
+      "tool": "agents.copy_agent.generate_copy",
+      "inputs": [
+        "StrategyAgent"
+      ]
+    },
+    "AdAgent": {
+      "type": "llm-tool",
+      "tool": "agents.ad_agent.plan_ads",
+      "inputs": [
+        "StrategyAgent"
+      ]
+    },
+    "LoopAgent": {
+      "type": "rule-engine",
+      "tool": "agents.loop_agent.optimize",
+      "inputs": [
+        "AdAgent",
+        "CopyAgent"
+      ]
+    }
+  },
+  "edges": [
+    [
+      "StrategyAgent",
+      "CopyAgent"
+    ],
+    [
+      "StrategyAgent",
+      "AdAgent"
+    ],
+    [
+      "AdAgent",
+      "LoopAgent"
+    ],
+    [
+      "CopyAgent",
+      "LoopAgent"
+    ]
+  ],
+  "entry_point": "StrategyAgent",
+  "exit_point": "LoopAgent"
+}

memory/database.py

@@ -0,0 +1,26 @@
+import sqlite3
+
+def init_db():
+    conn = sqlite3.connect("memory.db")
+    cursor = conn.cursor()
+    cursor.execute(
+        """CREATE TABLE IF NOT EXISTS agent_logs (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            agent TEXT,
+            action TEXT,
+            result TEXT,
+            timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+        )"""
+    )
+    conn.commit()
+    conn.close()
+
+def log_action(agent, action, result):
+    conn = sqlite3.connect("memory.db")
+    cursor = conn.cursor()
+    cursor.execute(
+        "INSERT INTO agent_logs (agent, action, result) VALUES (?, ?, ?)",
+        (agent, action, result)
+    )
+    conn.commit()
+    conn.close()

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+celery
+redis
+streamlit
+requests
+openai==0.28
+pandas