Create app.py

app.py

@@ -0,0 +1,88 @@
+# app.py
+import time
+import random
+import gradio as gr
+
+# -------------------------
+# Minimal HyperLayer demo
+# - mode: choose demo behavior
+# - latency: simulate zero / low / higher latency for demo
+# - examples: quick tryouts
+# -------------------------
+
+def simulate_processing(prompt: str, mode: str, latency_ms: int):
+    """
+    Simulate HyperLayer AI agent processing.
+    - prompt: user input
+    - mode: 'Explain', 'Summarize', 'Detect Intent', 'Tokenize'
+    - latency_ms: simulated processing time in milliseconds
+    """
+    # simulate processing delay
+    time.sleep(max(0, latency_ms) / 1000.0)
+
+    # create deterministic-ish fake outputs for demo
+    if not prompt.strip():
+        return "Please enter a prompt to see simulated HyperLayer output."
+
+    base = f"[Mode: {mode}]"
+
+    if mode == "Explain":
+        out = f"{base} Explanation: HyperLayer interprets your input and returns a concise, technical summary.\n\nInput: {prompt}\n\nSummary: {prompt[:120]}... (simulated explanation)"
+    elif mode == "Summarize":
+        out = f"{base} Summary: {prompt[:140]}... (simulated short summary)"
+    elif mode == "Detect Intent":
+        intents = ["query_price", "execute_trade", "get_balance", "unknown"]
+        detected = random.choice(intents)
+        out = f"{base} Detected intent = `{detected}` (confidence: {random.uniform(0.6,0.99):.2f})"
+    elif mode == "Tokenize":
+        tokens = prompt.split()
+        out = f"{base} Tokens ({len(tokens)}): " + ", ".join(tokens[:20])
+    else:
+        out = f"{base} Echo: {prompt}"
+
+    # simulate metadata block
+    meta = f"\n\n---\nSimulated latency: {latency_ms} ms • Node: x402-demo-01 • timestamp: {time.strftime('%Y-%m-%d %H:%M:%S')}"
+    return out + meta
+
+
+# Gradio UI details
+title = "🛰️ HyperLayer (x402) — Demo Playground"
+description = """
+**HyperLayer demo** — lightweight simulation of zero-latency AI agent responses on a Solana-native infra.
+Use the controls to pick a mode, set simulated latency and try sample prompts.  
+*This Space shows a demo-only simulation for presentation / hackathon purposes.*
+"""
+
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f"# {title}\n\n{description}")
+
+    with gr.Row():
+        with gr.Column(scale=2):
+            prompt = gr.Textbox(lines=4, label="Prompt / Data stream", placeholder="Type a request for the AI agent...")
+            mode = gr.Dropdown(choices=["Explain", "Summarize", "Detect Intent", "Tokenize", "Echo"], value="Explain", label="Mode")
+            latency = gr.Slider(minimum=0, maximum=2000, step=50, value=50, label="Simulated latency (ms)")
+            run_btn = gr.Button("Run Demo")
+            examples = gr.Examples(
+                examples=[
+                    ["Evaluate arbitrage opportunities between market A and B", "Explain", 50],
+                    ["Summarize last 24h orderbook activity for X token", "Summarize", 120],
+                    ["transfer 0.5 SOL to 0xabc...z", "Detect Intent", 30],
+                    ["tokenize: buy 100 sell 50", "Tokenize", 0],
+                ],
+                inputs=[prompt, mode, latency],
+                label="Try examples"
+            )
+        with gr.Column(scale=1):
+            output = gr.Textbox(lines=12, label="Agent Output (simulated)")
+            gr.Markdown("**Notes**\n- This is a demo to showcase how real-time agent responses would look.\n- Replace simulation with real RPC / model calls for production.")
+
+    def run(prompt_text, mode_val, latency_val):
+        return simulate_processing(prompt_text, mode_val, int(latency_val))
+
+    run_btn.click(fn=run, inputs=[prompt, mode, latency], outputs=[output])
+
+    # add default examples
+    prompt.submit(fn=run, inputs=[prompt, mode, latency], outputs=[output])
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)