Hyperspell | Respan Docs

Set up Respan

Sign up — Create an account at platform.respan.ai
Create an API key — Generate one on the API keys page
Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

Use AI

Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.

1 {
2   "mcpServers": {
3     "respan-docs": {
4       "url": "https://mcp.respan.ai/mcp/docs"
5     }
6   }
7 }

Hyperspell is a memory management platform for AI applications, providing persistent memory and context management for LLM-powered products.

Hyperspell + Respan gives you full observability over your AI application’s memory operations, letting you trace how context is stored, retrieved, and used across conversations.

Setup

Install dependencies

$ pip install hyperspell respan-tracing

Configure environment variables

.env

$ HYPERSPELL_API_KEY="YOUR_HYPERSPELL_API_KEY"
$ RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ RESPAN_BASE_URL="https://api.respan.ai/api"

Use Hyperspell with Respan tracing

1 import os
2 from hyperspell import Hyperspell
3 from respan_tracing.decorators import workflow, task
4 from respan_tracing.main import RespanTelemetry
5 
6 # Initialize Respan Telemetry
7 os.environ["RESPAN_API_KEY"] = "YOUR_RESPAN_API_KEY"
8 k_tl = RespanTelemetry()
9 
10 # Initialize Hyperspell client
11 client = Hyperspell(api_key=os.environ["HYPERSPELL_API_KEY"])
12 
13 @task(name="store_memory")
14 def store_memory(user_id: str, content: str):
15     """Store a memory for a user."""
16     return client.memories.create(
17         user_id=user_id,
18         content=content
19     )
20 
21 @task(name="retrieve_memory")
22 def retrieve_memory(user_id: str, query: str):
23     """Retrieve relevant memories for a user."""
24     return client.memories.search(
25         user_id=user_id,
26         query=query
27     )
28 
29 @workflow(name="memory_workflow")
30 def memory_workflow():
31     store_memory("user_123", "I prefer Python over JavaScript.")
32     memories = retrieve_memory("user_123", "programming language preference")
33     return memories
34 
35 if __name__ == "__main__":
36     result = memory_workflow()
37     print(result)

View your traces

After running your workflow, you can see the memory operations traced in the Traces page on Respan.