OpenAI Integration

Add persistent memory to OpenAI API calls with one line.

Setup


pip install unforget[openai]

Usage


from openai import AsyncOpenAI
from unforget import MemoryStore
from unforget.integrations.openai import wrap_openai
 
store = MemoryStore("postgresql://...")
await store.initialize()
 
client = wrap_openai(
    AsyncOpenAI(),
    store,
    org_id="acme",
    agent_id="support-bot",
    auto_recall=True,          # inject memories into system prompt
    auto_ingest=True,          # save conversation after response
    inject_tools=True,         # add memory tools to tool list
    inject_instructions=True,  # add memory usage hints
)
 
# Use normally — memory is handled transparently
response = await client.chat.completions.create(
    messages=[{"role": "user", "content": "What was my last order?"}],
    model="gpt-4o",
)

What happens under the hood

Before the call: auto_recall fetches relevant memories and prepends them to the system prompt
During the call: Agent can use memory_store, memory_search, memory_list, memory_forget, memory_update tools
After the call: auto_ingest saves the conversation to memory