AgentOps

AgentOps monitors AI agents: session replay, LLM cost tracking, and tool-call telemetry across most agent frameworks. It is complementary to SurrealDB Agent Memory: AgentOps observes the run; SurrealDB Agent Memory provides the memory. This guide uses both together with the Python SDK (surrealdb).

Installation

pip install agentops openai
pip install --pre 'surrealdb[memory]'

export AGENTOPS_API_KEY="..."
export AGENT_MEMORY_ENDPOINT="https://api.spectron.example"
export AGENT_MEMORY_CONTEXT="acme-prod"
export AGENT_MEMORY_API_KEY="sk-spec-..."

Instrument the agent, remember with Agent Memory

agentops.init() auto-instruments supported LLM and framework calls. Use the SurrealDB Agent Memory client for recall and storage inside the instrumented run:

import os
import agentops
from openai import OpenAI
from surrealdb.memory import Memory

agentops.init(os.environ["AGENTOPS_API_KEY"])

llm = OpenAI()
memory = Memory(
    endpoint=os.environ["AGENT_MEMORY_ENDPOINT"],
    context=os.environ["AGENT_MEMORY_CONTEXT"],
    api_key=os.environ["AGENT_MEMORY_API_KEY"],
)
scope = ["org/acme/user/alice"]

def answer(user_message: str) -> str:
    block = memory.query_context(user_message, k=8, lens=scope)

    completion = llm.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": f"You are a helpful assistant.\n\n## Memory\n{block}"},
            {"role": "user", "content": user_message},
        ],
    )
    reply = completion.choices[0].message.content

    memory.remember_many(
        [{"role": "user", "content": user_message}, {"role": "assistant", "content": reply}],
        scopes=scope,
    )
    return reply

The model call is captured in the AgentOps session automatically. To attribute the SurrealDB Agent Memory operations too, wrap them in an AgentOps operation span (@agentops.operation) so recall and storage appear in the session timeline.

Scope per user

Pass a scope on every SurrealDB Agent Memory call to isolate memory. A scope is a slash path or an array of paths, for example ["org/acme/user/alice"]. Register paths with agent-memory scopes create before first use.

Next steps

• •

  Python SDK: the full client surface

• •

  Agent frameworks: AgentOps also instruments CrewAI, AutoGen, and others that have first-party SurrealDB Agent Memory adapters