LlamaIndex | Spectron

LlamaIndex builds RAG and agent applications in Python. Spectron gives a LlamaIndex agent long-term memory that persists across sessions. There is no dedicated adapter. The Python SDK (surrealdb) exposes the memory operations you wrap as FunctionTools.

Note

This is an integration guide. It wires the Spectron SDK into LlamaIndex's tool interface; adapt to your installed LlamaIndex version.

Installation

pip install llama-index surrealdb

export SPECTRON_ENDPOINT="https://api.spectron.example"
export SPECTRON_CONTEXT="acme-prod"
export SPECTRON_API_KEY="sk-spec-..."

Memory as tools

Wrap the client in FunctionTools and hand them to an agent:

import os
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai import OpenAI
from surrealdb import Spectron

memory = Spectron(
    endpoint=os.environ["SPECTRON_ENDPOINT"],
    context=os.environ["SPECTRON_CONTEXT"],
    api_key=os.environ["SPECTRON_API_KEY"],
)
scope = ["org/acme/user/alice"]

def remember(text: str) -> str:
    """Store a durable fact for later recall."""
    memory.remember(text, scope=scope)
    return "stored"

def recall(query: str) -> str:
    """Retrieve relevant memory for a query."""
    return memory.query_context(query, k=8, scope=scope)

agent = FunctionAgent(
    llm=OpenAI(model="gpt-4o"),
    tools=[FunctionTool.from_defaults(remember), FunctionTool.from_defaults(recall)],
    system_prompt="Use recall before answering and remember anything worth keeping.",
)

Recall for retrieval

Because Spectron already ranks across semantic, lexical, graph, and temporal signals server-side, call query_context (or recall) directly rather than wiring it into a VectorStoreIndex:

block = memory.query_context("what is the return policy?", k=8, scope=["org/acme"])
# inject `block` into your prompt, or return it from a query tool

Note

LlamaIndex's built-in Memory stores chat history in a SQL database. Spectron is a separate, hosted memory tier with server-side extraction and hybrid retrieval. Use it when memory should be shared across agents and survive process restarts.

Scope per user

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

Next steps

Python SDK: the full client surface
JavaScript SDK: for LlamaIndex.TS