Zep — servicio de memoria para apps LLM con resumen integrado

Quick Start — Python SDK

La API clave es memory.get(session_id).context — devuelve una única cadena preformateada que contiene el resumen actualizado, los hechos extraídos del usuario y los últimos N mensajes. Inyéctala en tu system prompt y el resto de tu código LLM se queda igual.

# pip install zep-python openai
from zep_python.client import Zep
from openai import OpenAI

zep = Zep(api_key="z_...")  # or base_url="http://localhost:8000" for self-host
oai = OpenAI()

user_id, session_id = "william", "s_2026_04_14"
zep.user.add(user_id=user_id, email="william@example.com")
zep.memory.add_session(session_id=session_id, user_id=user_id)

def chat(message: str) -> str:
    zep.memory.add(session_id=session_id,
                   messages=[{"role": "user", "content": message}])

    # Zep returns pre-formatted context: summary + facts + recent messages
    ctx = zep.memory.get(session_id=session_id).context

    resp = oai.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {"role": "system", "content": ctx},
            {"role": "user", "content": message},
        ],
    )
    answer = resp.choices[0].message.content

    zep.memory.add(session_id=session_id,
                   messages=[{"role": "assistant", "content": answer}])
    return answer

print(chat("I'm planning a trip to Tokyo in May"))
print(chat("What should I pack for that trip?"))

Características clave

Comparación

Casos de uso

Precios y licencia

Activos relacionados en TokRepo

Zep — Long-Term Memory for AI Agents and Assistants

Production memory layer for AI assistants. Zep stores conversation history, extracts facts, builds knowledge graphs, and provides temporal-aware retrieval for LLMs.

Apache Zeppelin — Web-Based Notebook for Interactive Data Analytics

Apache Zeppelin is a web-based notebook that supports multiple language backends including Spark, SQL, Python, and Scala, enabling interactive data exploration, visualization, and collaboration.

Zephyr RTOS — Scalable Real-Time Operating System for IoT Devices

Build connected embedded systems on a vendor-neutral real-time OS supporting 700+ boards. Zephyr provides a small-footprint kernel with POSIX compatibility, networking stacks, Bluetooth, and security primitives for resource-constrained devices.

Zephyr RTOS — Scalable Real-Time Operating System for IoT

A small, scalable real-time operating system for resource-constrained devices supporting multiple architectures, backed by the Linux Foundation.

Preguntas frecuentes