The official Python library for the OpenAI REST API, with sync and async clients and typed request and response models.
getzep/zep-python
Python SDK for Zep Cloud, a context engineering platform that lets AI assistants recall past chat history and business data.
- Stars
- 210
- Forks
- 32
- Open issues
- 10
- Last commit
- 2 days ago
What is it?
Zep is a context engineering platform for AI assistant apps. It persists chat histories, asynchronously generates summaries and other artifacts from them, and embeds messages and summaries so the app can search for relevant past context.
This package is the official Python client for the Zep Cloud APIs. It exposes synchronous and async clients, typed responses, paginated list methods, streaming queries, and configurable retries, timeouts and custom httpx clients. The library is generated programmatically, and the project notes that direct contributions to the code will be overwritten on the next generated release.
A typical prompt built with Zep combines a few recent messages, a summary of earlier conversation, and summaries or messages retrieved from the wider session history.
Key features
- 01Persists chat histories and generates summaries asynchronously.
- 02Embeds messages and summaries for semantic search over past context.
- 03Provides sync and async clients with typed responses.
- 04Supports paginated listing and streaming query responses.
- 05Offers configurable retries, timeouts and custom httpx clients.
Use cases
- Giving a customer support agent memory of earlier conversations with the same user.
- Injecting relevant past messages or summaries into an LLM prompt.
- Building agents that reason over both chat history and business data.
Quick start
- 1
Install the Zep Cloud SDK from PyPI
pip install zep-cloud - 2
Create a client with your Zep Project API key and call the API
Things to know
- Requires a Zep Cloud project API key, so it depends on a hosted paid service.
- The SDK code is generated programmatically, so direct contributions are generally not merged.
Topics
FAQ
- What is zep-python?
- Python SDK for Zep Cloud, a context engineering platform that lets AI assistants recall past chat history and business data. Zep is a context engineering platform for AI assistant apps. It persists chat histories, asynchronously generates summaries and other artifacts from them, and embeds messages and summaries so the app can search for relevant past context.
- Is zep-python free to use? What license does it have?
- zep-python is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is zep-python still maintained?
- Actively maintained. The last commit to zep-python was on Oct 20, 2026.
- What can I use zep-python for?
- Giving a customer support agent memory of earlier conversations with the same user. Injecting relevant past messages or summaries into an LLM prompt. Building agents that reason over both chat history and business data.
- How do I install zep-python?
- Install the Zep Cloud SDK from PyPI: pip install zep-cloud Create a client with your Zep Project API key and call the API
- Where can I get zep-python?
- The source code and installation instructions are on GitHub: https://github.com/getzep/zep-python
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Python SDK for building agents on Claude Code, with query(), an interactive client, in-process custom tools and hooks.
A CLI that scans your codebase and generates compact AI context files (CLAUDE.md, .cursorrules, AGENTS.md) so coding assistants spend fewer tokens exploring the project.
Official Python SDK for building Model Context Protocol servers and clients that connect LLM applications to tools, data and prompts.
A spec-driven development workflow for AI coding assistants that agree on proposals, specs and tasks before any code is written.
An agile AI-driven development method that guides AI coding tools through planning, specs, and build steps for software projects of any size.