Zep is the enterprise context layer for reliable agents. Zep gives agents governed access to company knowledge, and skills that Zep builds from agent tasks.
| Part of Zep | What it does | Docs | Examples |
|---|---|---|---|
| Context Lake | Unifies business data into governed Context Graphs for agents | Context Lake | Context Lake harnesses |
| Zep Agent Skills | Turns the tasks of your agents into skills that the agents follow | Agent Skills | Agent Skills harnesses |
Agents connect to Zep through MCP or the Zep SDKs. Read more at www.getzep.com.
This repository is not Zep's product or service. It contains example code, agent harnesses, framework integrations, and tools for agents that use Zep Cloud.
To use Zep Cloud, sign up at www.getzep.com and read the documentation at help.getzep.com. Zep's official SDKs are:
- Python:
pip install zep-cloud - TypeScript/JavaScript:
npm install @getzep/zep-cloud - Go:
go get github.com/getzep/zep-go/v4
Looking for the open-source temporal knowledge graph framework that powers Zep? See Graphiti.
examples/README.md lists all of the agent harnesses and SDK
snippets.
agent-with-zepandagent-with-zep-adk: reference agents that retrieve from a Context Graph with tools, on PydanticAI and Google ADK.langgraph-agent,openai-agents-sdk, andtypescript/eve: agents with agent memory on other frameworks.
agent-skills-banking: the full Agent Skills loop with PydanticAI.python/agent-skills-frameworks: LangGraph, Google ADK, and Claude Agent SDK.typescript/agent-skills-frameworks: Mastra, OpenAI Codex SDK, and Eve.
| Project / directory | Description |
|---|---|
examples/ |
Agent harnesses, example apps, and snippets in Python, TypeScript, and Go |
integrations/ |
Agent-framework integration packages |
ingestion/ |
zep-ingest, a bulk data ingestion pipeline (Slack, documents, email, JSON/CSV, fact triples) |
ontology/ |
Default ontology definitions |
| Build with Zep | Agent plugin for Claude Code, Codex, and Cursor (separate repository) |
| Zep Memory | Agent plugin for Claude Desktop/Cowork and ChatGPT Work (separate repository) |
benchmarks/ |
Agent memory benchmarks (LoCoMo, LongMemEval) |
zep-eval-harness/ |
Evaluation harness for ingestion and retrieval |
Framework integration packages live under integrations/, organized
framework-first then language: integrations/<framework>/<language>/. Each package is built,
tested, and released independently.
- Python: Google ADK, Microsoft Agent Framework, Microsoft AutoGen, AG2, CrewAI, LangGraph, LiveKit, Pydantic AI, Strands Agents
- TypeScript: Google ADK, Mastra, Vercel AI SDK
- Go: Google ADK
See integrations/README.md for packages, release status, and
links, and integrations/CLAUDE.md for conventions.
We welcome contributions. See CONTRIBUTING.md for guidelines covering code, documentation, bug reports, and community examples.