This is an early release preview. You may encounter bugs.
Zep logo
Unclaimed

Tool memory

Zep

Examples, framework integrations, and ingestion tooling for the Zep Cloud agent memory platform

Built by Zep

B 75/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full breakdown.
No votes yet

01 / About

What Zep is.

This repository is the companion code for Zep Cloud, a managed agent memory service, rather than the service itself. It collects example applications, agent-framework integration packages, a bulk ingestion pipeline, ontology definitions, and evaluation tooling for teams building memory into their agents with Zep. The temporal knowledge graph engine underneath Zep is published separately as Graphiti.

Zep Cloud is reached through official SDKs for Python (zep-cloud), TypeScript/JavaScript (@getzep/zep-cloud), and Go (zep-go/v3). The service documentation covers threads and messages, adding business data and documents, graph customisation, and a Memory MCP server for use from Claude, ChatGPT, or Cursor.

Integration packages are organised framework-first, then by language, and each one is built, tested, and released on its own. The earlier self-hosted Zep Community Edition is deprecated, unsupported, and kept only under a legacy/ folder.

Features

  • Examples: example apps and snippets in Python, TypeScript, and Go
  • Python integrations: Google ADK, Microsoft Agent Framework, Microsoft AutoGen, AG2, CrewAI, LangGraph, LiveKit, Pydantic AI, and Strands Agents
  • TypeScript integrations: Google ADK, Mastra, and the Vercel AI SDK
  • Go integration: Google ADK
  • zep-ingest: a bulk ingestion pipeline for Slack, documents, email, JSON/CSV, and fact triples
  • Ontology: default ontology definitions for graph structure
  • Agent plugins: Build with Zep for Claude Code, Codex, and Cursor, and Zep Memory for Claude Desktop/Cowork and ChatGPT Work, each in a separate repository
  • Benchmarks: LoCoMo and LongMemEval memory benchmarks
  • Evaluation harness: zep-eval-harness for testing ingestion and retrieval

02 / Discussion CREDIBILITY-GATED

Discussion

Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.

  • No discussions yet.

04 / Build

Build with Zep.

Browse the catalogue for frameworks, tools, and harnesses, each scored on real GitHub credibility.

Get Zep →

Browse the catalogue