Zep Community Edition v1.0.2 is a deprecated, unsupported self-hosted memory service for developers building AI agents and conversational assistants. This legacy edition uses the Apache 2.0 license. It turns chat history into a knowledge graph that records how facts change over time, so an assistant can distinguish a user's current preferences from earlier ones.
Its graph engine, Graphiti, keeps historical context and tracks when facts become valid or stop being valid. Memory can belong to a chat session, a user, or a group, which lets applications retain personal context across conversations or share organizational knowledge. Retrieval combines keyword, semantic, and graph search to find facts relevant to the current conversation. Zep prepares facts and entity summaries in the background rather than using another agent during retrieval.
The server runs through Docker on your own infrastructure, but model processing depends on separate LLM and embedding services. It supports local servers and hosted providers with OpenAI-compatible APIs; Anthropic can connect through LiteLLM. Where conversation data goes therefore depends on the services you connect. Community Edition doesn't include a local embedding service. Zep Cloud is a separate managed offering with additional dialog classification and structured data extraction.
Python and TypeScript SDKs connect the memory service to applications, with integrations including LangChain, LangGraph, and Microsoft Autogen. This edition uses APIs rather than a web UI. It supports deleting user memory, and its optional usage telemetry can be disabled.
Claim this page and we'll verify you by hand. Zep Community Edition (legacy) gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Zep Community Edition (legacy)?Promote it
Something wrong or outdated on this page?
31.3KUpdated 1 day agoApache-2.0
Docker#Hybrid search#Knowledge graphs#llama.cpp backend
Graphiti is a self-hosted Python framework for developers building AI agents that need to remember changing facts. It builds knowledge graphs from conversations, structured records and unstructured text, so an agent can query current information or recover what was true earlier. It's open source under Apache 2.0.
31.2KUpdated 21 hours agoApache-2.0
Docker · Web#Knowledge graphs#MCP#Multi-user access
29.9KUpdated 1 day ago
Docker · JetBrains#Code execution#MCP#Persistent memory
28.4KUpdated 21 hours ago
Web#Human approval#LLM tracing#MCP
4.4KUpdated 19 hours agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
90.7KUpdated 1 week ago
Windows#Git integration#Knowledge graphs#MCP
MCP Reference Servers is a collection of locally run examples for developers building connections between AI applications and external tools or data. Maintained by the MCP steering group, the servers demonstrate the protocol and its SDKs. They're educational implementations, so developers should assess security requirements before using them in production.
Cognee gives AI agents persistent memory across sessions, connecting documents, code, and conversations in a searchable knowledge graph. It's for developers who want agents to retain project context and teams whose knowledge sits across tickets, discussions, and repositories. The Python package is open source under Apache 2.0.
Serena is a locally run MCP toolkit that gives AI coding agents access to code structure: functions, classes and the references between them. It's for developers who want their agent to find and change specific parts of a codebase without reading whole files or relying on text matching. It requires an LLM client and works with Claude Code, Codex, OpenCode, Cursor and OpenWebUI.
Mastra is a TypeScript framework for developers building AI agents and applications on their own servers or inside existing web apps. Its server runs locally or as a standalone deployment; Mastra Cloud provides a hosted alternative. Model routing connects to providers such as OpenAI, Anthropic, and Gemini, so running the framework locally doesn't keep those model requests on your machine.
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.