I built EasyMemory, an open-source Python library that provides a fully local-first memory layer for chatbots and agent-based systems, with no cloud dependency.
Most existing agent memory solutions rely on third-party services or embeddings-only retrieval. EasyMemory is designed as a local, modular system to experiment with how agents store, structure, and retrieve information beyond pure vector search.
Key features
• Automatic conversation persistence
• Hybrid retrieval: embeddings + keyword search + graph-style links
• Supports PDF, TXT, DOCX, and Markdown
• Optional integrations with Slack, Notion, and Google Drive
• MCP server for connecting local or remote LLMs
The goal is to provide a flexible foundation for exploring different memory patterns locally, without locking into a single retrieval strategy or external service.
Feedback and comparisons with other approaches to agent memory, RAG, or long-term context management are very welcome.