Compartment is a Python package that offers a high-security, fully offline, and encrypted vector database designed specifically for AI agents. It implements the Model Context Protocol (MCP) to enable secure semantic search and memory retrieval while keeping all data local. Ideal for privacy-conscious developers building autonomous agents or RAG systems that must remain air-gapped or fully encrypted.
In the AI & ML space, Compartment takes a focused approach. It focuses on storing and retrieving sensitive agent memory without relying on cloud services or exposing data to third parties. Compartment is an open-source project aimed at AI developers. The project is open source (Open Source). The product ships for the command line, and it can be self-hosted.
Behind Compartment is MaxFreedomPollard, and the product first shipped in 2026. The project is developed in the open on GitHub with 101 commits in the last 90 days. Among its 5 catalogued features are Encrypted Vector Memory, Offline Storage, and Semantic Search. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
