Memor is a Python package that implements reproducible structured memory for large language models and autonomous agents. It enables consistent management of conversational history, context, and structured data across LLM interactions. Designed for developers building reliable AI agents, it is fully open source under the MIT license.
In the Memory & skills space, memor takes a focused approach. It focuses on managing and persisting structured conversational history for LLMs in a reproducible way. It is built as an open-source project for developers. The project is open source (MIT). memor is available on the command line and API.
Behind memor is OpenSciLab, and it first shipped in 2024. Development happens publicly on GitHub with 67 stars and 27 commits in the last 90 days. Key capabilities include Structured Memory, Reproducible History, and Conversational Management.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do