Back to Gap Map Product / UX / Agent memory & context stores

MemoryOS

BAI-LAB
open source / Overall score: 2.6

MemoryOS manages a personalized agent's memory the way an operating system manages storage, moving dialogue from a short-term queue into mid-term topic segments and promoting often revisited segments into a long-term user profile and knowledge base. It ships as a Python library, an MCP server, a ChromaDB variant and a playground. BAI-LAB at the Beijing University of Posts and Telecommunications builds it.

The memoryos package on PyPI is MemTensor's MemOS, a different project; this entry declares memoryos-pro, the name the README installs.

Openness

5 high confidence
5.0
license
Apache-2.0 (library, MCP server, ChromaDB variant and playground)
source
public
core features withheld
no — the 73-path tree at 587ed77 carries one root Apache-2.0 LICENSE over the library, MCP, ChromaDB, playground and evaluation directories, with no ee/, enterprise/, commercial/ or proprietary/ path; an academic lab's release

MemoryOS is published under Apache 2.0, and every variant, the library, MCP server, ChromaDB build and playground, runs from the published source against the user's own model keys. It is a university lab's research release, and its hosted platform is an invitation-only demo of the same open playground.

Adoption

1 low confidence
1.0

Adoption is read from PyPI downloads of memoryos-pro, the package the README installs; the similarly named memoryos package belongs to MemTensor's MemOS and is not counted. Installs from source, the MCP server and the Docker set-up do not appear in this figure.

Capability

5 medium confidence
5.0

MemoryOS covers the whole cycle: it summarizes dialogue into segments, promotes the ones a user keeps returning to into a profile and knowledge base, and lets cold segments cool and drop out as capacity fills. Its forgetting is driven by access and recency rather than by any check that a fact is still true.

Verified 2026-11-20, except some scores, still awaiting re-confirmation