MemTensor
company · ChinaScores
1 product on the map — 1 open.
Openness
5 high confidence- license
- Apache-2.0 (the MemOS service, scheduler and memory modules)+MIT (the memos-local-plugin agent memory core)
- source
- public
- core features withheld
- no — the 2,061-path tree at 3a16e5f holds the Python service, scheduler, memory modules, Docker and Helm deployment and the local plugin with no ee/, enterprise/, commercial/ or proprietary/ path; the one cloud plugin in it is a client of MemOS Cloud
- commercial
- MemOS Cloud and MemMate Enterprise
MemOS's memory service, scheduler and local agent plugin are published in full, and the service self-hosts with Docker beside its graph and vector stores. MemTensor sells MemOS Cloud and an enterprise agent platform as separate hosted products rather than features withheld from the code.
- https://memos.openmem.net recorded 2026-11-20
The homepage lists MemOS Cloud, MemOS Lite, the "MemOS Official Open Source" service, MemMate Enterprise and the Memmy personal assistant as separate products.
- https://raw.githubusercontent.com/MemTensor/MemOS/main/apps/memos-local-plugin/package.json recorded 2026-11-20
The local plugin manifest declares "@memtensor/memos-local-plugin" with license "MIT" and ships its core, server and adapters as TypeScript source.
- https://raw.githubusercontent.com/MemTensor/MemOS/main/LICENSE recorded 2026-11-20
The root LICENSE is the Apache License 2.0 text with "Copyright 2025 - Present MemTensor Research".
- https://raw.githubusercontent.com/MemTensor/MemOS/main/pyproject.toml recorded 2026-11-20
The manifest builds the MemoryOS package with license "Apache-2.0".
- https://raw.githubusercontent.com/MemTensor/MemOS/main/README.md recorded 2026-11-20
The README's quick start offers four entry points, the hosted Cloud API, a self-hosted service started with docker compose, a Cloud plugin and a local plugin, and documents self-hosting as "Teams on own infra" with data on "Your servers".
Adoption
2 low confidenceAdoption is read from monthly downloads of MemoryOS on PyPI and @memtensor/memos-local-plugin on npm, the two packages that install MemOS itself, most of them for the local plugin. Docker deployments, MemOS Cloud and the cloud plugin pass through neither package and are not counted.
- https://api.npmjs.org/downloads/point/last-month/@memtensor/memos-local-plugin recorded 2026-11-20
11,394 downloads of @memtensor/memos-local-plugin on npm between 2026-10-20 and 2026-11-18.
- https://pypi.org/pypi/MemoryOS/json recorded 2026-11-20
PyPI lists MemoryOS, "Intelligence Begins with Memory", with its repository, documentation and issues at github.com/MemTensor/MemOS.
- https://pypistats.org/api/packages/memoryos/recent recorded 2026-11-20
1,742 downloads of MemoryOS on PyPI in the trailing 30 days.
- https://registry.npmjs.org/@memtensor/memos-local-plugin/latest recorded 2026-11-20
The npm package is the Reflect2Evolve memory plugin with layered memory, skill crystallization and three-tier retrieval for OpenClaw, Hermes Agent and DeepSeek Harness; it declares no repository field.
Capability
5 medium confidenceMemOS performs every part of the cycle itself: it extracts memories from raw input, merges and corrects them in the background, forgets and decays them over time, and keeps several typed memories in a graph.
- https://raw.githubusercontent.com/MemTensor/MemOS/main/docs/en/open_source/modules/mem_scheduler.md recorded 2026-11-20
The scheduler guide says it "Executes read/write, compression, forgetting, and type conversion operations on three-layer memory (Working/Long-term/User)" and runs reorganization and merge tasks.
- https://raw.githubusercontent.com/MemTensor/MemOS/main/docs/en/open_source/modules/memories/overview.md recorded 2026-11-20
The memory module overview describes automatic extraction, organizing and linking, and lists preference memory with "Preference deduplication and conflict detection" and "Temporal decay support".
- https://raw.githubusercontent.com/MemTensor/MemOS/main/docs/en/open_source/modules/memories/tree_textual_memory.md recorded 2026-11-20
The tree textual memory guide extracts structured memories with an LLM into graph nodes typed WorkingMemory, LongTermMemory or UserMemory, each activated, archived or deleted.
- https://raw.githubusercontent.com/MemTensor/MemOS/main/README.md recorded 2026-11-20
The README describes a unified memory API structured as a graph, multi-cube knowledge bases isolated across users and agents, asynchronous ingestion via MemScheduler, and memory feedback and correction.