TRACES · POLICIES · CRYSTALLIZED SKILLS
MemOS
@MEMTENSOR
Let the Agent's memory grow layer by layer from original trajectories into strategies, world models and reusable skills.
MemOS organizes memory into L1 trajectories, L2 strategies, L3 world models, and crystallized Skills, allowing the Agent to not only recall the past, but also turn experiences into subsequent abilities.
Project address (can be copied to AI):https://github.com/MemTensor/MemOS
PROJECT INTRO
Project introduction
MemOS 2.0 provides persistent capture, hybrid retrieval, deduplication and local Memory Viewer, and layers the experience into trajectories, strategies, world models and reusable Skills.
The project supports feedback-driven retrieval, skill evolution, multi-agent collaboration and DeepSeek Harness, Hermes, OpenClaw plug-ins, and thus belongs to both memory and AI subjectivity.
- Suitable for:Developers who want Agent to transform long-term experience into reusable strategies and skills.
- Platform:Python, self-hosting and multi-Agent plug-in ecosystem.
- Usage:Deploy the MemOS core or install the corresponding platform plug-in.
- License:Apache-2.0。
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...