MemTensor/MemOS

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

AI agentsTypeScript#agent#llm#memory#long-term-memory#memory-management

2.3 Steady Magnitude out of 10. Star growth looks organic. Data as of September 18, 2026.

Open on Seismograph Open on GitHub

About the project

MemOS is a memory operating system for LLMs and AI agents: a unified API to store, retrieve and manage long-term memory (text, images, tool traces, personas) with hybrid retrieval and cross-task skill reuse.

Useful for

Add long-term memory to an agent via Cloud API or local plugin
Connect memory to DeepSeek Harness, Hermes Agent or OpenClaw
Self-host the memory service on Neo4j and Qdrant via docker compose

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

22 stars so far today, about 27 expected by the end of the day.
Over the last two days the pace is 1.8× that of the previous week and a half.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 11,457
Stars in a day: 27
Forks: 1,046
Issues and pull requests: 2,279
Watchers: 52
Language: TypeScript
License: Apache-2.0
Latest release: memos-local-plugin-v2.0.19 · September 8, 2026
Created: July 6, 2025
Last push: September 18, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 17, 2026GitHub Trending TypeScript today: #8, +29 stars
September 16, 2026GitHub Trending TypeScript today: #8, +39 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/MemTensor/MemOS.svg?lang=en)](https://gitnova.dev/en/r/MemTensor/MemOS)

Similar projects

8.8
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

BreakoutAI agentsPython+2,396 stars in a day
8.5
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…

BreakoutAI agentsTypeScript+1,762 stars in a day
7.9
hypit-ai/hypit
Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.

BreakoutAI agentsTypeScript+813 stars in a day
7.9
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.

BreakoutAI agentsTypeScript+731 stars in a day
7.0
korcarc/text-humanizer
A Python tool that rewrites AI-generated text through an LLM and translation pipeline to bypass detectors like Turnitin and GPTZero. Supports 8 languages and requires a DeepSeek API key.

Early signalAI agentsPython+292 stars in a day
6.8
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

BreakoutAI agentsGo+413 stars in a day