EverMemOS: 提供 AI 代理專用的開源記憶體作業系統,但相比 supermemory 的託管 API,需要更多的自行架構與設定。 EverMemOS 每月有 24,237 次造訪,月增率 +12%,定價模式為免費試用、免費。supermemory 每月有 156,579 次造訪,成長率 -7.7%,定價模式為需聯絡報價。

EverMemOS (also described as EverOS) by EverMind is a memory operating system for AI agents and applications. It adds persistent, self-evolving memory on top of stateless LLMs: agents store multimodal content, retrieve it through hybrid mRAG, distill repeated patterns into reusable Skills, and keep facts in sync over time.
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | evermind.ai | supermemory.ai |
| 定價模式 | 免費試用、免費 | 需聯絡報價 |
| 每月造訪次數 | 2.42萬 (24,237) | 15.66萬 (156,579) |
| 月流量變化量 | +2599 (+12%) | -1.3萬 (-7.7%) |
| 主要市場與市佔 | 🇺🇸 美國 (34.6%) | 🇺🇸 美國 (46.2%) |
| 每月直接造訪 | 1.46萬 | 7.12萬 |
| 使用者評分 | 4.4 | 4.5 |
| 支援平台 | 網站 | 網站 |

EverMemOS (also described as EverOS) by EverMind is a memory operating system for AI agents and applications. It adds persistent, self-evolving memory on top of stateless LLMs: agents store multimodal content, retrieve it through hybrid mRAG, distill repeated patterns into reusable Skills, and keep facts in sync over time.
Multimodal retrieval and ingestion via a single API, covering PDFs, images, Word files, spreadsheets, decks, emails, HTML and URLs.
Agent trajectories are recorded as Cases, distilled into reusable Skills, and reused so performance improves over time.
Inspect, manage and edit user, group and agent memories in a dedicated Memory Bank interface.
EverMind publishes reproducible results on LoCoMo, LongMemEval and AMA alongside its memory research.

為 AI Agent 提供持久記憶與持續學習的記憶引擎
專用模型在既有上下文上執行萃取、合併、推論與遺忘,讓記憶圖譜持續優化,而不只是不斷累積。
每條學習結果都與相關實體、來源與時刻建立關聯,不僅儲存內容,還保留帶有時間維度的關係圖。
記憶位於模型廠商之外,透過 API、SDK、外掛與 MCP 使用,上下文可跨模型與工具遷移。
相關記憶在請求時以 token 形式注入提示詞,讓 Agent 獲得貼合需求的上下文,而無需攜帶無限增長的對話紀錄。
免費 / 開源ModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.
免費 / 開源ModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.

專項更強Focuses on tool integrations and authentication for agents, complementing memory engines rather than storing cross-session context.
免費 / 開源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
免費 / 開源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
專項更強提供企業級的可擴展向量搜尋與 RAG 儲存,但缺乏 supermemory 的自動化代理記憶體圖譜抽象功能。
免費 / 開源Provides high-performance open-source vector similarity search, requiring custom schema design for agent memory management.