> ## Documentation Index
> Fetch the complete documentation index at: https://docs.evermind.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Cloud FAQs

> Frequently asked questions about EverOS Cloud

## General

<AccordionGroup>
  <Accordion title="What core problem does EverOS solve?">
    As LLMs evolve from chatbots into long-term agents, they hit a practical “cognitive wall” driven by:

    * **Limited context windows**: You can’t keep weeks or months of history in the prompt.
    * **Fragmented memory**: Even with retrieval, systems often pull isolated snippets without proper integration, conflict handling, or stable user modeling.

    EverOS argues that the next leap comes from **structured memory organization**, not just longer context. It addresses the inability to integrate fragmented experiences into higher-level semantic structures, enabling agents to maintain consistent personas and reason consistently across time.
  </Accordion>

  <Accordion title="What are the main differences between EverOS and other memory systems?">
    The core difference lies in EverOS's **Lifecycle-based** architecture versus the traditional **Flat Storage + Fragment Retrieval** model.

    * **Others (Mem0, MemOS, Zep)**: Often treat memory as isolated records or focus on storage optimization and fact management.
    * **EverOS**: Simulates a complete biological memory lifecycle: **Episodic Trace Formation**, **Semantic Consolidation**, and **Reconstructive Recollection**. This allows it to actively transform fragmented dialogues into structured knowledge (MemScenes) and dynamic User Profiles, rather than passively storing and retrieving snippets.
  </Accordion>

  <Accordion title="What real-world scenarios is EverOS suitable for?">
    EverOS is ideal for applications requiring long-term consistency and deep user understanding:

    * **Long-term AI companions**: Maintaining coherent personas and evolving user models over weeks or months.
    * **Personalized health & lifestyle management**: Leveraging **Experience-grounded Foresight** to make safe recommendations (e.g., suggesting a mocktail because the system knows the user is currently on antibiotics, despite a past preference for IPA).
    * **Professional collaboration**: Ensuring context consistency across complex, multi-turn interactions.
  </Accordion>
</AccordionGroup>

## Technical & Performance

<AccordionGroup>
  <Accordion title="How does EverOS handle multi-hop and temporal reasoning?">
    EverOS leverages its three-stage lifecycle to handle complex reasoning:

    * **Multi-hop reasoning**: It employs **Semantic Consolidation** to organize MemCells into thematic **MemScenes**. During retrieval (**Reconstructive Recollection**), it uses MemScene-guided retrieval and episode re-ranking to effectively link dispersed information, significantly outperforming baselines.
    * **Temporal reasoning**: It introduces **Prospections** with **Validity Intervals**. The system infers future states (e.g., "flu" is temporary, "graduation" is permanent) and uses **Prospection Filtering** during retrieval to retain only currently valid information ($t_{now} \in [t_{start}, t_{end}]$), ensuring precise temporal reasoning.
  </Accordion>

  <Accordion title="Which benchmarks does EverOS excel in?">
    EverOS achieves State-of-the-Art (SOTA) performance on major long-context and memory benchmarks:

    * **LoCoMo**: **93.05%** overall accuracy (with GPT-4.1-mini), significantly outperforming Zep (85.22%). It shows massive gains in **Multi-hop** (91.84%) and **Temporal** (89.72%) tasks.
    * **LongMemEval**: **83.00%** overall accuracy, surpassing MemOS (77.80%).
    * **PersonaMem v2**: In user profiling tasks, incorporating the consolidated Profile improved accuracy by over 9%, validating its effectiveness in personalization.
  </Accordion>

  <Accordion title="How is memory usage calculated for monthly subscription plans?">
    For our monthly subscription plans, the quota is calculated based on the number of **MemCells** generated from your input messages.

    * **Generation Ratio**: On average, the ratio is approximately **10 raw messages to 1 MemCell**.
    * **Dynamic Segmentation**: EverOS uses **Semantic Boundary Detection** to identify topic shifts and group related turns into a single MemCell.
    * **Efficiency**: This structured approach ensures that each memory unit is contextually coherent and provides a more predictable usage model for long-term agents.

    For a deep dive into how Semantic Boundary Detection outperforms fixed heuristics, please refer to our research paper: [ArXiv:2601.02163](https://arxiv.org/pdf/2601.02163).
  </Accordion>
</AccordionGroup>