How MemOS Works

Memory Recall

Memory recall finds the content that is most relevant, trustworthy, and suitable to inject into context when a user makes a request.

1. What Is Memory Recall

Memory recall is the core ability of MemOS when reading memories. After a user sends a new request, MemOS combines the input, conversation context, filters, and memory states to find memories that can help the model complete the current task.

The goal is not to return all history. It is to put the most useful facts, preferences, tool experience, skill clues, or knowledge content into the limited context window.


2. Why Context Alone Is Not Enough

If a model only relies on the current conversation window, three problems appear:

  • Users must repeat themselves: preferences, background, and long-term matters cannot continue naturally.
  • Historical information is easily lost: earlier conversations, cross-session behavior, and tool results do not automatically appear in the current context.
  • Input becomes overloaded: adding all raw history is costly and makes answers less stable.

The value of memory recall is to turn long-term memories into usable input for the current task when needed.


3. What Recall Returns

Memory categoryTypical use
Fact memoriesAdd clear facts such as user identity, long-term matters, and business status
Preference memoriesContinue the user's tone, style, choice habits, or constraints
Tool memoriesHelp Agents select the right tool and invocation pattern in similar tasks
Skill memoriesReuse execution steps and constraints distilled from multi-turn tasks
Knowledge contentProvide documents, images, multimodal content, or knowledge base evidence

Recall results usually include source, time, type, tags, confidence, and status. Developers can further filter, rank, or decide whether to inject them into downstream models.


4. Key Stages in Recall

StageRole
Understand the requestDecide what background, preferences, or knowledge the current input needs
Filter the scopeLimit candidate memories by user, conversation, time, tags, type, and other conditions
Retrieve candidatesFind semantically relevant or condition-matched memories from the memory base
Rank and selectCombine relevance, confidence, freshness, and status to choose more reliable results
Govern injectionControl which memories enter model context, avoiding excessive, outdated, or non-compliant content

Together, these stages determine whether recalled memories are actually useful. Too little recall leaves the model without background; too much recall adds noise and cost.


5. Next Steps

Memory Filters

Use filters to control recall scope and reduce irrelevant memories

Search Memory

View how to integrate memory recall