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

# Dakera Memory Adapter • AI Agent SDK

> DakeraMemoryAdapter: Memory adapter that wraps the Dakera SDK to implement ``MemoryProtocol``.

# DakeraMemoryAdapter

> Defined in the [**factories**](../modules/factories) module.

<Badge color="blue">AI Agent</Badge>

Memory adapter that wraps the Dakera SDK to implement `MemoryProtocol`.

Dakera ([https://dakera.ai](https://dakera.ai)) is a self-hosted memory server that provides
persistent, decay-weighted vector recall across sessions: memories are
importance-scored and decay over time, so stale context stops competing
with fresh, relevant facts. All memories are scoped by `agent_id`.

Unlike a flat vector store, Dakera has a first-class `memory_type` field,
so this adapter maps PraisonAI's two tiers onto distinct Dakera types
(short-term -> `"working"`, long-term -> `"episodic"` by default),
keeping recency-heavy scratch context separate from durable knowledge.

Also implements the optional `DeletableMemoryProtocol` (`delete_memory` /
`delete_memories`) and `ResettableMemoryProtocol` (`reset_short_term` /
`reset_long_term`).

## Constructor

<ParamField query="dakera_config" type="Dict[str, Any]" required={true}>
  No description available.
</ParamField>

## Methods

<CardGroup cols={2}>
  <Card title="store_short_term()" icon="function" href="../functions/DakeraMemoryAdapter-store_short_term">
    Store content in short-term (`working`) memory.
  </Card>

  <Card title="search_short_term()" icon="function" href="../functions/DakeraMemoryAdapter-search_short_term">
    Search short-term (`working`) memory.
  </Card>

  <Card title="store_long_term()" icon="function" href="../functions/DakeraMemoryAdapter-store_long_term">
    Store content in long-term (`episodic`) memory.
  </Card>

  <Card title="search_long_term()" icon="function" href="../functions/DakeraMemoryAdapter-search_long_term">
    Search long-term (`episodic`) memory.
  </Card>

  <Card title="get_all_memories()" icon="function" href="../functions/DakeraMemoryAdapter-get_all_memories">
    Return all memories for the agent (no embedding required).
  </Card>

  <Card title="delete_memory()" icon="function" href="../functions/DakeraMemoryAdapter-delete_memory">
    Delete a specific memory by id. Returns True on success.
  </Card>

  <Card title="delete_memories()" icon="function" href="../functions/DakeraMemoryAdapter-delete_memories">
    Delete multiple memories by id. Returns the number deleted.
  </Card>

  <Card title="reset_short_term()" icon="function" href="../functions/DakeraMemoryAdapter-reset_short_term">
    Clear all short-term (`working`) memory for the agent.
  </Card>

  <Card title="reset_long_term()" icon="function" href="../functions/DakeraMemoryAdapter-reset_long_term">
    Clear all long-term (`episodic`) memory for the agent.
  </Card>
</CardGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/memory/adapters/factories.py#L568">
  `praisonaiagents/memory/adapters/factories.py` at line 568
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Memory Concept" icon="brain" href="/docs/docs/concepts/memory" />

  <Card title="Memory Overview" icon="database" href="/docs/docs/memory/overview" />

  <Card title="Memory Configuration" icon="gear" href="/docs/docs/configuration/memory-config" />

  <Card title="Session Resume" icon="rotate-right" href="/docs/docs/memory/session-resume" />
</CardGroup>