DakeraMemoryAdapter
Defined in the factories module.AI Agent Memory adapter that wraps the Dakera SDK to implement
MemoryProtocol.
Dakera (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
Dict[str, Any]
required
No description available.
Methods
store_short_term()
Store content in short-term (
working) memory.search_short_term()
Search short-term (
working) memory.store_long_term()
Store content in long-term (
episodic) memory.search_long_term()
Search long-term (
episodic) memory.get_all_memories()
Return all memories for the agent (no embedding required).
delete_memory()
Delete a specific memory by id. Returns True on success.
delete_memories()
Delete multiple memories by id. Returns the number deleted.
reset_short_term()
Clear all short-term (
working) memory for the agent.reset_long_term()
Clear all long-term (
episodic) memory for the agent.Source
View on GitHub
praisonaiagents/memory/adapters/factories.py at line 568