mnemosyne-crewai 0.1.0

CrewAI long-term memory adapter for the Mnemosyne memory substrate. Implements the LongTermMemory protocol via duck typing, with per-agent and per-task scoping, hybrid BM25+vector recall, idempotent writes.

mnemosyne-crewai

CrewAI long-term memory adapter for the Mnemosyne memory substrate. Implements the LongTermMemory protocol via duck typing, with per-agent and per-task scoping, hybrid BM25+vector recall, and idempotent writes.

Install

pip install mnemosyne-crewai

Quick start

from mnemosyne_crewai import MnemosyneLongTermMemory, MnemosyneMemoryTool
from crewai import Agent, Crew, Task

# Long-term memory for the crew
ltm = MnemosyneLongTermMemory(container_tag="research-crew")

# Save a memory
ltm.save("GPT-5 is now the default flagship model.", agent="researcher")

# Search
results = ltm.search("latest model", limit=5)
for r in results:
    print(r["content"], r["score"])

# Tool
tool = MnemosyneMemoryTool(container_tag="research-crew")
agent = Agent(
    role="Researcher",
    goal="Find the latest AI news",
    backstory="Expert AI researcher.",
    tools=[tool],
)
task = Task(description="What's the latest model?", agent=agent)
crew = Crew(agents=[agent], tasks=[task])
crew.kickoff()

License

MIT © Geass Labs