Python SDK

# Initialize client (only needs API key)
client = MemoryStackClient(api_key="your_api_key")

# Research agent gathers information
client.add(
    "Research finding: 73% of users prefer AI recommendations",
    metadata={
        "agent_id": "researcher",
        "team": "editorial",
        "project": "content_creation",
        "scope": "team"  # Share with editorial team
    }
)

# Writer accesses team research
team_research = client.search("research finding", limit=10)

# Writer creates draft
client.add(
    "Draft: AI Recommendations article ready for review",
    metadata={
        "agent_id": "writer",
        "team": "editorial",
        "project": "content_creation",
        "scope": "team"
    }
)

# Editor checks team drafts
drafts = client.search("draft status")

# Editor provides feedback
client.add(
    "Feedback: Add more concrete examples in section 2",
    metadata={
        "agent_id": "editor",
        "team": "editorial",
        "project": "content_creation",
        "scope": "team"
    }
)

from crewai import Agent, Task, Crew, Tool
from memorystack import MemoryStackClient

# Initialize Memorystack client (only needs API key)
memory = MemoryStackClient(api_key="your_api_key")

# Create memory tools for agents
def store_memory(content: str, agent_id: str):
    """Store a memory with agent context"""
    return memory.add(content, metadata={
        "agent_id": agent_id,
        "project": "research_team"
    })

def search_memory(query: str):
    """Search memories"""
    return memory.search(query, limit=10)

memory_store_tool = Tool(
    name="store_memory",
    description="Store information in memory",
    func=lambda x: store_memory(x, "researcher")
)

memory_search_tool = Tool(
    name="search_memory",
    description="Search for information in memory",
    func=search_memory
)

# Define agents with memory capabilities
researcher = Agent(
    role="Research Analyst",
    goal="Gather and analyze market data",
    backstory="Expert in market research and data analysis",
    tools=[memory_store_tool, memory_search_tool],
    verbose=True
)

writer = Agent(
    role="Content Writer",
    goal="Create engaging content from research",
    backstory="Skilled writer with data storytelling expertise",
    tools=[memory_search_tool],
    verbose=True
)

# Define tasks
research_task = Task(
    description="Research AI market trends and store findings",
    agent=researcher,
    expected_output="Market research summary with key statistics"
)

writing_task = Task(
    description="Write article using research findings from memory",
    agent=writer,
    expected_output="1000-word article on AI market trends"
)

# Create crew
crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, writing_task],
    verbose=True
)

# Execute workflow
result = crew.kickoff()
print(result)