PraisonAI + Awareness Memory
Add persistent, cross-session memory to your PraisonAI agents. Tools and workflows remember past context across sessions.
Installation
pip install awareness-memory-cloud[praisonai]
Quick Start
from memory_cloud import MemoryCloudClient
from memory_cloud.integrations.praisonai import MemoryCloudPraisonAI
import openai
# Local mode (no API key needed)
client = MemoryCloudClient(mode="local")
mc = MemoryCloudPraisonAI(client=client) # memory_id auto-managed
# Cloud mode (team collaboration, semantic search, multi-device sync)
client = MemoryCloudClient(base_url="https://awareness.market/api/v1", api_key="YOUR_API_KEY")
mc = MemoryCloudPraisonAI(client=client, memory_id="memory_123")
# Wrap the LLM client for auto-recall + auto-capture
mc.wrap_llm(openai.OpenAI())
# Or get tool dicts for PraisonAI agent config
tools = mc.build_tools()
Integration Patterns
Pattern 1: Interceptor (Zero-Code Memory)
mc.wrap_llm(openai.OpenAI())
# All LLM calls within your PraisonAI agents now have cross-session memory
Pattern 2: Tool Registration
tools = mc.build_tools()
# Use in PraisonAI agent config
agent_config = {
"tools": tools,
# ...
}
Pattern 3: Direct API
result = mc.awareness_recall("What decisions were made about the database schema?")
mc.awareness_record("Migrated from MySQL to PostgreSQL for JSON support")
Use Cases
- PraisonAI agents with cross-session memory — knowledge persists between runs
- Tool-based memory access — agents can read and write memory via registered tools
- Multi-agent workflows — shared memory across agent teams
Multi-User / Multi-Role
mc_analyst = MemoryCloudPraisonAI(
client=client, memory_id="memory_123",
default_metadata={"agent_role": "analyst", "user_id": "alice"}
)
Example
See examples/e2e_praisonai_cloud.py in the SDK repository for a complete end-to-end example.
Next Steps
- SDK Usage Guide — Interceptor pattern and full API reference
- LangChain Integration — Use with LangChain
- CrewAI Integration — Use with CrewAI
- AutoGen Integration — Use with AutoGen