my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: AgentOps
#3	---
#4
#5	Integrate [Mem0](https://github.com/mem0ai/mem0) with [AgentOps](https://agentops.ai), a comprehensive monitoring and analytics platform for AI agents. This integration enables automatic tracking and analysis of memory operations, providing insights into agent performance and memory usage patterns.
#6
#7	## Overview
#8
#9	1. Automatic monitoring of Mem0 operations and performance metrics
#10	2. Real-time tracking of memory add, search, and retrieval operations
#11	3. Analytics dashboard with memory usage patterns and insights
#12	4. Error tracking and debugging capabilities for memory operations
#13
#14	## Prerequisites
#15
#16	Before setting up Mem0 with AgentOps, ensure you have:
#17
#18	1. Installed the required packages:
#19	```bash
#20	pip install mem0ai agentops python-dotenv
#21	```
#22
#23	2. Valid API keys:
#24	- [AgentOps API Key](https://app.agentops.ai/dashboard/api-keys)
#25	- OpenAI API Key (for LLM operations)
#26	- [Mem0 API Key](https://app.mem0.ai/dashboard/api-keys) (optional, for cloud operations)
#27
#28	## Basic Integration Example
#29
#30	The following example demonstrates how to integrate Mem0 with AgentOps monitoring for comprehensive memory operation tracking:
#31
#32	```python
#33	#Import the required libraries for local memory management with Mem0
#34	from mem0 import Memory, AsyncMemory
#35	import os
#36	import asyncio
#37	import logging
#38	from dotenv import load_dotenv
#39	import agentops
#40	import openai
#41
#42	load_dotenv()
#43	#Set up environment variables for API keys
#44	os.environ["AGENTOPS_API_KEY"] = os.getenv("AGENTOPS_API_KEY")
#45	os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
#46
#47	#Set up the configuration for local memory storage and define sample user data.
#48	local_config = {
#49	"llm": {
#50	"provider": "openai",
#51	"config": {
#52	"model": "gpt-4.1-nano-2025-04-14",
#53	"temperature": 0.1,
#54	"max_tokens": 2000,
#55	},
#56	}
#57	}
#58	user_id = "alice_demo"
#59	agent_id = "assistant_demo"
#60	run_id = "session_001"
#61
#62	sample_messages = [
#63	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#64	{"role": "assistant", "content": "How about a thriller? They can be quite engaging."},
#65	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#66	{
#67	"role": "assistant",
#68	"content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future.",
#69	},
#70	]
#71
#72	sample_preferences = [
#73	"I prefer dark roast coffee over light roast",
#74	"I exercise every morning at 6 AM",
#75	"I'm vegetarian and avoid all meat products",
#76	"I love reading science fiction novels",
#77	"I work in software engineering",
#78	]
#79
#80	#This function demonstrates sequential memory operations using the synchronous Memory class
#81	def demonstrate_sync_memory(local_config, sample_messages, sample_preferences, user_id):
#82	"""
#83	Demonstrate synchronous Memory class operations.
#84	"""
#85
#86	agentops.start_trace("mem0_memory_example", tags=["mem0_memory_example"])
#87	try:
#88
#89	memory = Memory.from_config(local_config)
#90
#91	result = memory.add(
#92	sample_messages, user_id=user_id, metadata={"category": "movie_preferences", "session": "demo"}
#93	)
#94
#95	for i, preference in enumerate(sample_preferences):
#96	result = memory.add(preference, user_id=user_id, metadata={"type": "preference", "index": i})
#97
#98	search_queries = [
#99	"What movies does the user like?",
#100	"What are the user's food preferences?",
#101	"When does the user exercise?",
#102	]
#103
#104	for query in search_queries:
#105	results = memory.search(query, user_id=user_id)
#106
#107	if results and "results" in results:
#108	for j, result in enumerate(results['results']):
#109	print(f"Result {j+1}: {result.get('memory', 'N/A')}")
#110	else:
#111	print("No results found")
#112
#113	all_memories = memory.get_all(user_id=user_id)
#114	if all_memories and "results" in all_memories:
#115	print(f"Total memories: {len(all_memories['results'])}")
#116
#117	delete_all_result = memory.delete_all(user_id=user_id)
#118	print(f"Delete all result: {delete_all_result}")
#119
#120	agentops.end_trace(end_state="success")
#121	except Exception as e:
#122	agentops.end_trace(end_state="error")
#123
#124	# Execute sync demonstrations
#125	demonstrate_sync_memory(local_config, sample_messages, sample_preferences, user_id)
#126
#127	```
#128
#129	For detailed information on this integration, refer to the official [Agentops Mem0 integration documentation](https://docs.agentops.ai/v2/integrations/mem0).
#130
#131
#132	## Key Features
#133
#134	### 1. Automatic Operation Tracking
#135
#136	AgentOps automatically monitors all Mem0 operations:
#137
#138	- Memory Operations: Track add, search, get_all, delete operations and much more
#139	- Performance Metrics: Monitor response times and success rates
#140	- Error Tracking: Capture and analyze operation failures
#141
#142	### 2. Real-time Analytics Dashboard
#143
#144	Access comprehensive analytics through the AgentOps dashboard:
#145
#146	- Usage Patterns: Visualize memory usage trends over time
#147	- User Behavior: Analyze how different users interact with memory
#148	- Performance Insights: Identify bottlenecks and optimization opportunities
#149
#150	### 3. Session Management
#151
#152	Organize your monitoring with structured sessions:
#153
#154	- Session Tracking: Group related operations into logical sessions
#155	- Success/Failure Rates: Track session outcomes for reliability monitoring
#156	- Custom Metadata: Add context to sessions for better analysis
#157
#158	## Best Practices
#159
#160	1. Initialize Early: Always initialize AgentOps before importing Mem0 classes
#161	2. Session Management: Use meaningful session names and end sessions appropriately
#162	3. Error Handling: Wrap operations in try-catch blocks and report failures
#163	4. Tagging: Use tags to organize different types of memory operations
#164	5. Environment Separation: Use different projects or tags for dev/staging/prod
#165
#166	<CardGroup cols={2}>
#167	<Card title="CrewAI Integration" icon="users" href="/integrations/crewai">
#168	Monitor multi-agent CrewAI systems
#169	</Card>
#170	<Card title="LangChain Integration" icon="link" href="/integrations/langchain">
#171	Track LangChain agent performance
#172	</Card>
#173	</CardGroup>
#174
#175

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public