my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Collaborative Task Assistant
#3	description: "Coordinate multi-user projects with shared memories and roles."
#4	---
#5
#6
#7	## Overview
#8
#9	Build a multi-user collaborative chat or task management system with Mem0. Each message is attributed to its author, and all messages are stored in a shared project space. Mem0 makes it easy to track contributions, sort and group messages, and collaborate in real time.
#10
#11	## Setup
#12
#13	Install the required packages:
#14
#15	```bash
#16	pip install openai mem0ai
#17	```
#18
#19	## Full Code Example
#20
#21	```python
#22	from openai import OpenAI
#23	from mem0 import Memory
#24	import os
#25	from datetime import datetime
#26	from collections import defaultdict
#27
#28	# Set your OpenAI API key
#29	os.environ["OPENAI_API_KEY"] = "sk-your-key"
#30
#31	# Shared project context
#32	RUN_ID = "project-demo"
#33
#34	# Initialize Mem0
#35	mem = Memory()
#36
#37	class CollaborativeAgent:
#38	def __init__(self, run_id):
#39	self.run_id = run_id
#40	self.mem = mem
#41
#42	def add_message(self, role, name, content):
#43	msg = {"role": role, "name": name, "content": content}
#44	self.mem.add([msg], run_id=self.run_id, infer=False)
#45
#46	def brainstorm(self, prompt):
#47	# Get recent messages for context
#48	memories = self.mem.search(prompt, run_id=self.run_id, limit=5)["results"]
#49	context = "\n".join(f"- {m['memory']} (by {m.get('actor_id', 'Unknown')})" for m in memories)
#50	client = OpenAI()
#51	messages = [
#52	{"role": "system", "content": "You are a helpful project assistant."},
#53	{"role": "user", "content": f"Prompt: {prompt}\nContext:\n{context}"}
#54	]
#55	reply = client.chat.completions.create(
#56	model="gpt-4.1-nano-2025-04-14",
#57	messages=messages
#58	).choices[0].message.content.strip()
#59	self.add_message("assistant", "assistant", reply)
#60	return reply
#61
#62	def get_all_messages(self):
#63	return self.mem.get_all(run_id=self.run_id)["results"]
#64
#65	def print_sorted_by_time(self):
#66	messages = self.get_all_messages()
#67	messages.sort(key=lambda m: m.get('created_at', ''))
#68	print("\n--- Messages (sorted by time) ---")
#69	for m in messages:
#70	who = m.get("actor_id") or "Unknown"
#71	ts = m.get('created_at', 'Timestamp N/A')
#72	try:
#73	dt = datetime.fromisoformat(ts.replace('Z', '+00:00'))
#74	ts_fmt = dt.strftime('%Y-%m-%d %H:%M:%S')
#75	except Exception:
#76	ts_fmt = ts
#77	print(f"[{ts_fmt}] [{who}] {m['memory']}")
#78
#79	def print_grouped_by_actor(self):
#80	messages = self.get_all_messages()
#81	grouped = defaultdict(list)
#82	for m in messages:
#83	grouped[m.get("actor_id") or "Unknown"].append(m)
#84	print("\n--- Messages (grouped by actor) ---")
#85	for actor, mems in grouped.items():
#86	print(f"\n=== {actor} ===")
#87	for m in mems:
#88	ts = m.get('created_at', 'Timestamp N/A')
#89	try:
#90	dt = datetime.fromisoformat(ts.replace('Z', '+00:00'))
#91	ts_fmt = dt.strftime('%Y-%m-%d %H:%M:%S')
#92	except Exception:
#93	ts_fmt = ts
#94	print(f"[{ts_fmt}] {m['memory']}")
#95	```
#96
#97	## Usage
#98
#99	```python
#100	# Example usage
#101	agent = CollaborativeAgent(RUN_ID)
#102	agent.add_message("user", "alice", "Let's list tasks for the new landing page.")
#103	agent.add_message("user", "bob", "I'll own the hero section copy.")
#104	agent.add_message("user", "carol", "I'll choose product screenshots.")
#105
#106	# Brainstorm with context
#107	print("\nAssistant reply:\n", agent.brainstorm("What are the current open tasks?"))
#108
#109	# Print all messages sorted by time
#110	agent.print_sorted_by_time()
#111
#112	# Print all messages grouped by actor
#113	agent.print_grouped_by_actor()
#114	```
#115
#116	## Key Points
#117
#118	- Each message is attributed to a user or agent (actor)
#119	- All messages are stored in a shared project space (`run_id`)
#120	- You can sort messages by time, group by actor, and format timestamps for clarity
#121	- Mem0 makes it easy to build collaborative, attributed chat/task systems
#122
#123	## Conclusion
#124
#125	Mem0 enables fast, transparent collaboration for teams and agents, with full attribution, flexible memory search, and easy message organization.
#126
#127	---
#128
#129	<CardGroup cols={2}>
#130	<Card title="Partition Memories by Entity" icon="layers" href="/cookbooks/essentials/entity-partitioning-playbook">
#131	Learn how to scope memories across users, agents, and runs for team workflows.
#132	</Card>
#133	<Card title="Support Inbox with Mem0" icon="headset" href="/cookbooks/operations/support-inbox">
#134	Apply collaborative memory patterns to customer support scenarios.
#135	</Card>
#136	</CardGroup>
#137

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public