my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Camel AI
#3	description: "Plug Mem0 cloud memory into Camel's agents with the built‑in Mem0Storage."
#4	partnerBadge: "Camel AI"
#5	---
#6
#7	# Camel AI integration
#8
#9	Connect Camel's agent framework to Mem0 so every agent can persist and recall conversation context across sessions with minimal setup.
#10
#11	<Info>
#12	Prerequisites
#13	- Mem0: `MEM0_API_KEY` (or self-hosted endpoint), `pip install mem0ai`
#14	- Camel AI: `pip install camel-ai` (requires Python 3.9+)
#15	- Optional: OpenAI API key if you run LLM-backed agents
#16	</Info>
#17
#18	<Note>Camel provides a Python SDK today. A TypeScript path is not available yet.</Note>
#19
#20	## Configure credentials
#21
#22	<Tabs>
#23	<Tab title="Mem0">
#24	<Steps>
#25	<Step title="Export your API key">
#26	```bash
#27	export MEM0_API_KEY="sk-..."
#28	```
#29	</Step>
#30	<Step title="(Self-host) Point to your Mem0 API">
#31	```bash
#32	export MEM0_BASE_URL="https://your-mem0-domain"
#33	```
#34	</Step>
#35	</Steps>
#36	</Tab>
#37	<Tab title="Camel">
#38	<Steps>
#39	<Step title="Install Camel with Mem0 dependency">
#40	```bash
#41	pip install "camel-ai>=0.2.0" mem0ai
#42	```
#43	</Step>
#44	<Step title="(Optional) Add your model credentials">
#45	```bash
#46	export OPENAI_API_KEY="sk-openai..."
#47	```
#48	</Step>
#49	</Steps>
#50	</Tab>
#51	</Tabs>
#52
#53	<Tip>
#54	Mem0Storage reads `MEM0_API_KEY` automatically. Pass `api_key` explicitly only when you need to override the environment.
#55	</Tip>
#56
#57	## Wire Mem0 into a Camel agent
#58
#59	<Steps>
#60	<Step title="Create a Mem0-backed memory store">
#61	```python
#62	import os
#63	from camel.storages import Mem0Storage
#64
#65	mem0_store = Mem0Storage(
#66	api_key=os.environ.get("MEM0_API_KEY"),
#67	agent_id="travel_agent",
#68	user_id="alice",
#69	metadata={"source": "camel-demo"},
#70	)
#71	```
#72	</Step>
#73	<Step title="Attach it to Camel memory">
#74	```python
#75	from camel.memories import ChatHistoryMemory, ScoreBasedContextCreator
#76	from camel.utils import OpenAITokenCounter
#77	from camel.types import ModelType
#78
#79	memory = ChatHistoryMemory(
#80	context_creator=ScoreBasedContextCreator(
#81	token_counter=OpenAITokenCounter(ModelType.GPT_4O_MINI),
#82	token_limit=1024,
#83	),
#84	storage=mem0_store,
#85	agent_id="travel_agent",
#86	)
#87	```
#88	</Step>
#89	<Step title="Let your agent read and write Mem0">
#90	```python
#91	from camel.agents import ChatAgent
#92	from camel.messages import BaseMessage
#93
#94	agent = ChatAgent(
#95	system_message=BaseMessage.make_assistant_message(
#96	role_name="Agent",
#97	content="You are a helpful travel assistant. Reuse stored memories."
#98	)
#99	)
#100
#101	agent.memory = memory
#102
#103	response = agent.step(
#104	BaseMessage.make_user_message(
#105	role_name="User",
#106	content="I prefer boutique hotels in Paris."
#107	)
#108	)
#109
#110	print(response.msgs[0].content)
#111	```
#112	</Step>
#113	</Steps>
#114
#115	<Info icon="check">
#116	Run `python camel_mem0_demo.py` (or the snippet above in a REPL). You should see the agent respond and the memory persisted to Mem0. Re-running with a new prompt should include the stored preference.
#117	</Info>
#118
#119	## Verify the integration
#120
#121	- Mem0 dashboard shows new memories under `agent_id=travel_agent` and `user_id=alice`.
#122	- `mem0_store.load()` returns the records you just wrote.
#123	- Camel agent replies reference prior user preferences on subsequent runs.
#124
#125	## Troubleshooting
#126
#127	- Missing MEM0_API_KEY — set `export MEM0_API_KEY="sk-..."` or pass `api_key` into `Mem0Storage`.
#128	- No memories returned — ensure `agent_id`/`user_id` in your query match what you used when writing.
#129	- Network errors to Mem0 — if self-hosting, set `MEM0_BASE_URL` to your deployment URL.
#130
#131	<CardGroup cols={2}>
#132	<Card
#133	title="Memory types in Mem0"
#134	description="Choose between chat history and semantic search for your Camel agents."
#135	icon="sparkles"
#136	href="/core-concepts/memory-types"
#137	/>
#138	<Card
#139	title="Try LangChain next"
#140	description="Wire the same Mem0 project into LangChain workflows."
#141	icon="rocket"
#142	href="/integrations/langchain"
#143	/>
#144	</CardGroup>
#145

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public