klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Improve readme structure (#1654)

Browse Source
This commit is contained in:
Taranjeet Singh
2024-08-06 21:08:17 -07:00
committed by GitHub
parent 9f6ec325fb
commit de7ee38e45
2 changed files with 57 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
README.md
View File

@@ -1,30 +1,57 @@
<p align="center">
<a href="https://github.com/mem0ai/mem0">
<img src="docs/images/banner.png" width="800px" alt="Mem0 Logo">
</a>
<h3 align="center">Mem0</h3>
<p align="center">
The Memory Layer for Personalized AI.
<br />
<a href="https://mem0.ai"><strong>Learn more »</strong></a>
<br />
<br />
<a href="https://mem0.ai/discord">Discord</a>
·
<a href="https://mem0.ai">Website</a>
·
<a href="https://github.com/mem0ai/mem0/issues">Issues</a>
</p>
</p>
<p align="center">
<a href="https://mem0.ai/slack">
<img src="https://img.shields.io/badge/slack-mem0-brightgreen.svg?logo=slack" alt="Mem0 Slack">
</a>
<a href="https://mem0.ai/discord">
<img src="https://dcbadge.vercel.app/api/server/6PzXDgEjG5?style=flat" alt="Mem0 Discord">
</a>
<a href="https://pepy.tech/project/mem0ai">
<img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads" >
</a>
<a href="https://www.ycombinator.com/companies/mem0">
<img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24">
</a>
<a href="https://x.com/mem0ai">
<img src="https://img.shields.io/twitter/follow/mem0ai" alt="Mem0 Twitter">
</a>
<a href="https://www.ycombinator.com/companies/mem0"><img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24"></a>
<a href="https://www.npmjs.com/package/mem0ai"><img src="https://img.shields.io/npm/v/mem0ai?style=flat-square&label=npm+mem0ai" alt="mem0ai npm package"></a>
<a href="https://pypi.python.org/pypi/mem0ai"><img src="https://img.shields.io/pypi/v/mem0ai.svg?style=flat-square&label=pypi+mem0ai" alt="mem0ai Python package on PyPi"></a>
<a href="https://mem0.ai/email"><img src="https://img.shields.io/badge/substack-mem0-brightgreen.svg?logo=substack&label=mem0+substack" alt="Mem0 newsletter"></a>
</p>
# Mem0: The Memory Layer for Personalized AI
Mem0 provides an intelligent, adaptive memory layer for Large Language Models (LLMs), enhancing personalized AI experiences by retaining and utilizing contextual information across diverse applications. This enhanced memory capability is crucial for applications ranging from customer support and healthcare diagnostics to autonomous systems and personalized content recommendations, allowing AI to remember user preferences, adapt to individual needs, and continuously improve over time.
[Mem0](https://mem0.ai) enhances AI agents and Large Language Models (LLMs) with an intelligent memory layer. By retaining and utilizing contextual information, Mem0 enables more personalized and effective AI interactions across various applications. Whether you're building customer support chatbots, AI assistants, or autonomous systems, Mem0 helps your AI remember user preferences, adapt to individual needs, and continuously improve over time.
## 🚀 Quickstart
Use cases enabled by Mem0 include:
### Installation
- **Personalized Learning Assistants**: Enhance learning experiences with tailored content recommendations and progress tracking.
- **Customer Support AI Agents**: Provide context-aware assistance by remembering past interactions and user preferences.
- **Healthcare Assistants**: Keep track of patient history, treatment plans, and medication schedules for personalized care.
- **Virtual Companions**: Build deeper relationships with users by remembering personal details and past conversations.
- **Productivity Tools**: Streamline workflows by remembering user habits, frequently used documents, and task history.
- **Gaming AI**: Create immersive gaming experiences by adapting game environments based on player choices and progress.
## Get Started
The simplest way to set up Mem0 is to create a managed deployment with Mem0 Cloud. This hosted solution offers a hassle-free experience with automatic updates, advanced analytics, and dedicated support. [Sign up](https://app.mem0.ai/) for Mem0 Cloud to get started.
If you prefer to install and manage Mem0 yourself, you can use the open-source Mem0 package. Read the [manual installation instructions](#install) below to get started with Mem0 on your machine.
## Manual Installation Instructions <a name="install"></a>
The Mem0 package can be installed directly from pip command in the terminal.
@@ -32,9 +59,12 @@ The Mem0 package can be installed directly from pip command in the terminal.
pip install mem0ai
```
### Basic Usage (Open Source)
Alternatively, you can use Mem0 in one click using the hosted platform [here](https://app.mem0.ai/).
### Basic Usage
Mem0 supports a variety of LLMs, with details available in our [Supported LLMs documentation](https://docs.mem0.ai/llms). By default, Mem0 comes equipped with `gpt-4o`. To use it, simply set the keys in the environment variables.
Mem0 supports various LLMs, details of which can be found in our docs, checkout [Supported LLMs](https://docs.mem0.ai/llms). By default, Mem0 is equipped with ```gpt-4o```, and to use it, you need to set the keys in the environment variable.
```python
import os
@@ -92,37 +122,10 @@ history = m.history(memory_id=<memory_id_1>)
# Logs corresponding to memory_id_1 --> {'prev_value': 'Working on improving tennis skills and interested in online courses for tennis.', 'new_value': 'Likes to play tennis on weekends' }
```
### Mem0 Platform
```python
from mem0 import MemoryClient
client = MemoryClient(api_key="your-api-key") # get api_key from https://app.mem0.ai/
# Store messages
messages = [
{"role": "user", "content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."},
{"role": "assistant", "content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."}
]
result = client.add(messages, user_id="alex")
print(result)
# Retrieve memories
all_memories = client.get_all(user_id="alex")
print(all_memories)
# Search memories
query = "What do you know about me?"
related_memories = client.search(query, user_id="alex")
# Get memory history
history = client.history(memory_id="m1")
print(history)
```
> [!TIP]
> If you are looking for a hosted version and don't want to setup the infrastucture yourself, checkout [Mem0 Platform Docs](https://docs.mem0.ai/platform/quickstart) to get started in minutes.
> If you are looking for a hosted version and don't want to setup the infrastucture yourself, checkout [Mem0 Cloud Docs](https://app.mem0.ai/) to get started in minutes.
## 🔑 Core Features
## Core Features
- **Multi-Level Memory**: User, Session, and AI Agent memory retention
- **Adaptive Personalization**: Continuous improvement based on interactions
@@ -130,11 +133,11 @@ print(history)
- **Cross-Platform Consistency**: Uniform behavior across devices
- **Managed Service**: Hassle-free hosted solution
## 📖 Documentation
## Documentation
For detailed usage instructions and API reference, visit our documentation at [docs.mem0.ai](https://docs.mem0.ai).
## 🔧 Advanced Usage
## Advanced Usage
For production environments, you can use Qdrant as a vector store:
@@ -154,47 +157,18 @@ config = {
m = Memory.from_config(config)
```
## 🗺️ Roadmap
## Roadmap
- Integration with various LLM providers
- Support for LLM frameworks
- Integration with AI Agents frameworks
- Customizable memory creation/update rules
- Hosted platform support
## 💰 Pricing
Choose the Mem0 plan that best fits your needs:
### Open Source (Self-hosted)
Perfect for developers and small teams who want full control over their infrastructure.
### Pro (Hosted)
Ideal for growing businesses that need a reliable, managed solution with generous free usage. Try the platform [here](https://app.mem0.ai)
### Enterprise (Hosted)
Designed for large organizations with advanced security, compliance, and scalability needs.
| Feature | Open Source | Pro | Enterprise |
|---------|-------------|-----|------------|
| Hosting | Self-hosted | Hosted | Hosted |
| API Calls | Unlimited | 100K free/month | Custom limits |
| Support | Community | Email | Dedicated support |
| Updates | Manual | Automatic | Automatic |
| SSO | ❌ | ❌ | ✅ |
| Audit Logs | ❌ | ❌ | ✅ |
| Custom Integrations | ❌ | ❌ | ✅ |
| SLA | ❌ | ❌ | ✅ |
| Advanced Analytics | ❌ | Basic | Advanced |
| Multi-region Deployment | ❌ | ❌ | ✅ |
[Contact us](mailto:taranjeet@mem0.ai) for Enterprise pricing and custom solutions.
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=mem0ai/mem0&type=Date)](https://star-history.com/#mem0ai/mem0&Date)
## 🙋‍♂️ Support
## Support
Join our Slack or Discord community for support and discussions.
If you have any questions, feel free to reach out to us using one of the following methods:
@@ -204,9 +178,14 @@ If you have any questions, feel free to reach out to us using one of the followi
- [Follow us on Twitter](https://x.com/mem0ai)
- [Email us](mailto:founders@mem0.ai)
## 📝 License
## Contributors
This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
We value and appreciate the contributions of our community. Special thanks to our contributors for helping us improve Mem0.
> [!NOTE]
> The Mem0 repository now also includes the Embedchain project. We continue to maintain and support Embedchain ❤️. You can find the Embedchain codebase in the [embedchain](https://github.com/mem0ai/mem0/tree/main/embedchain) directory.
<a href="https://github.com/mem0ai/mem0/graphs/contributors">
<img src="https://contrib.rocks/image?repo=mem0ai/mem0" />
</a>
## License
This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.

BIN
docs/images/banner.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 177 KiB

After

Width:  |  Height:  |  Size: 1.2 MiB