## Polywrap Newsletters: AI and LLMs Updates - June 2023

---

**1.** ***Introducing VOYAGER: An Open-Ended Embodied Agent with Large Language Models***
The Minecraft-based AI, VOYAGER, leverages large language models to develop a set of growing skills and implement complex behaviors. Its robust learning abilities make it a standout project in the AI landscape. Read more about this project [here](https://voyager.minedojo.org/assets/documents/voyager.pdf).

**2.** ***Gorilla: Bridging the Gap between LLMs and APIs***
Gorilla is an innovative solution teaching large language models how to accurately invoke APIs. With a growing store of APIs, Gorilla aims to enhance the capability of LLMs significantly. Find out more about this project [here](https://arxiv.org/abs/2305.15334).

**3.** ***LLMs as Tool Makers***
Discover how large language models can become tool makers with a closed-loop framework, enabling them to create their own reusable tools. It's an intriguing approach that offers cost-effective operations without sacrificing the quality of generated tools. Learn more about this project [here](https://arxiv.org/pdf/2305.17126.pdf).

**4.** ***ReWOO: Efficient Augmented Language Models through Reasoning-Observation Decoupling***
ReWOO is a new paradigm that reduces computation complexity by separating the reasoning process of LLMs from external observations. With proven enhancements across several NLP benchmarks, ReWOO shows a promising future. Learn more about ReWOO [here](https://arxiv.org/pdf/2305.18323.pdf). And the [Code Repository](https://github.com/billxbf/ReWOO)


**5.** ***FastChat's OpenAI-compatible API Server by lmsys.org***
FastChat's OpenAI-compatible API server offers an open-source alternative for applications built on OpenAI APIs. This makes it possible to port applications to use open-source alternatives without modifying the code. Read more about this announcement on their [blog post](https://lmsys.org/blog/2023-06-09-api-server/).

**6.** ***Orca: The New Open-Source LLM Model***
Orca, an open-source LLM model, has shown impressive performance, surpassing ChatGPT-3.5 turbo. Remarkably, this can be achieved on consumer computers with no internet connection and around 8GB of hard drive space. Learn more about Orca from this [video](https://youtu.be/Dt_UNg7Mchg) and on [Twitter](https://twitter.com/BrianRoemmele/status/1667207113767292930).

---

### **Exploring the AutoGPT Clones**

There has been a surge of LLMs, also known as AutoGPT clones, that are designed to emulate OpenAI's GPT technology. Here are a few noteworthy projects:

**1.** ***Fusionate.ai***: Fusionate.ai is an AI platform built with the mission to democratize the power of AI for everyone. This agent is closed source. Learn more [here](https://www.fusionate.ai/).

**2.** ***Reworkd AgentGPT***: Reworkd is an AI software company focusing on providing businesses with customizable AI chatbots. This client is open source. Learn more [here](https://agentgpt.reworkd.ai/). And look at their [Github](https://github.com/reworkd/AgentGPT) which has become very popular.


**3.** ***Godmode***: Godmode is another AI chatbot, using LLMs to provide sophisticated conversational abilities. Learn more [here](https://godmode.space/).

**4.** ***SuperAGI***: SuperAGI is an open-source LLM that runs locally. The system has a very complete user interface and integrates with external tools. Learn more about SuperAGI from this [video](https://www.youtube.com/watch?v=Unj5NLNTkLY) and on [GitHub](https://github.com/TransformerOptimus/SuperAGI).


**5.** ***LangChain Python Agents***: LangChain provides an open-source Python library for developing advanced AI agents. It has an extensive framework for different kinds of Agents and implementations. This doesnt have a Frontend to work with, rather it relies on jupyter notebooks to test the agent. Learn more [here](https://python.langchain.com/en/latest/modules/agents.html).

---

Stay tuned for more updates and developments in the field of AI and Large Language Models!