langchain/docs/use_cases/personal_assistants.md

Personal Assistants (Agents)

Conceptual Guide

We use "personal assistant" here in a very broad sense. Personal assistants have a few characteristics:

• They can interact with the outside world
• They have knowledge of your data
• They remember your interactions

Really all of the functionality in LangChain is relevant for building a personal assistant. Highlighting specific parts:

• Agent Documentation (for interacting with the outside world)
• Index Documentation (for giving them knowledge of your data)
• Memory (for helping them remember interactions)

Specific examples of this include:

• Baby AGI: a notebook implementing BabyAGI by Yohei Nakajima as LLM Chains
• Baby AGI with Tools: building off the above notebook, this example substitutes in an agent with tools as the execution tools, allowing it to actually take actions.
• CAMEL: an implementation of the CAMEL (Communicative Agents for “Mind” Exploration of Large Scale Language Model Society) paper, where two agents communicate with eachother.
• AI Plugins: an implementation of an agent that is designed to be able to use all AI Plugins.