Teenage AGI

Objective Inspired by several Auto-GPT-related Projects (predominantly BabyAGI) and the Paper "Generative Agents: Interactive Simulacra of Human Behavior", this Python project uses OpenAI and Pinecone to Give memory to an AI agent and also allows it to "think" before making an action (outputting text). Also, just by shutting down the AI, it doesn't forget its memories since it lives on Pinecone and its memory_counter saves the index that it's on.

Updates April 12: Added "read" and "think" commands. Add "read: " or "think: " in front of a query to feed it information using read (any length works) or insert a memory into an agent.

Sections

• How it Works
• How to Use
• Experiments
• More About Project & Me
• Credits

How it Works Here is what happens every time the AI is queried by the user:

1. 1.AI vectorizes the query and stores it in a Pinecone Vector Database
2. 2.AI looks inside its memory and finds memories and past queries that are relevant to the current query
3. 3.AI thinks about what action to take
4. 4.AI stores the thought from Step 3
5. 5.Based on the thought from Step 3 and relevant memories from Step 2, AI generates an output
6. 6.AI stores the current query and its answer in its Pinecone vector database memory

Compatible with popular AI development environments.

Category: Developer Tools