🔮 AI Agents

Welcome to our list of AI autonomous agents. Your favorite one is missing? Add them via pull request. ❤️

AgentGPT

Here is a short summary

• Website
• GitHub

Stack:

• Frontend: NextJS + Typescript
• Backend: FastAPI + Python
  • DB: MySQL through docker with the option of running SQLite locally
• GitHub

AI Legion

Similar in spirit to AutoGPT and Baby AGI, but written in the superior language that is TypeScript (Author's Description)

• Author: eumemic
• Website
• GitHub
• Twitter

AIrplane

Developer infrastructure for internal tools

Aomni

AutoGPT

- [GitHub](https://github.com/Significant-Gravitas/Auto-GPT)

BabyAGI

• Default model is OpenAI GPT3-turbo
• Paper: Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications
• The main idea behind this system is that it creates tasks based on the result of previous tasks and a predefined objective.
• The script then uses OpenAI's NLP capabilities to create new tasks based on the objective

BabyCatAGI

BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI. BabyCatAGI is at 300 lines of code.

BitBuilder

Bloop

Butternut AI

Camel

CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society

Cognosys - Friendly UI for building AI agents

Description: web based version of AutoGPT/babyAGI

• Author: Sully Omarr
• Twitter: https://twitter.com/SullyOmarr

Databerry

Factory

Fixie

Generative Agents

• "Paper presenting an architecture that extends a language model to store and synthesize the agent's experiences, enabling dynamic behavior planning in an interactive sandbox environment with generative agents"

GitWit

Grit

HayStack Agent

Hex Magic

Heymoon.ai

Personal assistant for life: to keep you on top of your calendar, tasks and information. Was at Llama event demo

Hyperwrite

Your personal AI writing assistant

Jarvis

LangChain - Agents Round

LastMile AI

Loop GPT

- Languages: Python - Default model: GPT-3.5-turbo (also possible with GPT-4) - Modular Auto-GPT Framework - Plug N Play" API - Extensible and modular "Pythonic" framework, not just a command line tool - Easy to add new features, integrations and custom agent capabilities, all from python code, no nasty config files! - Minimal prompt overhead - Every token counts. We are continuously working on getting the best results with the least possible number of tokens. - Human in the Loop - Ability to "course correct" agents who go astray via human feedback. - Full state serialization - can save the complete state of an agent, including memory and the states of its tools to a file or python object. No external databases or vector stores required (but they are still supported)!

Minion AI

MultiOn

Naut ai

Pezzo

Saga

Second

Smol developer

Superagent

Sweep

Yourgoal

Description: Swift implementation of BabyAGI.

Author: PJ Gray Twitter: https://twitter.com/pj4533