I build a completely Local and portable AutoGPT with the help of gpt-llama, running on Vicuna-13b

• gpt-llama.cpp

  12 587 8.2 JavaScript

  A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.

• AGiXT

  26 2,456 9.9 Python

  AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

That is nice and all, but AgentLLM has been able to do this for a little while now, and has a nice webui to interface with agents as they run along with support for GPU accelerations via oobabooga api or many other options.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• Auto-LLM-Local

  1 29 10.0 Python

  Discontinued Created my own python script similar to AutoGPT where you supply a local llm model like alpaca13b (The main one I use), and the script can access the supplied tools to achieve your objective. Code fully works as far as I can tell. Takes me 5 minutes per chain on my slow laptop.

• AutoGPT4J

  3 27 5.3 Java

  A repository for a Java implementation of AutoGPT. It is heavily inspired by AutoGPT if not a clone of some of its functionality, though there is some deviation from it particularly in how Agents are implemented as well as planned support for more open source models.

Suggest a related project