Found it here https://github.com/irgolic/AutoPR

https://github.com/Pythagora-io/gpt-pilot

🧑‍✈️ GPT PILOT

GPT Pilot codes the entire app as you oversee the code being written

This is a research project to see how can GPT-4 be utilized to generate fully working, production-ready, apps. The main idea is that AI can write most of the code for an app (maybe 95%) but for the rest 5%, a developer is and will be needed until we get full AGI.

https://github.com/microsoft/autogen

It's become quite popular.

What is AutoGen

AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.

• AutoGen enables building next-gen LLM applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation, and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcomes their weaknesses.
• It supports diverse conversation patterns for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy,
  the number of agents, and agent conversation topology.
• It provides a collection of working systems with different complexities. These systems span a wide range of applications from various domains and complexities. This demonstrates how AutoGen can easily support diverse conversation patterns.
• AutoGen provides enhanced LLM inference. It offers easy performance tuning, plus utilities like API unification and caching, and advanced usage patterns, such as error handling, multi-config inference, context programming, etc.

AutoGen is powered by collaborative research studies from Microsoft, Penn State University, and the University of Washington.

Probably under "build your own" and open source: https://github.com/gptscript-ai/gptscript

Hello, thank you for the awesome repository.
I believe the tool TaskWeaver also has a place here. Perhaps in the coding-specific agents tab.
https://github.com/microsoft/TaskWeaver

Llama Coder is a better and self-hosted Github Copilot replacement for VS Studio Code. Llama Coder uses Ollama and codellama to provide autocomplete that runs on your hardware. Works best with Mac M1/M2/M3 or with RTX 4090.

https://github.com/ex3ndr/llama-coder

https://myaskai.com/?utm_source=twitter&utm_medium=organic_social&utm_content=profile_company

https://twitter.com/usemyaskai

• Noodl https://noodl.net
• Wizard Coder https://github.com/nlpxucan/WizardLM
• Flowize https://github.com/FlowiseAI/Flowise
• LangFlow https://github.com/logspace-ai/langflow
• Star Coder https://github.com/bigcode-project/starcoder
• Chain Forge https://github.com/ianarawjo/ChainForge
• Eval https://github.com/corca-ai/EVAL

Hi, first of all really appreciate the Infographic created by your team. just wanted to create this issue to remind of small issues like:

• some of the links are broken( Awesome AI agents SDK , contact calendly link, etc ).
• Also in the infographics , I think Huggingface Agents SDK is also must needed addition under "Build you own" GPT.

Would be great if this was in table format, with a standardized number of columns that represent aspects of the frameworks. For example, many of these don't support open-source models, only OpenAI's offerings. Would be great if I could quickly see which ones do or don't.

@tizkovatereza sorry for the tagging, but I noticed there's not much activity here so just making sure....

Please add LangGraph

Awesome list.!!!

Launch date/month may be added to sort out list by date.

I found this interesting multi-agent framework a few days ago
https://github.com/geekan/MetaGPT

Tabula is a GPT-powered data analytics platform built for modern data stack.
Tabula enables working with both structured and unstructured data with no-code AI tools.

Details:

• data cleanup, transformation
• workflow automation and scheduling
• data visualization
• data enrichment

Tech details:

• 150+ integrations
• dbt compatible
• works on top of any database

Suspicion Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

Project Demo
Game Data Replay
Code

Let's add a new coding copilot on the block
https://continue.dev/

https://codellama.dev/about

MiniAutoGen - A Lightweight and Flexible Library for Creating Agents and Multi-Agent Conversations

Here are some notable features of MiniAutoGen:

• Multi-Agent Dialogues: The ability to create complex and nuanced interactions with multiple intelligent agents operating together.
• Agent Coordination: A mechanism that ensures harmony and efficient management among the agents.
• Customizable Agents: Total freedom to shape agent behaviors according to project needs.
• Action Pipeline: Simplifies and automates agent operations, facilitating scalability and maintenance.
• Integration with +100 LLMs: Expanding conversational capabilities with over 100 LLMs for intelligent and contextualized responses.

I discovered several agents that I think we should add:

• Fine
  • https://twitter.com/thisisfinedev
  • https://twitter.com/leshemco
• AI Maintainer
• GPT-researcher
• GPT Runner

such as https://github.com/THUDM/AgentBench

Github Repo: https://github.com/eosphoros-ai/DB-GPT
Sub Module Multi-Agents Repo: https://github.com/eosphoros-ai/DB-GPT-Plugins

DB-GPT-Plugins is a Multi-Agents & Plugins repo for DB-GPT, Can complete various tasks around databases.

in addition to or in place of integrating with any aggregators - Please integrate APIpie so devs can access them all from one place/subscription and plus it also provides:

-The most affordable, reliable and fastest AI available
-One API to access ~500 Models and growing
-Language, embedding, voice, image, vision and more
-Global AI load balancing, route queries based on price or latency
-Redundancy for major models providing the greatest up time possible
-Global reporting of AI availability, pricing and performance

Its the same API format as openai, just change the domain name and your API key and enjoy a plethora of models without changing any of your code other than how you handle the models list.