Build your next agent with graphs, monitoring, and replay analytics. Tools to make agents that work. No more black boxes and prompt guessing.

https://github.com/AgentOps-AI/agentops

Nelima is designed for taking actions on your behalf with natural language commands.

https://github.com/HumanSignal/Adala

A recommender system simulator with 1,000 LLM-empowered generative agents.

https://github.com/LehengTHU/Agent4Rec

A low-code framework designed for the swift creation, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures, compatible with various LLM models.

https://github.com/DataBassGit/AgentForge

https://github.com/reworkd/AgentGPT

https://github.com/jbexta/AgentPilot

https://agents-readthedocsio.readthedocs.io/en/latest/index.html

A systematic framework for training language agents, which is inspired by the connectionist learning procedure used for training neural nets.

https://github.com/aiwaves-cn/agents

Designed to facilitate the deployment of multiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: task-solving and simulation.

https://github.com/OpenBMB/AgentVerse

https://gpt3demo.com/apps/ai-legion

https://github.com/eumemic/ai-legion

A command line tool that lets you pair program with GPT-3.5/GPT-4, to edit code stored in your local git repository.

https://github.com/paul-gauthier/aider

A fully autonomous, general-purpose AI agent. This project aims to create a standalone artificial intelligence assistant, similar to JARVIS, based on the open-source LLM.

https://github.com/myshell-ai/AIlice

https://github.com/microsoft/autogen

https://github.com/Significant-Gravitas/AutoGPT?utm_source=awesome-ai-agents

https://x.com/Auto_GPT/?utm_source=awesome-ai-agents

Automata's objective is to evolve into a fully autonomous, self-programming Artificial Intelligence system.

https://github.com/emrgnt-cmplxty/automata

https://github-production-user-asset-6210df.s3.amazonaws.com/68796651/250135126-61fe3c33-9b7a-4c1b-9726-a77140476b83.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20240703%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240703T105824Z&X-Amz-Expires=300&X-Amz-Signature=4ee833bac892d28f1f04186002304fe163842a440abff661ee71d85184af4f54&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=656278816

https://github.com/irgolic/AutoPR

https://agents.staf.ai/AutonomousHRChatbot

https://github.com/stepanogil/autonomous-hr-chatbot

The system uses OpenAI and vector databases such as Chroma or Weaviate to create, prioritize, and execute tasks. The main idea behind this system is that it creates tasks based on the result of previous tasks and a predefined objective.

https://github.com/yoheinakajima/babyagi

https://yoheinakajima.com/babybeeagi-task-management-and-functionality-expansion-on-top-of-babyagi/

BabyBeeAGI: Task Management and Functionality Expansion on top of BabyAGI

https://github.com/yoheinakajima/babyagi/blob/main/classic/BabyBeeAGI.py

This was built as a continued iteration on the original BabyAGI code in a lightweight way.

https://github.com/yoheinakajima/babyagi/blob/main/classic/BabyCatAGI.py

https://replit.com/@YoheiNakajima/BabyDeerAGI

A mod of BabyCatAGI, which is a mod of BabyBeeAGI, which is a mod of OG BabyAGI. BabyDeerAGI is at ~350 lines of code.

https://github.com/yoheinakajima/babyagi/blob/main/classic/BabyDeerAGI.py

https://replit.com/@YoheiNakajima/BabyElfAGI

https://github.com/yoheinakajima/babyagi/blob/main/classic/BabyElfAGI/main.py

https://agents.staf.ai/BabyCommanAGI

Designed to test what happens when you combine CLI and LLM, which are older computer interfaces than GUI. Based on BabyAGI, and using GPT-4 API. Imagine LLM and CLI having a conversation.

https://github.com/saten-private/BabyCommandAGI

A mod of BabyElfAGI, in a series of mods w the naming of BabyAGI in alphabetical order.

https://github.com/yoheinakajima/babyagi/tree/main/classic/babyfoxagi

A lightweight library that leverages Language Models (LLMs) to enable natural language interactions, allowing you to source and converse with data.

https://github.com/pgalko/BambooAI

BeeBot is your personal worker bee, an Autonomous AI Assistant designed to perform a wide range of practical tasks autonomously.

https://github.com/AutoPackAI/beebot

Find Code. Fast. Understand codebases with GPT-4 and semantic code search

https://github.com/BloopAI/bloop

A highly capable, autonomous AI Agent with an easy to use CLI, RESTful/WebSocket API, Pre-built Docker image and a robust suite of integrated tools.

https://github.com/krohling/bondai

Bumpgen builds your project to understand what broke when a dependency was bumped.

https://github.com/xeol-io/bumpgen

Cal.ai can book meetings, summarize your week, and find time with others based on natural language.

https://github.com/calcom/cal.com/tree/main/apps/ai

https://camo.githubusercontent.com/8e9f64be3c8dab914b01094e195cdb6feda132fbb51575e049bc3882d19f8a6a/68747470733a2f2f333632303130373734332d66696c65732e676974626f6f6b2e696f2f7e2f66696c65732f76302f622f676974626f6f6b2d782d70726f642e61707073706f742e636f6d2f6f2f737061636573253246706d554f715a6a6647714e6b69506d71676e4d7625324675706c6f6164732532463951617131686c615463714b667263396b344f47253246696d6167652e706e673f616c743d6d6564696126746f6b656e3d31666665383533302d313966662d346165612d623032302d613939636463323234636531

An open-source library designed for the study of autonomous and communicative agents. 1)AI user agent: give instructions to the AI assistant with the goal of completing the task.

https://github.com/camel-ai/camel

https://x.com/intent/follow?original_referer=https%3A%2F%2F1508613885-atari-embeds.googleusercontent.com%2F&ref_src=twsrc%5Etfw%7Ctwcamp%5Ebuttonembed%7Ctwterm%5Efollow%7Ctwgr%5ECamelAIOrg&screen_name=CamelAIOrg

A Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

https://github.com/Farama-Foundation/chatarena

https://chatarena.slack.com/join/shared_invite/zt-1t5fpbiep-CbKucEHdJ5YeDLEpKWxDOg#/shared-invite/email

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

https://github.com/OpenBMB/ChatDev

ChemCrow is an open source package for the accurate solution of reasoning-intensive chemical tasks. Built with Langchain, it uses a collection of chemical tools including RDKit, paper-qa, as well as some relevant databases in chemistry, like Pubchem and chem-space.

https://github.com/ur-whitelab/chemcrow-public

https://python-poetry.org/docs/#installing-with-pipx

Develop code for or with the user. It can plan, write, debug, and test some projects autonomously.

https://github.com/ennucore/clippinator

https://github.com/codefuse-ai/codefuse-chatbot#-%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

https://github.com/codefuse-ai/codefuse-chatbot

https://github.com/ajhous44/cody/blob/main/cody.py

An AI assistant designed to let you interactively query your codebase using natural language.

https://github.com/ajhous44/cody

https://github.com/sourcegraph/docs

An AI code assistant from Sourcegraph that writes code and answers questions for you by reading your entire codebase and the code graph.

https://github.com/sourcegraph/sourcegraph/tree/main/client/cody

Leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains.

https://github.com/continuedev/continue

https://github.com/joaomdmoura/crewai

https://github.com/gmpetrov/databerry

https://github.com/melih-unsal/DemoGPT

Code generation leverages a vectorised version of your repository, ensuring highly relevant and contextually useful code. Say goodbye to copy-pasting; the generated code appears directly in your editor.

https://github.com/jina-ai/dev-gpt

https://github.com/stitionai/devika/tree/main/docs/architecture

Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

https://github.com/stitionai/devika

https://github.com/entropy-research/Devon

https://github.com/entropy-research/Devon

Multi agent system for AI-driven software development. Combine LLM with DevOps tools to convert natural language requirements into working software. Supports any development language and extends the existing code.

https://github.com/kuafuai/DevOpsGPT

An agent management system that facilitates the creation of robust AI applications and experimental autonomous agents through a rich suite of developer tools.

https://github.com/dot-agent/nextpy

https://github.com/eidolon-ai/eidolon

https://agents.staf.ai/EnglishCompiler

POC AI based Compiler, for converting english based markdown specs, into functional code

https://github.com/uilicious/english-compiler

Evo utilizes pre-defined agent personas that are tailored to specific domains of tasks. Each iteration of evo's execution loop it will select and adopt the persona that fits the task at hand best.

https://github.com/agentcoinorg/evo.ninja

Build LLMs Apps Easily. Open source UI visual tool to build your customized LLM flow using LangchainJS, written in Node Typescript/Javascript

https://github.com/FlowiseAI/Flowise

https://github.com/amirrezasalimi/friday/blob/main/readme.md

Friday is a developer agent that helps you quickly create applications with AI assistance.

https://github.com/amirrezasalimi/friday/

GeniA is able to work along side you on your production enviroment, executing tasks on your behalf in your dev & cloud environments, AWS/k8s/Argo/GitHub etc.

https://github.com/genia-dev/GeniA

Godmode is a web platform to access the powers of autoGPT and babyAGI. AI agents are still in their infancy, but they are quickly growing in capabilities, and we hope that Godmode will enable more people to tap into autonomous AI agents even in this early stage.

https://github.com/FOLLGAD/Godmode-GPT

https://github.com/Kav-K/GPTDiscord

Specify what you want it to build, the AI asks for clarification, and then builds it.

https://github.com/gpt-engineer-org/gpt-engineer

https://github.com/joshpxyne/gpt-migrate

https://github.com/Pythagora-io/gpt-pilot/blob/main/README.md

GPT Pilot is an AI agent that codes the entire app as you oversee the code being written.

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

GPT Researcher is a GPT-based autonomous agent that does online comprehensive research on any given topic.

https://github.com/assafelovic/gpt-researcher

https://github.com/nicepkg/gpt-runner

Use GPT-Runner to manage your AI presets, engage in AI-powered conversations with your code, and significantly boost the development efficiency of both you and your team!

https://github.com/nicepkg/gpt-runner

https://private-user-images.githubusercontent.com/34775414/252919370-a48b745f-c803-4884-95a8-26c63f7f5b53.svg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.k8RKOHKW2VDsPa3MUjJEHDGloZ2xHX5ArTblrjNhaKg

https://github.com/metauto-ai/GPTSwarm

IX is a platform for designing and deploying autonomous and [semi]-autonomous LLM powered agents and workflows.

https://github.com/kreneskyp/ix

JARVIS is to explore artificial general intelligence (AGI) and deliver cutting-edge research to the whole community.

https://github.com/microsoft/JARVIS

Langroid is an intuitive, lightweight, extensible and principled Python framework to easily build LLM-powered applications, from ex-CMU and UW-Madison researchers.

https://github.com/langroid/langroid

https://github.com/felixbrock/lemon-agent?tab=readme-ov-file

Lemon agent is a Plan-Validate-Solve (PVS) Agent for accurate, reliable and reproducable workflow automation.

https://github.com/felixbrock/lemon-agent

https://www.paepper.com/blog/posts/intelligent-agents-guided-by-llms/

A minimalistic library for building agents that leverage large language models to automate tasks through a loop of commands and tool integrations.

https://github.com/mpaepper/llm_agents

https://x.com/intent/follow?original_referer=https%3A%2F%2Fwww.paepper.com%2F&ref_src=twsrc%5Etfw%7Ctwcamp%5Ebuttonembed%7Ctwterm%5Efollow%7Ctwgr%5Empaepper&region=follow_link&screen_name=mpaepper

LLMStack is a no-code platform for building generative AI agents, workflows and chatbots, connecting them to your data and business processes.

https://github.com/trypromptly/LLMStack

LocalGPT is an open-source initiative that allows you to converse with your documents without compromising your privacy. Inspired by privateGPT, allows using your own documents as an information source

https://github.com/PromtEngineer/localGPT

https://github.com/farizrahman4u/loopgpt/tree/mainn

L2MAC is a multi-agent generation framework that, a single input prompt can generate an extensive unbounded output, such as an entire codebase or an entire book.

https://github.com/samholt/l2mac

Maige is a codebase agent that runs when new issues and pull requests come up. Its core features are labelling, assigning, and answering questions.

https://github.com/RubricLab/maige

Magick is an AIDE for creating, deploying, scaling, and monetizing useful AI agents, and prompt chaining.

https://github.com/Oneirocom/Magick

https://memgpt.readme.io/docs/index

A system that intelligently manages different memory tiers in LLMs to effectively provide the extended context within the LLM's limited context window.

https://github.com/cpacker/MemGPT

https://github.com/AbanteAI/mentat

MetaGPT is a multi-agent framework that, given one line requirement, returns PRD, Design, Tasks, or Repo.

https://github.com/geekan/MetaGPT

MiniAGI is a minimal general-purpose autonomous agent based on GPT-3.5 / GPT-4. Can analyze stock prices, perform network security tests, create art, and order pizza.

https://github.com/muellerberndt/mini-agi

https://composable-models.github.io/llm_debate/

Multiagent Debate is an implementation of the paper "Improving Factuality and Reasoning in Language Models through Multiagent Debate".

https://github.com/composable-models/llm_multiagent_debate

https://www.loom.com/share/b6bec93065794eb8a47e2109697afa39

https://github.com/sidhq/Multi-GPT

https://github.com/mczhuge/NLSOM

https://github.com/xlang-ai/OpenAgents?tab=readme-ov-file

OpenAgents is an Open Platform for Language Agents in the Wild, ChatGPT Plus Replica for Researchers, Developers, and General Users.

https://github.com/xlang-ai/OpenAgents

https://github.com/agiresearch/OpenAGI

OpenAGI is an open-source AGI R&D platform that enables agents for both benchmark tasks and open-ended tasks

https://github.com/agiresearch/OpenAGI

The OpenDevin project is born out of a desire to replicate, enhance, and innovate beyond the original Devin model.

https://github.com/OpenDevin/OpenDevin

A new way to use computers. Open Interpreter lets LLMs run code on your computer to complete tasks

https://github.com/KillianLucas/open-interpreter

Pezzo is a development toolkit designed to streamline prompt design, version management, publishing, collaboration, troubleshooting, observability and more

https://github.com/pezzolabs/pezzo

Interact with your documents using the power of GPT, 100% privately, no data leaks

https://github.com/imartinez/privateGPT

Open-source framework that gives you AI Agents that help you navigate decision-making, get personalized goals and execute them

https://github.com/topoteretes/PromethAI-Backend

https://github.com/eylonmiz/react-agent

https://www.hyperwriteai.com/self-operating-computer

https://github.com/OthersideAI/self-operating-computer

https://camo.githubusercontent.com/d441f22e80e23e72bf5541662c4062dd68f2d7631d4e2c7975e463087015c976/68747470733a2f2f6173736574732d676c6f62616c2e776562736974652d66696c65732e636f6d2f3633666364373964343130623232646466333937653162382f3635343237323535343430323431306137316338346162395f3634303563316361626466396336396630356231303830655f6f74686572736964655f6c6f676f5f73796d626f6c2e77656270

https://github.com/smol-ai/developer

Stackwise is a VS Code extension that writes and imports nodejs functions so that you can write code without context switching.

https://github.com/stackwiseai/stackwise

https://github.com/superagent-ai/superagent

https://camo.githubusercontent.com/41e23b277675be4f7ed1fb1653e080af5d59e0000ea9c6cc4023664500b47387/68747470733a2f2f6170692e74797065647265616d2e636f6d2f76302f646f63756d656e742f7075626c69632f62396436383862612d386633342d343065342d613234612d6336326234303362343032642f3259756b6751737662566b5570377531484c7372424b436a66724f5f73757065726167656e745f6c6f676f5f63616e6469646174655f325f696e76697369626c655f6261636b67726f756e645f736d616c6c2e706e67

Dev-first opensource AI agents framework to build, manage & run autonomous agents

https://github.com/TransformerOptimus/SuperAGI

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

https://github.com/CR-Gjx/Suspicion-Agent

https://princeton-nlp.github.io/SWE-agent/

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice.

https://github.com/princeton-nlp/SWE-agent

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

https://github.com/sweepai/sweep

Taxy uses GPT-4 to control your browser and perform repetitive actions on your behalf

https://github.com/TaxyAI/browser-extension