https://github.com/kyrolabs/awesome-agents
🤖 Awesome list of AI Agents
https://github.com/kyrolabs/awesome-agents
List: awesome-agents
Last synced: 7 months ago
JSON representation
🤖 Awesome list of AI Agents
- Host: GitHub
- URL: https://github.com/kyrolabs/awesome-agents
- Owner: kyrolabs
- Created: 2023-07-02T11:12:36.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-15T20:47:22.000Z (almost 2 years ago)
- Last Synced: 2024-05-23T03:03:15.272Z (almost 2 years ago)
- Homepage:
- Size: 32.2 KB
- Stars: 149
- Watchers: 3
- Forks: 15
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- Awesome-AI-Agents - awesome-agents - 🤖 Awesome list of AI Agents (Reference Repo / Blog)
- ultimate-awesome - awesome-agents - 🤖 Awesome list of AI Agents. (Programming Language Lists / Python Lists)
- awesome-ai-tools - kyrolabs/awesome-agents - Curated open-source AI agent frameworks organized by type and domain (AI Frameworks / 🔧 AI Agent Development Frameworks)
- awesome-rainmana - kyrolabs/awesome-agents - 🤖 Awesome list of AI Agents (Others)
- awesome-vibe-coding - Awesome Agents
README
# 🤖 Awesome Agents
Awesome Agents is a curated list of open-source tools and products to build AI agents.
## Table of Contents
- [🤖 Awesome Agents](#-awesome-agents)
- [Table of Contents](#table-of-contents)
- [Frameworks](#frameworks)
- [Testing and Evaluation](#testing-and-evaluation)
- [Software Development](#software-development)
- [Research](#research)
- [Conversational / General Agents](#conversational--general-agents)
- [Game / Simulation](#game--simulation)
- [Knowledge Management](#knowledge-management)
- [Automation](#automation)
- [Browser](#browser)
- [Multimodal](#multimodal)
## Frameworks
- [llama-agentic-system](https://github.com/meta-llama/llama-agentic-system): Agentic components of the Llama Stack APIs 
- [Transformers Agents](https://huggingface.co/docs/transformers/transformers_agents): Provides a natural language API on top of transformers
- [LlamaIndex](https://github.com/jerryjliu/llama_index): provides a central interface to connect your LLM's with external data. 
- [LangChain](https://github.com/hwchase17/langchain): the original 🐍 
- [Botpress](https://github.com/botpress/botpress): The building blocks for building chatbots 
- [Haystack](https://github.com/deepset-ai/haystack): NLP framework to interact with your data using Transformer models and LLMs 
- [Semantic Kernel](https://github.com/microsoft/semantic-kernel): Microsoft C# SDK to integrate cutting-edge LLM technology quickly and easily into your apps 
- [Agent-LLM](https://github.com/Josh-XT/Agent-LLM): An Artificial Intelligence Automation Platform. 
- [LLM Agents](https://github.com/mpaepper/llm_agents): Build agents which are controlled by LLMs 
- [e2b](https://github.com/e2b-dev/e2b): Open-source platform for building & deploying virtual developers’ agents
- [Dust](https://github.com/dust-tt/dust): Design and Deploy Large Language Model Apps 
- [MetaGPT](https://github.com/geekan/MetaGPT): The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo and CI 
- [AgentFlow](https://github.com/simonmesmith/agentflow): About Complex LLM Workflows from Simple JSON. 
- [Lagent](https://github.com/InternLM/lagent): A lightweight framework for building LLM-based agents 
- [Autogen](https://github.com/microsoft/autogen): Enable Next-Gen Large Language Model Applications. 
- [AgentVerse](https://github.com/openbmb/agentverse) Provides a flexible framework that simplifies the process of building custom multi-agent environments for LLMs 
- [Maestro](https://github.com/Doriandarko/maestro): A framework for Claude Opus to intelligently orchestrate subagents. 
- [AgentScope](https://github.com/modelscope/agentscope): Start building LLM-empowered multi-agent applications in an easier way. 
- [CrewAI](https://github.com/joaomdmoura/crewai): Cutting-edge framework for orchestrating role-playing, autonomous AI agents. 
- [Swarm](https://github.com/openai/swarm): Educational framework exploring ergonomic, lightweight multi-agent orchestration by OpenAI. 
- [agency-swarm](https://github.com/VRSEN/agency-swarm): Reliable agent framework built on top of the latest OpenAI Assistants API. 
- [Upsonic](https://github.com/upsonic/upsonic): Reliable agent framework that supports MCP. 
- [Mastra](https://github.com/mastra-ai/mastra): Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. 
- [Vectara-agentic](https://github.com/vectara/py-vectara-agentic): Vectara-agentic is a framework for creating AI Assistants and agents using Vectara.
- [Portia AI](https://github.com/portiaAI/portia-sdk-python/) Portia is a new open source agentic Python framework designed for creating reliable agents in production. 
- [AgentDock](https://github.com/AgentDock/AgentDock): Stop wrestling with countless APIs and complex integrations. AgentDock provides the open-source foundation to build, manage, and deploy production-ready AI agents and workflows, frictionlessly. 
- [Modus](https://github.com/hypermodeinc/modus): An open source, serverless framework for building intelligent agents and APIs in Go or AssemblyScript (a TypeScript-like language).
- [Swarms Framework](https://github.com/kyegomez/swarms) Bleeding-Edge Multi-Agent Orchestration Framework for Enterprise Applications 
- [Strands Agents SDK](https://github.com/strands-agents/sdk-python): A model-driven approach to building AI agents in just a few lines of code. 
## Testing and Evaluation
- [Voice Lab](https://github.com/saharmor/voice-lab): A comprehensive testing and evaluation framework for voice agents across language models, prompts, and agent personas. 
- [Open-RAG-Eval](https://github.com/vectara/open-rag-eval): an open source RAG evaluation framework that does not require golden answers, and can be used to evaluate performance of RAG tools connected to an AI Agent (Agentic RAG)
- [EvoAgentX](https://github.com/EvoAgentX/EvoAgentX) - EvoAgentX is building a Self-Evolving Ecosystem of AI Agents, it will give you automated framework for evaluating and evolving agentic workflows. 
## Software Development
- [MetaGPT](https://github.com/geekan/MetaGPT): The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming 
- [OpenHands](https://github.com/All-Hands-AI/OpenHands): 🙌 OpenHands: Code Less, Make More. (formerly OpenDevin), a platform for software development agents powered by AI 
- [GPT Pilot](https://github.com/Pythagora-io/gpt-pilot): GPT Pilot is the core technology for the Pythagora VS Code extension that aims to provide the first real AI developer companion. 
- [Aider](https://github.com/Aider-AI/aider): aider is AI pair programming in your terminal 
- [Devika](https://github.com/stitionai/devika): Devika is an 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 
- [RepoAgent](https://github.com/OpenBMB/RepoAgent): An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly 
- [DSPy](https://github.com/stanfordnlp/dspy): The framework for programming—not prompting—foundation models 
- [ThinkGPT](https://github.com/alaeddine-13/thinkgpt): Agent techniques to augment your LLM and push it beyond its limits 
- [PyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI): A small AGI experiment to generate a Python app given what app the user wants to build 
- [SuperAGI](https://github.com/TransformerOptimus/SuperAGI): SuperAGI - A dev-first open source autonomous AI agent framework 
- [Plandex](https://github.com/plandex-ai/plandex): An AI coding engine for complex tasks 
- [Codel](https://github.com/semanser/codel): ✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor. 
- [DB GPT](https://github.com/csunny/DB-GPT): Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security 
- [Agency](https://github.com/neurocult/agency): 🕵️♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach 
- [TaskWeaver](https://github.com/microsoft/TaskWeaver): A code-first agent framework for seamlessly planning and executing data analytics tasks. 
- [MicroAgent](https://github.com/aymenfurter/microagents): Agents Capable of Self-Editing Their Prompts / Python Code 
- [SWE Agent](https://github.com/princeton-nlp/swe-agent): SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. 
- [AgentRun](https://github.com/Jonathan-Adly/AgentRun): The easiest, and fastest way to run AI-generated Python code safely 
- [Claude Engineer](https://github.com/Doriandarko/claude-engineer): Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.
- [Vision agent](https://github.com/landing-ai/vision-agent): Vision Agent is a library that helps you utilize agent frameworks to generate code to solve your vision task. 
- [Nous](https://github.com/TrafficGuard/nous): TypeScript AI agent platform with Autonomous agents, Software developer agents, AI code review agents and more. 
## Research
- [GPT Researcher](https://github.com/assafelovic/gpt-researcher): GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks. 
- [BlockAGI](https://github.com/blockpipe/blockagi): BlockAGI conducts iterative, domain-specific research, and outputs detailed narrative reports to showcase its findings 
- [data-to-paper](https://github.com/Technion-Kishony-lab/data-to-paper): data-to-paper: AI-driven research from data to human-verifiable research papers 
- [AI Scientist](https://github.com/SakanaAI/AI-Scientist): The AI Scientist: Towards Fully Automated Open-Ended Scientific 
- [Storm](https://github.com/stanford-oval/storm): An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. 
## Conversational / General Agents
- [CollosalAI Chat](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Chat): implement LLM with RLHF, powered by the Colossal-AI project 
- [RasaGPT](https://github.com/paulpierre/RasaGPT): RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. 
- [SuperAgent](https://github.com/homanp/superagent): Deploy LLM Agents to production 
- [BabyAGI UI](https://github.com/miurla/babyagi-ui): Make it easier to run and develop with babyagi in a web app, like a ChatGPT 
- [ix](https://github.com/kreneskyp/ix): Autonomous GPT-4 agent platform 
- [DuetGPT](https://github.com/kristoferlund/duet-gpt): A conversational semi-autonomous developer assistant, AI pair programming without the copypasta. 
- [Multi-Modal LangChain agents in Production](https://github.com/steamship-packages/langchain-agent-production-starter): Deploy LangChain Agents and connect them to Telegram 
- [Autonomous HR Chatbot](https://github.com/stepanogil/autonomous-hr-chatbot): An autonomous agent that can answer HR related queries autonomously using the tools it has on hand 
- [LLama Cpp Agent](https://github.com/Maximilian-Winter/llama-cpp-agent): The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models 
- [Memgpt](https://github.com/cpacker/memgpt): Create LLM agents with long-term memory and custom tools 📚🦙 
- [GPT Agent](https://github.com/iris-networks/gpt-agent): The Free, Open-Source AI Agent for Computer Automation 
## Game / Simulation
- [Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT): role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT 
- [SkyAGI](https://github.com/litanlitudan/skyagi): Emerging human-behavior simulation capability in LLM agents 
- [Voyager](https://github.com/MineDojo/Voyager): An Open-Ended Embodied Agent with Large Language Models 
## Knowledge Management
- [Private GPT](https://github.com/imartinez/privateGPT): Interact privately with your documents using the power of GPT, 100% privately, no data leaks 
- [Local GPT](https://github.com/PromtEngineer/localGPT): Inspired on Private GPT with the GPT4ALL model replaced with the Vicuna-7B model and using the InstructorEmbeddings instead of LlamaEmbeddings 
- [LLocalSearch](https://github.com/nilsherzig/LLocalSearch): LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed. 
- [Second Brain AI Agent](https://github.com/flepied/second-brain-agent): A streamlit app to dialog with your second brain notes using OpenAI and ChromaDB locally. 
## Automation
- [DemoGPT](https://github.com/melih-unsal/DemoGPT): DemoGPT enables you to create quick demos by just using prompt. It applies ToT approach on Langchain documentation tree. 
- [RestGPT](https://github.com/Yifan-Song793/RestGPT): An LLM-based autonomous agent controlling real-world applications via RESTful APIs 
- [XAgent](https://github.com/OpenBMB/XAgent): An Autonomous LLM Agent for Complex Task Solving 
- [LLM Agents](https://github.com/mpaepper/llm_agents): Build agents which are controlled by LLMs 
- [uAgents](https://github.com/fetchai/uAgents): A fast and lightweight framework for creating decentralized agents with ease. 
- [Maestro](https://github.com/Doriandarko/maestro): A framework for Claude Opus to intelligently orchestrate subagents. 
- [llama-agents](https://github.com/run-llama/llama-agents): llama-agents is an async-first framework for building, iterating, and productionizing multi-agent systems, including multi-agent communication, distributed tool execution, human-in-the-loop, and more 
- [Phidata](https://github.com/phidatahq/phidata): Build AI Assistants with memory, knowledge and tools. 
- [AgentK](https://github.com/mikekelly/AgentK): An autoagentic AGI that is self-evolving and modular. 
- [ADAS](https://github.com/ShengranHu/ADAS): Automated Design of Agentic Systems 
- [Giselle](https://github.com/giselles-ai/giselle): Giselle is an agentic workflow builder that empowers you to create AI-driven solutions with ease. 
### Browser
- [AgentGPT](https://github.com/reworkd/AgentGPT): AI Agents with Langchain & OpenAI (Vercel / Nextjs) 
- [OpenAgents](https://github.com/xlang-ai/OpenAgents): An Open Platform for Language Agents in the Wild 
### Multimodal
- [Pipecat](https://github.com/pipecat-ai/pipecat): Open Source framework for voice and multimodal conversational AI. 