This project involves collecting data on the most famous open-source AI agents from GitHub. By examining these open-source projects, we gain insights into trends, key players, and the technological landscape shaping the development of AI agents.
scraped_url | full_name | description | language | stargazers_count | topics | org_name | org_company | org_blog | org_location | org_email | owner_company | owner_blog | owner_location | owner_email | owner_bio |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
https://github.com/significant-gravitas/autogpt | Significant-Gravitas/AutoGPT | AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. | Python | 165162 | ai,artificial-intelligence,autonomous-agents,gpt-4,openai,python | AutoGPT | agpt.co | agpt.co | |||||||
https://github.com/langchain-ai/langchain | langchain-ai/langchain | 🦜🔗 Build context-aware reasoning applications | Jupyter Notebook | 89859 | LangChain | https://www.langchain.com | United States of America | [email protected] | https://www.langchain.com | United States of America | [email protected] | ||||
https://github.com/ollama/ollama | ollama/ollama | Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models. | Go | 81389 | gemma,gemma2,go,golang,llama,llama2,llama3,llava,llm,llms,mistral,ollama,phi3 | Ollama | https://ollama.com | [email protected] | https://ollama.com | [email protected] | |||||
https://github.com/imartinez/privategpt | zylon-ai/private-gpt | Interact with your documents using the power of GPT, 100% privately, no data leaks | Python | 53114 | Zylon | https://zylon.ai/ | [email protected] | https://zylon.ai/ | [email protected] | The AI collaborator for every workplace | |||||
https://github.com/antonosika/gpt-engineer | gpt-engineer-org/gpt-engineer | Specify what you want it to build, the AI asks for clarification, and then builds it. | Python | 51500 | ai,autonomous-agent,code-generation,codebase-generation,codegen,coding-assistant,gpt-4,gpt-engineer,openai,python | gpt-engineer | gptengineer.app | gptengineer.app | |||||||
https://github.com/killianlucas/open-interpreter | OpenInterpreter/open-interpreter | A natural language interface for computers | Python | 51128 | chatgpt,gpt-4,interpreter,javascript,nodejs,python | Open Interpreter | www.openinterpreter.com | www.openinterpreter.com | |||||||
https://github.com/geekan/metagpt | geekan/MetaGPT | 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming | Python | 41933 | agent,gpt,hacktoberfest,llm,metagpt,multi-agent | Shenzhen, China | [email protected] | Discord: alexanderwu_ | |||||||
https://github.com/langgenius/dify | langgenius/dify | Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. | TypeScript | 39303 | agent,ai,anthropic,backend-as-a-service,chatbot,gemini,genai,gpt,gpt-4,llama3,llm,llmops,nextjs,openai,orchestration,python,rag,workflow,workflows | LangGenius | https://dify.ai | [email protected] | https://dify.ai | [email protected] | Dify is an LLMOps platform that helps you build GPT-based applications easily and intuitively. | ||||
https://github.com/lobehub/lobe-chat | lobehub/lobe-chat | 🤯 Lobe Chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT chat application. | TypeScript | 36043 | ai,azure-openai-api,chat,chatglm,chatgpt,claude,dalle-3,function-calling,gemini,gpt,gpt-4,gpt-4-vision,llama3,nextjs,ollama,openai,qwen2,tts | LobeHub | https://lobehub.com | [email protected] | https://lobehub.com | [email protected] | Empowering your AI dreams with LobeHub | ||||
https://github.com/lm-sys/fastchat | lm-sys/FastChat | An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. | Python | 35918 | LMSYS | Large Model Systems Organization | |||||||||
https://github.com/run-llama/llama_index | run-llama/llama_index | LlamaIndex is a data framework for your LLM applications | Python | 33987 | agents,application,data,fine-tuning,framework,llamaindex,llm,rag,vector-database | LlamaIndex | |||||||||
https://github.com/reworkd/agentgpt | reworkd/AgentGPT | 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser. | TypeScript | 30873 | agent,agentgpt,agi,autogpt,baby-agi,gpt,langchain,next,openai,t3,t3-stack | Reworkd | https://reworkd.ai | San Francisco, CA | [email protected] | https://reworkd.ai | San Francisco, CA | [email protected] | Pushing the Boundaries of OpenSource Agents | ||
https://github.com/pythagora-io/gpt-pilot | Pythagora-io/gpt-pilot | The first real AI developer | Python | 29208 | ai,codegen,coding-assistant,developer-tools,gpt-4,research-project | ||||||||||
https://github.com/opendevin/opendevin | OpenDevin/OpenDevin | 🐚 OpenDevin: Code Less, Make More | Python | 29089 | agent,artificial-intelligence,llm | ||||||||||
https://github.com/microsoft/autogen | microsoft/autogen | A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap | Jupyter Notebook | 28810 | agent-based-framework,agent-oriented-programming,agentic,agentic-agi,chat,chat-application,chatbot,chatgpt,gpt,gpt-35-turbo,gpt-4,llm-agent,llm-framework,llm-inference,llmops | Microsoft | https://opensource.microsoft.com | Redmond, WA | [email protected] | https://opensource.microsoft.com | Redmond, WA | [email protected] | Open source projects and samples from Microsoft | ||
https://github.com/milvus-io/milvus | milvus-io/milvus | A cloud-native vector database, storage for next generation AI applications | Go | 28510 | anns,cloud-native,distributed,embedding-database,embedding-similarity,embedding-store,faiss,golang,hnsw,image-search,llm,nearest-neighbor-search,tensor-database,vector-database,vector-search,vector-similarity,vector-store | The Milvus Project | https://milvus.io/ | San Francisco | [email protected] | https://milvus.io/ | San Francisco | [email protected] | The open source vector database designed for AI applications | ||
https://github.com/flowiseai/flowise | FlowiseAI/Flowise | Drag & drop UI to build your customized LLM flow | TypeScript | 28097 | artificial-intelligence,chatgpt,javascript,large-language-models,llm,low-code,no-code,react,typescript | FlowiseAI | https://flowiseai.com/ | [email protected] | https://flowiseai.com/ | [email protected] | Open source UI visual tool to build LLM apps | ||||
https://github.com/openbmb/chatdev | OpenBMB/ChatDev | Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration) | Shell | 24619 | OpenBMB | https://www.openbmb.cn | [email protected] | https://www.openbmb.cn | [email protected] | OpenBMB (Open Lab for Big Model Base), founded by ModelBest Inc (面壁智能) & TsinghuaNLP, aims to build foundation models and systems towards AGI. | |||||
https://github.com/microsoft/jarvis | microsoft/JARVIS | JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf | Python | 23411 | deep-learning,platform,pytorch | Microsoft | https://opensource.microsoft.com | Redmond, WA | [email protected] | https://opensource.microsoft.com | Redmond, WA | [email protected] | Open source projects and samples from Microsoft | ||
https://github.com/logspace-ai/langflow | langflow-ai/langflow | ⛓️ Langflow is a visual framework for building multi-agent and RAG applications. It's open-source, Python-powered, fully customizable, model and vector store agnostic. | JavaScript | 22601 | chatgpt,generative-ai,large-language-models,react-flow | Langflow | https://www.langflow.org/ | Brazil | [email protected] | https://www.langflow.org/ | Brazil | [email protected] | Discover a simpler & smarter way to build around Foundation Models | ||
https://github.com/janhq/jan | janhq/jan | Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM) | TypeScript | 21153 | electron,gpt,llama2,llamacpp,localai,self-hosted | Jan | https://jan.ai | [email protected] | https://jan.ai | [email protected] | An open source alternative to OpenAI that runs on your own computer or server | ||||
https://github.com/getcursor/cursor | getcursor/cursor | The AI Code Editor | 20710 | Cursor | https://cursor.com/ | [email protected] | https://cursor.com/ | [email protected] | The AI Code Editor | ||||||
https://github.com/tabbyml/tabby | TabbyML/tabby | Self-hosted AI coding assistant | Rust | 20127 | ai,codegen,coding-assistant,coding-language,developer-experience,developer-tools,gen-ai,ide,llms | ||||||||||
https://github.com/pydantic/pydantic | pydantic/pydantic | Data validation using Python type hints | Python | 19893 | hints,json-schema,parsing,pydantic,python,python310,python311,python312,python37,python38,python39,validation | Pydantic | https://pydantic.dev | United Kingdom | https://pydantic.dev | United Kingdom | Pydantic brings schema and sanity to your data. | ||||
https://github.com/danielmiessler/fabric | danielmiessler/fabric | fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere. | Python | 19836 | ai,augmentation,flourishing,life,work | Unsupervised Learning | https://danielmiessler.com/upgrade | SF Bay Area | [email protected] | Founder of Unsupervised Learning. Creator of Fabric and Threshold. Working towards Human 3.0 so we can survive and thrive as humans after AI. | |||||
https://github.com/yoheinakajima/babyagi | yoheinakajima/babyagi | Python | 19750 | Untapped Capital | http://yoheinakajima.com | I don't know what I'm doing here, don't judge me. | |||||||||
https://github.com/promtengineer/localgpt | PromtEngineer/localGPT | Chat with your documents on your local device using GPT models. No data leaves your device and 100% private. | Python | 19663 | https://www.youtube.com/@engineerprompt | Building Cool Stuff! | |||||||||
https://github.com/guidance-ai/guidance | guidance-ai/guidance | A guidance language for controlling large language models. | Jupyter Notebook | 18312 | |||||||||||
https://github.com/stitionai/devika?tab=readme-ov-file#demos | 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. Devika aims to be a competitive open-source alternative to Devin by Cognition AI. | Python | 18002 | stition | https://stition.ai | [email protected] | https://stition.ai | [email protected] | the pre-agi security company. | |||||
https://github.com/mem0ai/mem0 | mem0ai/mem0 | The memory layer for Personalized AI | Python | 17880 | ai,application,chatbots,chatgpt,embeddings,llm,long-term-memory,memory,python,rag,vector-database | Mem0 | https://mem0.ai | United States of America | [email protected] | https://mem0.ai | United States of America | [email protected] | The Memory Layer for Personalized AI | ||
https://github.com/joaomdmoura/crewai | crewAIInc/crewAI | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. | Python | 17703 | agents,ai,ai-agents,llms | crewAI | https://crewai.com | United States of America | https://crewai.com | United States of America | |||||
https://github.com/joonspk-research/generative_agents | joonspk-research/generative_agents | Generative Agents: Interactive Simulacra of Human Behavior | 15957 | http://www.joonsungpark.com/ | CS Ph.D. student at StanfordHCI + StanfordNLP. | ||||||||||
https://github.com/labring/fastgpt | labring/FastGPT | FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration. | TypeScript | 15829 | gpt,gpt-35-turbo,gpt-4,gpt35,llm,nextjs,openai,rag,react | labring | [email protected] | [email protected] | wallfacer lab | ||||||
https://github.com/transformeroptimus/superagi | TransformerOptimus/SuperAGI | <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably. | Python | 15041 | agents,agi,ai,artificial-general-intelligence,artificial-intelligence,autonomous-agents,gpt-4,hacktoberfest,llm,llmops,nextjs,openai,pinecone,python,superagi | I’m | |||||||||
https://github.com/stanfordnlp/dspy | stanfordnlp/dspy | DSPy: The framework for programming—not prompting—foundation models | Python | 14885 | Stanford NLP | nlp.stanford.edu | Stanford, CA | nlp.stanford.edu | Stanford, CA | ||||||
https://github.com/deepset-ai/haystack | deepset-ai/haystack | :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots. | Python | 14843 | ai,bert,chatgpt,generative-ai,gpt-3,information-retrieval,language-model,large-language-models,llm,machine-learning,nlp,python,pytorch,question-answering,rag,retrieval-augmented-generation,semantic-search,squad,summarization,transformers | deepset | https://deepset.ai | Berlin, Germany | [email protected] | https://deepset.ai | Berlin, Germany | [email protected] | Building enterprise search systems powered by latest NLP & open-source. | ||
https://github.com/paul-gauthier/aider | paul-gauthier/aider | aider is AI pair programming in your terminal | Python | 14599 | chatgpt,claude-3,cli,command-line,gpt-3,gpt-35-turbo,gpt-4,gpt-4o,openai,opus | ||||||||||
https://github.com/continuedev/continue | continuedev/continue | ⏩ Continue is the 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 | TypeScript | 13823 | ai,chatgpt,copilot,developer-tools,intellij,jetbrains,llm,open-source,openai,pycharm,software-development,visual-studio-code,vscode | Continue | https://continue.dev | https://continue.dev | The leading open-source AI code assistant | ||||||
https://github.com/chroma-core/chroma | chroma-core/chroma | the AI-native open-source embedding database | Rust | 13811 | document-retrieval,embeddings,llms | Chroma | trychroma.com | United States of America | trychroma.com | United States of America | |||||
https://github.com/vincigit00/scrapegraph-ai | ScrapeGraphAI/Scrapegraph-ai | Python scraper based on AI | Python | 13520 | automated-scraper,gpt-3,gpt-4,llama3,llm,machine-learning,sc,scraping,scraping-python,scrapingweb | ||||||||||
https://github.com/assafelovic/gpt-researcher | assafelovic/gpt-researcher | GPT based autonomous agent that does online comprehensive research on any given topic | Python | 13368 | ai,autonomous-agent,gpt-4,gpt-researcher,openai,python,research-assistant,web-search | www.assafelovic.com | New York | [email protected] | AI Tech Leader | ||||||
https://github.com/microsoft/graphrag | microsoft/graphrag | A modular graph-based Retrieval-Augmented Generation (RAG) system | Python | 13118 | gpt,gpt-4,gpt4,graphrag,llm,llms,rag | Microsoft | https://opensource.microsoft.com | Redmond, WA | [email protected] | https://opensource.microsoft.com | Redmond, WA | [email protected] | Open source projects and samples from Microsoft | ||
https://github.com/eosphoros-ai/db-gpt | eosphoros-ai/DB-GPT | AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents | Python | 12706 | agents,bgi,database,gpt,gpt-4,langchain,llm,private,rag,security,vicuna | eosphoros | http://docs.dbgpt.site | [email protected] | http://docs.dbgpt.site | [email protected] | Revolutionizing Database Interactions with Private LLM Technology | ||||
https://github.com/neonbjb/tortoise-tts | neonbjb/tortoise-tts | A multi-voice TTS system trained with an emphasis on quality | Jupyter Notebook | 12547 | OpenAI | nonint.com | CO | Latent Analyst, Entropy Wrangler | |||||||
https://github.com/princeton-nlp/swe-agent | princeton-nlp/SWE-agent | SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run. | Python | 12131 | agent,agent-based-model,ai,developer-tools,llm,lms | Princeton Natural Language Processing | http://nlp.cs.princeton.edu | http://nlp.cs.princeton.edu | |||||||
https://github.com/langchain-ai/langchainjs | langchain-ai/langchainjs | 🦜🔗 Build context-aware reasoning applications 🦜🔗 | TypeScript | 11949 | LangChain | https://www.langchain.com | United States of America | [email protected] | https://www.langchain.com | United States of America | [email protected] | ||||
https://github.com/smol-ai/developer | smol-ai/developer | the first library to let you embed a developer agent in your own app! | Python | 11754 | smol.ai | https://twitter.com/SmolModels | United States of America | https://twitter.com/SmolModels | United States of America | a simple, safe, speedy org for smol ai enjoyers | |||||
https://github.com/cpacker/memgpt | cpacker/MemGPT | Create LLM agents with long-term memory and custom tools 📚🦙 | Python | 10934 | chat,chatbot,gpt,gpt-4,llm,llm-agent | UC Berkeley | charlespacker.com | Berkeley, CA | [email protected] | 🌊🏄🌊🌊🌊 | |||||
https://github.com/berriai/litellm | BerriAI/litellm | Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs) | Python | 10805 | anthropic,langchain,langchain-python,llm,llmops,openai | Berri AI | https://docs.litellm.ai/docs/ | [email protected] | https://docs.litellm.ai/docs/ | [email protected] | The fastest way to take your LLM app to production | ||||
https://github.com/phidatahq/phidata | phidatahq/phidata | Build AI Assistants with memory, knowledge and tools. | Python | 10758 | ai,aws,developer-tools,gpt-4,llm,llmops,python | phidata | https://phidata.com | https://phidata.com | Add memory, knowledge and tools to LLMs | ||||||
https://github.com/weaviate/weaviate | weaviate/weaviate | Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database. | Go | 10389 | approximate-nearest-neighbor-search,generative-search,grpc,hnsw,hybrid-search,image-search,information-retrieval,mlops,nearest-neighbor-search,neural-search,recommender-system,search-engine,semantic-search,semantic-search-engine,similarity-search,vector-database,vector-search,vector-search-engine,vectors,weaviate | Weaviate | https://weaviate.io | worldwide | [email protected] | https://weaviate.io | worldwide | [email protected] | Weaviate creates database software like the Weaviate vector search engine | ||
https://github.com/plandex-ai/plandex | plandex-ai/plandex | AI driven development in your terminal. Designed for large, real-world tasks. | Go | 10075 | ai,ai-agents,ai-developer-tools,ai-tools,cli,command-line,developer-tools,git,golang,gpt-4,llm,openai,polyglot-programming,terminal,terminal-based,terminal-ui | plandex-ai | [email protected] | [email protected] |