langflow-ai/langflow
Langflow is a powerful open-source platform for building, testing, and deploying AI-powered agents and workflows with visual authoring, multi-agent orchestration, and enterprise-ready features.
Awesome ChatGPT › Python library, sdk or frameworks
Python library, sdk or frameworks
nomic-ai/gpt4all
GPT4All is an open-source project that enables running large language models locally on various devices without requiring API calls or GPUs, providing private, offline AI capabilities with broad platform support and integrations.
xtekky/gpt4free
gpt4free is a proof-of-concept API package that enables multi-provider AI requests with features like load balancing, request flow control, and supports text and image generation through various powerful language models.
infiniflow/ragflow
RAGFlow is an open-source Retrieval-Augmented Generation engine that leverages deep document understanding and Large Language Models to provide accurate, citation-backed question-answering from complex and diverse data sources.
zylon-ai/private-gpt
PrivateGPT is a privacy-focused AI project that enables offline interaction with documents using Large Language Models through a secure, private API and RAG pipeline.
microsoft/autogen
AutoGen is a Microsoft-developed framework for building and managing multi-agent AI applications that operate autonomously or alongside humans, featuring layered APIs, developer tools, and no-code interfaces.
QuivrHQ/quivr
Quivr is an opinionated and customizable Retrieval-Augmented Generation framework that enables easy integration of generative AI into applications, supporting multiple LLMs, vector stores, and file types to build an AI-powered second brain.
Vision-CAIR/MiniGPT-4
MiniGPT-4 and MiniGPT-v2 are open-source projects that enhance vision-language understanding and multi-task learning using advanced large language models like Vicuna and Llama 2, enabling sophisticated AI-driven vision-language interactions.
chroma-core/chroma
Chroma is an open-source embedding database that enables efficient storage, management, and similarity querying of embeddings to build AI-native applications with memory, supporting Python and JavaScript clients and integrating with popular AI frameworks.
deepset-ai/haystack
Haystack is an AI orchestration framework for building customizable, production-ready LLM applications that integrate models, vector databases, and file converters into pipelines for tasks like retrieval-augmented generation, question answering, semantic search, and conversational agents.
AI4Finance-Foundation/FinGPT
FinGPT is an open-source project providing specialized large language models for finance, enabling cost-effective, adaptable, and personalized AI-driven financial analysis and predictions.
BlinkDL/RWKV-LM
RWKV is a novel RNN-based large language model architecture that combines transformer-level performance with linear time complexity and constant memory usage, enabling efficient and scalable training and inference.
FujiwaraChoki/MoneyPrinter
MoneyPrinter automates the creation of YouTube Shorts videos by generating content based on user-provided topics using MoviePy.
Chainlit/chainlit
Chainlit is an open-source Python framework that enables rapid development of production-ready conversational AI applications with seamless integration of various AI tools and services.
BlinkDL/ChatRWKV
ChatRWKV is an open-source conversational AI project powered by the RWKV 100% RNN language model, offering a faster and more VRAM-efficient alternative to transformer-based models like ChatGPT.
togethercomputer/OpenChatKit
OpenChatKit is an open-source toolkit for training, fine-tuning, and deploying large-scale instruction-tuned language models with integrated retrieval and moderation capabilities.
OptimalScale/LMFlow
LMFlow is an extensible and efficient toolkit for fine-tuning and inference of large foundation models, supporting advanced features and a wide range of state-of-the-art language models to democratize access to large-scale AI.
zilliztech/GPTCache
GPTCache is a semantic caching library that reduces API costs and improves response speed for large language model queries by storing and retrieving cached responses based on semantic similarity.
openai/point-e
Point-E is a system for generating 3D point clouds from complex prompts such as text and images, with tools for converting point clouds into meshes and evaluating model quality.
open-compass/opencompass
OpenCompass is a versatile and powerful evaluation platform for large language models, supporting numerous models and datasets with advanced features for comprehensive NLP model assessment.
kyegomez/swarms
Swarms is an enterprise-grade, production-ready multi-agent orchestration framework designed to enable scalable, secure, and efficient AI workflows with extensive integration and developer tools.
marqo-ai/marqo
Marqo is an end-to-end vector search engine that unifies embedding generation and search for text and images, providing a comprehensive, scalable, and easy-to-use solution with cloud and framework integrations.
Drakkar-Software/OctoBot
OctoBot is an open-source, highly customizable cryptocurrency trading bot that enables users to automate, backtest, and optimize trading strategies across multiple exchanges using advanced tools like AI and technical analysis.
h2oai/h2o-llmstudio
H2O LLM Studio is a no-code GUI framework for fine-tuning large language models using advanced techniques like LoRA, 8-bit training, and preference optimization, with integrated performance tracking and model sharing capabilities.
kyegomez/tree-of-thoughts
Tree of Thoughts is a plug-and-play implementation that enhances large language model reasoning by up to 70% through a multi-agent, tree-structured problem-solving algorithm.
rawandahmad698/PyChatGPT
PyChatGPT is a Python client for the unofficial ChatGPT API that features automatic token regeneration, conversation tracking, proxy support, and seamless login without a browser, enabling programmatic interaction with ChatGPT sessions.
promptslab/Promptify
Promptify is an open-source Python library that enables prompt engineering and structured output generation for various NLP tasks using large language models like GPT and PaLM.
AI4Finance-Foundation/FinRobot
FinRobot is an open-source AI agent platform that leverages large language models and diverse AI technologies to provide advanced financial analysis, decision-making, and actionable insights through a modular and extensible ecosystem.
eth-sri/lmql
LMQL is a Python-based programming language designed for constraint-guided and efficient interaction with large language models, enabling advanced control and integration of LLMs within traditional programming workflows.
shroominic/codeinterpreter-api
An open-source implementation of the ChatGPT Code Interpreter enabling sandboxed Python code execution with features like dataset analysis, image manipulation, and scalable production deployment using CodeBox API.
langroid/langroid
Langroid is a Python framework that enables building LLM-powered applications using a multi-agent programming paradigm for collaborative problem solving.
NExT-GPT/NExT-GPT
NExT-GPT is an end-to-end multimodal large language model that processes and generates any combination of text, image, video, and audio inputs and outputs, enabling versatile AI interactions across multiple modalities.
mukulpatnaik/researchgpt
ResearchGPT is a FastAPI-based LLM research assistant that enables interactive conversations with research papers by extracting text from PDFs, generating embeddings, and answering user queries with source references.
minimaxir/simpleaichat
simpleaichat is a Python package that simplifies interfacing with chat apps like ChatGPT and GPT-4, offering robust features for efficient, customizable AI chat sessions with minimal code complexity.
BeastByteAI/scikit-llm
Scikit-LLM integrates large language models like ChatGPT into scikit-learn to enhance text analysis and enable zero-shot classification within familiar machine learning workflows.
EvolvingLMMs-Lab/Otter
Otter is a multi-modal model based on OpenFlamingo, trained on the MIMIC-IT dataset, showcasing advanced instruction-following and in-context learning capabilities with support for high-resolution visual inputs and extensive benchmarking.
open-compass/VLMEvalKit
VLMEvalKit is an open-source evaluation toolkit that supports over 220 large vision-language models and 80+ benchmarks, enabling streamlined and standardized evaluation of multi-modal AI models.
reloadware/reloadium
Reloadium is an advanced Python tool that provides hot reloading, profiling, and AI integration to enhance development productivity across various frameworks and environments.
THUDM/AgentBench
AgentBench is a comprehensive benchmark designed to evaluate large language models as autonomous agents across diverse environments, including novel and existing domains, with extensions for visual multimodal agents.
PhoebusSi/Alpaca-CoT
Alpaca-CoT is a unified instruction-tuning platform that integrates instruction data, multiple large language models, and parameter-efficient tuning methods to facilitate easy and efficient fine-tuning and research.
microsoft/promptbench
PromptBench is a unified evaluation framework for large language models that provides tools for performance assessment, prompt engineering, adversarial robustness testing, and dynamic and efficient multi-prompt evaluation across diverse datasets and models.
thunlp/UltraChat
UltraChat is a project offering a large-scale, diverse multi-round dialogue dataset and state-of-the-art chat language models, including UltraLM, which ranks top among open-source models on the AlpacaEval leaderboard.
zjunlp/EasyEdit
EasyEdit is an easy-to-use knowledge editing framework for large language models that enables precise, flexible, and real-time modification of LLM knowledge without retraining.
paulpierre/RasaGPT
RasaGPT is a headless chatbot platform that integrates Rasa with large language models using Langchain, providing a flexible, multi-platform conversational AI solution with document training, embedding search, and API support.
jackmpcollins/magentic
Magentic is a Python library that enables seamless integration of Large Language Models into Python code by providing decorators to create functions with structured LLM outputs, supporting advanced features like streaming, function calling, and observability.
lifeiteng/vall-e
An unofficial PyTorch implementation of VALL-E, a zero-shot text-to-speech synthesizer that preserves speaker identity, with training and inference support on single GPU.
protectai/llm-guard
LLM Guard is a comprehensive security toolkit by Protect AI designed to safeguard interactions with Large Language Models by providing sanitization, harmful language detection, data leakage prevention, and prompt injection resistance through a variety of input and output scanners.
QIN2DIM/hcaptcha-challenger
hCaptcha Challenger is an advanced AI-driven project that uses multimodal large language models to solve various hCaptcha challenges without relying on third-party services or scripts.
melih-unsal/DemoGPT
DemoGPT is an all-in-one open-source library that automates the creation of interactive LLM-based applications by generating LangChain code and transforming it into user-friendly Streamlit apps.
OpenMotionLab/MotionGPT
MotionGPT is a unified motion-language generation model that treats human motion as a language, enabling multiple motion-related tasks with state-of-the-art performance.
richardyc/Chrome-GPT
Chrome-GPT is an experimental AutoGPT agent that autonomously controls and interacts with the Chrome browser to perform web automation tasks using AI-driven agents.
Farama-Foundation/chatarena
ChatArena is a versatile library that creates multi-agent language game environments to develop and study communication and collaboration capabilities of large language model agents like GPT-3 and GPT-4.
farizrahman4u/loopgpt
LoopGPT is a modular and extensible Auto-GPT framework implemented as a Python package, designed for building flexible AI agents with GPT models and supporting custom tools, human feedback, and state serialization.
hiyouga/FastEdit
FastEdit is a tool for rapidly editing large language models to inject fresh and customized knowledge efficiently within 10 seconds using the ROME algorithm.
travisvn/openai-edge-tts
OpenAI-Compatible Edge-TTS API is a free, high-quality text-to-speech API that mimics OpenAI's TTS endpoint, offering multiple voices, audio formats, and real-time streaming, deployable via Docker or Python environments.
lupantech/chameleon-llm
Chameleon is a compositional reasoning framework that enhances large language models like GPT-4 by integrating various external tools to improve performance on complex tasks such as scientific question answering and table-based math problems.
BAAI-DCAI/Bunny
Bunny is a family of lightweight and powerful multimodal models that integrate various vision encoders and language backbones to deliver high-performance vision-language understanding and generation, supporting high-resolution inputs and accessible through popular AI platforms.
taranjeet/unofficial-chatgpt-api
An unofficial ChatGPT API using Playwright and Chromium to provide a local server for interacting with ChatGPT via a simple API endpoint for development purposes.
voidful/TextRL
TextRL is a Python library that enhances text generation models using reinforcement learning with human feedback, supporting various Hugging Face transformer models and customizable training.
labteral/chatgpt-python
An unofficial Python SDK that enables easy integration of OpenAI's ChatGPT into Python projects with CLI and streaming support.
Writesonic/GPTRouter
GPTRouter is a unified AI model gateway that manages multiple large language and image generation models, ensuring fast, reliable, and uninterrupted AI service through smart fallbacks and a universal API.