#open-source

Dify is an open-source platform offering features like AI workflows, RAG pipeline, and model management, supporting LLMs such as GPT and Llama3. Its APIs and visual tools streamline integration and development for efficient AI solutions.

DeepSpeech is an open-source speech-to-text engine powered by machine learning, inspired by Baidu's Deep Speech research. It employs TensorFlow, providing comprehensive documentation for installation, usage, and model training at deepspeech.readthedocs.io. Access the latest releases, pre-trained models, and contribution guidelines on GitHub. This project is ideal for developers in search of reliable and scalable speech recognition solutions.

Keras-llm-robot utilizes Langchain and Fastchat frameworks in a Streamlit UI for offline deployment of Hugging Face models, with features like model integration, multimodal support, and customizations including quantization and fine-tuning. It also offers tools for retrieval, speech, and image recognition, plus environment setup guides for multiple OSs, ideal for developers exploring AI model deployment.

RAGFlow is an open-source engine improving the RAG workflow via deep document understanding. It effectively extracts knowledge from unstructured data using large language models, providing accurate question-answering with reliable citations. Compatible with varied data formats, including Word documents, slides, and scanned files, it features intelligent document chunking to enhance data retrieval. RAGFlow simplifies integration with user-friendly APIs, serving as a dependable tool for both personal and business applications in automating the RAG process.

MONAI, built on PyTorch, is an open-source framework designed for deep learning in medical imaging. It offers state-of-the-art workflows with flexible pre-processing, compositional APIs, and domain-specific tools. Supporting multi-GPU environments, MONAI promotes collaboration among researchers. Its Model Zoo and extensive documentation streamline integration and use, making MONAI a valuable resource in healthcare.

Evidently is an open-source framework built to evaluate, test, and monitor both predictive and generative ML and LLM systems. It provides over 100 metrics, including those for data drift detection, classification, and regression. The tool supports exploratory analysis and real-time monitoring with outputs in formats like JSON and HTML. Its modular architecture allows for custom metrics integration with existing data pipelines. Available as a self-hosted or cloud service, it includes features such as user management and alerting.

DeepPavlov 1.0 is an intuitive open-source NLP framework using PyTorch and transformers, designed to provide seamless model deployment for practitioners with little NLP background. It supports diverse applications with pre-trained models, simple installation, and various interfaces across platforms.

Writer Framework streamlines AI app development with its open-source, state-driven structure. A visual editor and Python backend allow for efficient, complex builds without CSS. Real-time synchronization and easy installation enhance developer experience across platforms.

CAMEL is an open-source project aimed at understanding the scaling laws of AI agents by exploring their behaviors and capabilities. It supports a variety of agents, tasks, and simulated environments to advance research. The project offers installation via PyPI and source code, and facilitates integration with platforms like HuggingFace. Comprehensive documentation and examples assist users in setup and model deployment, inviting contributions to the study of AI agent dynamics.

llm.report offers open-source tools for logging and analytics of OpenAI ChatGPT API requests, aiding in cost analysis and prompt optimization through features like API analytics and user analytics. Suitable for self-hosted and cloud setups, it uses technologies like Next.js and Postgres. Although not actively maintained, it provides valuable insights into AI app expenditures and usage impacts.

TorchRL is a Python-first, efficient, and modular open-source Reinforcement Learning (RL) library specifically designed for seamless integration with the PyTorch ecosystem. It offers a versatile architecture with tools like distributed data collectors, replay buffers, and `TensorDict`, which optimize RL research. The library supports major environment libraries and provides extensive tutorials, documentation, and real-world application examples, making it an invaluable resource for implementing RL solutions across various domains.

Athena is an open-source engine for end-to-end speech processing, suitable for both industrial and research applications. Built on Tensorflow, it includes models for tasks such as ASR, TTS, VAD, and KWS. Athena supports hybrid attention/CTC models, multi-GPU training with Horovod, and WFST-based decoding. Recent enhancements allow Tensorflow C++ deployment and introduce models like AV-Transformer and Conformer-CTC. The platform aims to make advanced speech processing accessible to all, backed by thorough documentation and community resources.

Discover how developers navigate the fast-paced DevAI sector by choosing between open-source and commercial LLMs for software development. This guide details vital factors, practical use cases, and top models including Code Llama, GPT-4, and Claude 2. Learn about deployment strategies and key considerations to optimize development workflows with the most suitable LLMs.

Explore an open-source AI chat platform designed for easy deployment and enhanced mobile compatibility. Experience the convenience of a hosted version or opt for local or cloud setup using Supabase. Perfect for developers and tech enthusiasts, this project offers straightforward customization with comprehensive guidance on backend integration and environment setup. Join community discussions to stay updated with recent improvements and contribute to ongoing innovation.

LLM Engine is a comprehensive tool for deploying and customizing large language models such as LLaMA, MPT, and Falcon. It supports hosted infrastructure or Kubernetes deployment, offering scalable solutions with ready-to-use APIs, efficient inference, and open-source integrations. Upcoming documentation for K8s installation and cost-effective strategies aim to optimize resources further. Explore the potential of AI models with LLM Engine's detailed guidance and flexible deployment options.

IOPaint is a free, open-source tool for seamless inpainting and outpainting using cutting-edge AI models. Compatible with various OS including Windows and macOS, it features object erasure, text overlay, and object replacement. Utilize plugins for super-resolution and image segmentation. Ideal for any user looking to enhance images effortlessly.

Botpress Cloud offers a comprehensive platform for developing AI-driven chatbots and virtual assistants. Featuring OpenAI technology integration, it enables rapid chatbot creation and deployment through Botpress's extensive SDK and CLI tools. The platform also provides detailed documentation and community support for building tailored integrations aligned with business requirements. Whether creating bespoke chatbots or engaging with the Botpress open-source community, developers are equipped to advance chatbot development and functionality.

Vanna is an open-source Python framework enabling high-accuracy SQL query generation through retrieval-augmented generation, suitable for complex datasets. It ensures data privacy and integrates easily into Jupyter Notebook. Ideal for developers seeking precise and innovative data solutions.

The Open-Sora Plan, spearheaded by Peking University and TuShare's AIGC Lab, seeks to reproduce 'Sora' with a focus on simplicity and scalability. The project harnesses Huawei Ascend AI for comprehensive training and inference, achieving video quality that meets industry standards. It encourages contributions from the open-source community to address gaps and improve the system continuously. Upcoming updates will feature multi-modal support via MindSpeed-MM and enhanced distributed training capabilities.

Chidori is an open-source platform offering a reactive runtime for developing AI agents. It supports Python and JavaScript execution, providing detailed monitoring and state management. Key features include time-travel debugging and visual representation for effective state control, enhancing integration with existing systems.

ShareGPT was a Chrome Extension designed for sharing ChatGPT conversations, featuring tools for exploring examples, saving, and commenting before its 2024 discontinuation. Its innovative use of Next.js, TypeScript, and Tailwind guaranteed a seamless user experience, leaving a notable legacy despite limited current functionality.

Explore a versatile open-source platform with tools for prompt engineering, evaluation, and deployment of LLM applications. It facilitates team collaboration, prompt experimentation, human annotation collection, and one-click application deployment. Compatible with any LLM workflow and integrates with frameworks such as Langchain and LlamaIndex. Boost productivity with user-friendly management tools and connect with an active community. Access comprehensive documentation and enterprise support, and participate in the platform's continuous evolution.

E2B offers a robust open-source infrastructure for the secure execution of AI-generated code in isolated cloud environments. The platform supports both JavaScript and Python through user-friendly SDKs, facilitating easy initiation and management of sandboxes. With comprehensive documentation and a rich cookbook filled with examples across various AI frameworks, E2B caters to developers seeking a safe and seamless approach to AI code execution.

CARLA is an open-source simulator tailored for autonomous driving research. It aids in development, training, and validation of autonomous systems while offering digital assets such as urban layouts and vehicles. CARLA supports customizable sensor setups and environmental conditions, and is compatible with Unreal Engine 4 and 5. It integrates with various driving stacks and reinforcement learning models, and runs on Linux and Windows with specific hardware needs. Detailed documentation and community resources are available.

Friend OS 'Helium' v1.3.0 is a versatile, cloud-based system that allows cross-device access and collaboration, independent of specific hardware. By utilizing advanced web technologies, it ensures seamless use across devices from smartphones to VR. Installation is simple and requires only an internet connection. Users can customize their experience with features like Friend Network and Friend Chat, focusing on security and autonomy for both personal and enterprise uses.

Delve into a column-oriented database management system renowned for its real-time data processing. With effortless installation across Linux, macOS, and FreeBSD, access extensive resources like tutorials and documentation, backed by a robust community. Engage in monthly calls and global meetups to discuss updates and gain insights. Stay informed on the latest with expert talks, and contribute to a pioneering team in analytics.

Distilabel is a framework for creating synthetic data and obtaining AI feedback, serving those developing NLP and LLM projects. It facilitates the creation of high-quality, varied datasets using established research techniques. The framework allows engineers to concentrate on enhancing data quality and controlling model tuning, integrating feedback across LLM providers with a single API. As an open-source, community-supported project, Distilabel ensures scalable and adaptable data generation pipelines to enhance the efficiency and quality of AI development.

Streamlit provides an efficient platform for turning Python scripts into interactive web applications. Suitable for dashboards, reports, or chat applications, it enables quick prototyping and immediate feedback. With straightforward Pythonic code and real-time editing, Streamlit is supported by an open-source community. The Community Cloud platform facilitates easy deployment and management of applications. Simple installation and rich resources, including Streamlit Components and an inspiring gallery, support extended functionality. Streamlit is free under the Apache 2.0 license, offering a budget-friendly option for data applications.

ChatTTS is an advanced TTS model optimized for natural dialogue with multi-speaker and prosody control features. It supports over 100,000 hours of training data in multiple languages, surpassing many open-source models in quality. Pretrained models are available for educational and research use, enabling seamless integration into AI systems. Discover its features and ethical guidelines.

The h2oGPT project provides users with an open-source platform to query and summarize private documents using local GPT LLMs such as LLaMa2 and Mistral. It features offline database support, semantic chunking, and HYDE retrieval, all available through Gradio or CLI interfaces. The tool includes advanced capabilities like voice control, AI-assisted management, and multimedia generation, ensuring security and compatibility across major operating systems. Docker is recommended for full installation, offering extensive model support for seamless user experience.

VisualGLM-6B is a multi-modal dialog language model supporting images, Chinese, and English, based on ChatGLM-6B with 7.8 billion parameters including visual capabilities from BLIP2-Qformer. The model achieves visual-linguistic interoperability and can be deployed on consumer GPUs by using quantized accuracy. It is pre-trained on 330 million captioned images, optimizing alignment across languages while adhering to open-source protocols. Limitations include image specificity and potential model hallucinations, with plans for future improvements.

Explore an open-source RPA tool to automate tasks across websites, apps, and command lines effortlessly. Compatible with Windows, macOS, and Linux, it supports 23 languages, offers visual automation, and integrates with MS Office. Operates securely on user computers. Access tutorials and join a global community for enhanced productivity.

MaxText is an open-source LLM that enables efficient training and inference on Google Cloud TPUs and GPUs. With support for models such as Llama2, Mistral, and Gemma, it provides robust scalability and high Model Flops Utilization through Jax and XLA compiler integration, making it adaptable for diverse LLM applications.

Khoj is an open-source AI tool that enhances both personal and business functions. Users can engage with various language models like llama3 and GPT, importing data from the web and different file types, such as PDF and Word. Compatible with web and desktop apps, it also links with services like WhatsApp. Users can build custom AI agents to perform tasks like research and receive notifications, and Khoj's semantic search improves document accessibility, enhancing learning. It supports both private self-hosting and cloud-based use.

Pezzo provides a cloud-native, open-source platform designed to enhance AI operations. It allows for efficient monitoring, troubleshooting, and prompt management, significantly reducing costs and latency. Pezzo's infrastructure supports various clients like Node.js, Python, and LangChain using PostgreSQL, ClickHouse, Redis, and Supertokens. Comprehensive documentation and community resources make it developer-friendly and conducive for AI innovation.

Webots is a versatile platform for modeling, programming, and simulating a variety of robotic and mechanical systems. First developed at EPFL and later enhanced by Cyberbotics, this open-source simulator supports both industry and academia with its customer service and training offerings. The platform provides pre-compiled binaries and source code options, along with online simulations and competitive events like the IROS 2023 Simulated Humanoid Robot Wrestling Competition. Engage with a robust community via GitHub discussions and leverage continuous integration for consistent testing across operating systems.

Wukong-robot is an open-source Chinese voice assistant designed for developing customizable smart speakers. With modular functionality, Chinese language support, and compatibility with devices such as Xiaomi and Siri, it supports offline wake-up and BCI technologies. As of March 2023, it has been installed on over 13,000 devices, accumulating over 700,000 wake-ups. With integration for smart home systems and an open API, it continues to evolve with regular updates.

AutoGPT4All provides bash and Python scripts for easily setting up AutoGPT with the GPT4All model on LocalAI servers. This allows executing queries on an open-source licensed model offline and without restriction. Suitable for integrating AI models into applications, it offers customization through options like model URL specifications and is easy to remove. Although mainly tested on macOS, it is also suitable for Linux and Windows. Contributions are encouraged via the fork, modify, and pull request method under the MIT License.

This open-source platform simplifies comparative prompt engineering and LLM response evaluation. It enables users to simultaneously query multiple LLMs, offering quick comparisons in response quality across various prompts and models. Supporting model providers like OpenAI and Google PaLM2, the platform provides robust tools for setting evaluation metrics and visualizing results. With features like prompt permutations, chat turns, and evaluation nodes, it facilitates a thorough analysis of prompt and model efficiency. Encouraging experimentation and sharing, it includes functionalities for exporting results and integrating evaluations into research projects, making it a practical tool for researchers.

vLLM provides efficient LLM inference and serving solutions with leading-edge throughput and seamless memory management via PagedAttention. It integrates smoothly with popular models and supports diverse hardware platforms and decoding algorithms, ensuring flexible and high-performance deployments. Updates include Llama 3.1 integration, enhanced quantization, and comprehensive support for Hugging Face models. As a community-driven project, vLLM benefits from industry sponsorships, promoting continual improvement through collaboration and feedback.

Cody is an open-source AI coding assistant that enhances coding efficiency by utilizing AI and codebase context. It integrates with IDEs to help write, understand, and fix code. Features include chat-based inquiries, autocomplete, inline edits, and more. Supporting models like Anthropic Claude 3.5 Sonnet and OpenAI GPT-4o, Cody is suitable for individual and enterprise use, providing free model access to developers. It streamlines coding tasks by leveraging code context, enhancing productivity.

Chroma is an open-source embedding database optimized for LLM application development in Python and JavaScript. It features a simple in-memory setup for prototyping with options for data persistence and supports powerful document management and querying tools via a minimalist API. Fully typed, tested, and documented, Chroma integrates easily with systems such as LangChain and LlamaIndex, facilitating natural language processing and custom embedding. Licensed under Apache 2.0, it fosters rapid development and scalability from local environments to large-scale clusters. Explore further at trychroma.com.

Devon is a neutral open-source tool designed for pair programming, offering features like multi-file editing and code exploration. It supports multiple models such as GPT4 and Ollama's deepseek, with a primary focus on Python. The project includes both UI and terminal interfaces and is open to community contributions.

This Golang-based open-source chatbot leverages machine learning for customizable and privacy-focused solutions, presenting an alternative to services like DialogFlow. It allows developers to train new models easily and integrate seamlessly with mobile devices through its Progressive Web Application format. With support for multiple languages, this chatbot is designed for flexible and user-friendly deployment in various projects.

Dot is an open-source application that enhances document management by utilizing local LLMs and Retrieval Augmented Generation. It supports various document types, such as PDF and DOCX, within a fully local environment. Developed with Electron JS, Dot integrates technologies like FAISS and Langchain to improve query handling and document interaction. Currently available for Apple Silicon and soon Windows, it provides an interface that merges advanced AI capabilities with practical document management solutions.

FunClip is an open-source tool designed for precise video clipping using Alibaba TONGYI's Paraformer and SeACo-Paraformer models. It supports local deployment for conducting video speech recognition, enabling the extraction and clipping of specific segments by text or speaker. Integrating AI capabilities through large language models (LLM), it offers hotword customization and intuitive use with Gradio and cross-platform accessibility. With enhanced features for English audio and speaker diarization, it provides SRT subtitle generation for entire and clipped videos. Accessible via Modelscope and HuggingFace, it serves both experienced users and newcomers to video editing.

Explore Magicoder's unique method of using open-source code via OSS-Instruct to improve Large Language Models, generating diverse and low-bias instruction data. Models excel in HumanEval benchmarks and are accessible via Gradio demos, showcasing practical applications. Evaluate robust APIs supporting various coding tasks and performance metrics available on the EvalPlus Leaderboard.

OpenRecall provides a secure and transparent option for managing digital memory, improving productivity while maintaining privacy. It captures and allows retrieval of digital history via screenshots on Windows, macOS, and Linux. As an open-source platform, it ensures code transparency, allowing local data storage and hardware compatibility. OpenRecall supports AI-assisted semantic search within the user's device, emphasizing data security. With easy installation and community support on Discord and Telegram, it presents a reliable and cost-effective choice for digital history management.

Explore a unique open-source Obsidian plugin designed to streamline personal knowledge management by incorporating large language models like ChatGPT and Llama2. The tool enables direct interaction with notes, featuring capabilities such as note-based chatting, reference linking, and conversation archiving. Maintains data privacy and security by functioning offline. Offers a range of LLMs, facilitating local model integration with Ollama for enhanced flexibility and control. Delve into advanced features including various chat interfaces and note retrieval based on content similarity. Keep up-to-date with ongoing development and engage with evolving AI functionalities. Benefit from efficient note management through an AI-centric approach that balances simplicity with depth.

Explore freeGPT, an AI tool providing free access to diverse text and image generation models, such as gpt3, gpt4, and others. Easily install via pip to harness AI-generated content. This tool supports text completion and image creation, with an official Discord bot enhancing functionality. Models are sourced from multiple platforms, including you.com and pollinations.ai, ensuring consistent AI performance. The project encourages community support on GitHub. Experience smooth integration with clear examples and strong support.