Coding & Development

ControlNet + Anything v4.0 is an AI-powered image generation tool hosted on Hugging Face Spaces, enabling users to leverage ControlNet models for creative image synthesis. This application is built with Gradio, providing a user-friendly interface for interacting with the underlying AI models. While the live website currently indicates a runtime error, suggesting it may not be fully operational at this moment, the tool's description and open-source nature (MIT license) point to its intended purpose as a free and accessible platform for AI image creation. It is a duplication of the original hysts/ControlNet, offering a specific version for users interested in Anything v4.0 capabilities.

rnn-tutorial-rnnlm is an open-source project available on GitHub, offering a comprehensive tutorial for implementing Recurrent Neural Networks (RNNs). Specifically, it focuses on Part 2 of a tutorial series, guiding users through the process of building an RNN in Python and Theano. The repository includes all necessary code, a Jupyter Notebook for interactive learning, and detailed setup instructions. It covers both local development environments and advanced configurations for CUDA-enabled GPU instances on platforms like EC2, making it suitable for developers looking to understand and implement RNNs for language modeling and other sequential data tasks. The project is licensed under Apache-2.0.

RNNoise is a noise suppression library built upon a recurrent neural network, designed to enhance audio quality by effectively reducing unwanted noise. The project, available on GitHub, offers a robust solution for developers and audio engineers looking to integrate advanced noise reduction capabilities into their applications. It supports processing raw 16-bit mono PCM files sampled at 48 kHz and includes a command-line tool for demonstration and basic usage. RNNoise also provides comprehensive documentation for training custom models using publicly available datasets, allowing for tailored noise suppression solutions. The library emphasizes real-time performance and offers options for optimizing performance with AVX2 or SSE4.1 support.

Leon is an open-source personal AI assistant built around tools, context, memory, and agentic execution. Designed for practicality and privacy, it can operate locally, leveraging dedicated tools instead of relying on free-form guessing to complete tasks. Leon supports both deterministic workflows and agent-style execution, allowing it to understand goals, choose how to handle them, and recover from errors. It integrates with local and remote AI providers, balancing privacy, control, and capability. The core architecture organizes capabilities into Skills, Actions, Tools, and Functions, with a compact self-model and proactive pulse system for consistency. It's ideal for users who prioritize privacy and grounded, extensible AI assistance.

LLaVA (Large Language and Vision Assistant) is an open-source project focused on visual instruction tuning to develop large language and vision models with capabilities comparable to GPT-4. It offers improved baselines and supports community contributions, making it a robust platform for multimodal AI research and development. Recent releases include LLaVA-NeXT models with support for LLaMA-3 and Qwen-1.5, LLaVA-NeXT (Video) for zero-shot modality transfer, and LMMs-Eval for efficient evaluation of Large Multimodal Models. The project also provides LLaVA-Plus for multimodal agents and LLaVA-Interactive for human-AI multimodal interaction, including image chat, segmentation, generation, and editing. LLaVA supports LoRA finetuning for reduced GPU RAM and offers various model checkpoints through its Model Zoo.

Symboolic is an AI development platform that enables the creation of AI projects in real-time, offering a unique 'Bright Factory' approach. Users describe their project needs, and AI agents and engineers collaborate to build the application, visible through a real-time dashboard. The platform provides instant quotes through a guided form, which can be validated by a pre-sales engineer. A key feature is the ability to modify requirements at any time, with AI analyzing the impact and generating necessary tasks instantly. Symboolic ensures production-ready software with solid architecture and professional oversight. It also offers dedicated human or AI project managers and provides a complete package upon release, including product, history, and documentation. The platform is built on its own products, Persona (an agentic AI platform) and Many (a knowledge orchestrator), designed to bring generative intelligence and collective knowledge to businesses securely and compliantly.

tree-of-thought-llm is the official open-source implementation of the Tree of Thoughts (ToT) framework, designed for deliberate problem-solving with large language models. This repository, published after the NeurIPS 2023 paper, includes the core code, example prompts, and model outputs, enabling researchers and developers to explore and replicate the ToT methodology. It supports various problem-solving tasks like the game of 24, text generation, and crosswords, offering different thought generation and state evaluation methods. Users can easily set up new tasks and customize prompts, making it a flexible tool for advancing research in LLM reasoning and problem-solving.

CyberSecEvalTest is a specialized tool designed for evaluating the cybersecurity posture of large language models (LLMs). Developed by AI at Meta, this application offers a comprehensive suite of tests to identify potential risks and assess the security capabilities of LLMs. It features a public leaderboard that ranks different models based on their performance in these evaluations, alongside visual analysis tools to help users understand the strengths and weaknesses of each LLM. The platform is hosted on Hugging Face Spaces, making it accessible for researchers and developers interested in enhancing the security of AI systems. It operates under the Apache-2.0 license, promoting open collaboration and development in the field of AI security.

Maxun is an open-source, no-code web data platform designed to transform websites into structured, reliable data. It supports various functionalities including extraction, crawling, scraping, and search, and is built to scale from simple tasks to complex, automated workflows. Key features include a Recorder Mode to turn browsing actions into reusable extraction robots, and an AI Mode that uses natural language for LLM-powered extraction. Maxun can convert full webpages into clean Markdown or HTML, capture screenshots, and crawl entire websites with control over scope. It also facilitates automated web searches with time-based filters and offers a comprehensive developer SDK and CLI for programmatic control and data automation. The platform is self-hostable, provides RESTful endpoints, and integrates with various tools, making it suitable for lead generation, market research, and content aggregation.

ER-NeRF is an open-source project providing Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis, as presented at ICCV 2023. This tool is designed for computer vision and graphics research, enabling users to generate realistic talking portraits from input videos and audio. It includes functionalities for processing custom training videos, extracting facial features like AU45 for eye blinking, and pre-processing audio using DeepSpeech, Wav2Vec, or HuBERT models. The repository offers detailed instructions for installation, data preparation, training, and testing, supporting both head-only and head-plus-torso synthesis. It also allows for inference with target audio, making it a comprehensive solution for advanced talking portrait generation.

ngram2vec is a Python-based toolkit designed for learning high-quality word and ngram embeddings. It implements four distinct word embedding models and supports arbitrary context features, making it a versatile framework for NLP research. The toolkit features a decoupled architecture, which enhances readability, extensibility, and efficiency by allowing intermediate results to be reused. It can generate embeddings for various linguistic units, including text embeddings, and has achieved state-of-the-art results on several datasets. ngram2vec has been successfully applied in projects like Chinese-Word-Vectors, providing over 100 Chinese word embeddings. It supports both Python 2 and 3, along with numpy, scipy, and sparsesvd.

Cerebras Inference offers a high-performance solution for deploying and running large language models, specifically designed to achieve significantly faster AI inference speeds and ultra-low latency. This platform utilizes custom Wafer Scale Engine chips, making it ideal for real-time interactive AI applications where immediate responses are critical. The focus on speed and efficiency positions Cerebras Inference as a powerful tool for developers and data scientists working with demanding AI workloads, ensuring that complex models can operate with the responsiveness required for modern applications.

Xonsh (pronounced "consh") is a powerful, open-source shell that combines the best features of Python 3 with traditional shell functionality. It allows users to execute both Python code and shell commands directly, offering a unique and flexible environment for scripting, automation, and interactive command-line tasks. Xonsh is cross-platform, working on Linux, macOS, and Windows, and is designed to be AI-friendly, facilitating integration with AI tools and workflows. Its extensibility through "xontribs" enables users to customize and enhance its capabilities, from prompt customization to deep integration with other tools like ChatGPT and GitHub Copilot. This makes xonsh an ideal choice for developers and data scientists seeking a highly programmable and adaptable shell.

CogView3-Plus-3B is a Gradio demo of an AI image generation model, designed for generating detailed and high-quality images based on user-provided text prompts. Users can input a description of the desired image and receive a generated visual output. The tool also offers features to enhance prompts, allowing for more refined and specific results, and provides options to customize the image generation process. This platform is suitable for individuals interested in exploring, developing, or testing AI-driven image creation capabilities.

Node provides a supplementary code for Neural Oblivious Decision Ensembles, designed for deep learning on tabular data. This tool specializes in learning deep ensembles of oblivious differentiable decision trees, offering a robust approach to data analysis. While it can run on CPU, optimal performance is achieved with a GPU, which significantly reduces processing time. The implementation is noted to be memory inefficient, potentially requiring substantial GPU memory. It is compatible with popular Linux x64 distributions and MacOS, with Docker recommended for other systems. Users need Python (Anaconda recommended) and specific Torch versions to run the provided notebooks, which showcase classification and regression scenarios.

Neural Complete is an autocomplete tool specifically designed to assist in writing neural network code. It leverages a generative LSTM neural network, trained on Python code, including Keras imports, to provide intelligent suggestions. Unlike typical autocompletion that finishes words, Neural Complete suggests entire lines of code, taking into account the context from previous lines. This allows it to understand the flow of code and offer more semantically relevant suggestions. The tool includes both character-based and token-based models, offering flexibility in how suggestions are generated. Users are encouraged to train the model on their own data for personalized autocomplete experiences, making it a valuable resource for developers working with neural networks.

NeoAI is a Neovim plugin designed to seamlessly integrate OpenAI's GPT models, including GPT-4, directly into your coding environment. It empowers developers to generate code, rewrite text, and obtain in-context suggestions without disrupting their workflow. The plugin offers a user-friendly interface with three distinct modes: Normal GUI Mode for chat-like interactions, Context Mode for providing additional information from selected code or text, and Inject Mode for quickly inserting AI responses directly into the buffer. NeoAI prioritizes efficiency and utility, aiming to enhance productivity by facilitating a smooth and responsive coding experience within Neovim. Users need an OpenAI API key and are advised to monitor their usage to manage costs.

Seaml.es v2.0.1 is an AI-powered tool designed to streamline scientific literature review and legal research processes. It provides users with capabilities to search and draft content, leveraging advanced language models. The platform offers a free tier that utilizes GPT-3.5, allowing users to try out its core functionalities without immediate cost. For those requiring higher quality search and drafting capabilities, a PRO upgrade is available, which grants access to the more powerful GPT-4 model. This makes Seaml.es suitable for individuals and professionals in scientific and legal fields looking to enhance their research efficiency and output quality.

Notebook Copilot is an open-source, AI-powered assistant designed for data scientists and engineers working with Jupyter Notebooks. Inspired by GitHub Copilot, it streamlines the development of professional, high-quality notebooks by generating code and markdown cells based on user inputs. Key features include GPT-based generation, seamless integration with various notebook environments, and automatic context retrieval to ensure relevant code suggestions. Users can bring their own OpenAI key for personalized results. It offers magic functions for continuous generation, turning comments into code, explaining code with markdown, optimizing code for speed, and visualizing data with single-line commands, making it a powerful tool for enhancing productivity and documentation.

Vosk-android-demo offers robust offline speech recognition and speaker identification capabilities specifically designed for Android mobile applications. This tool is built upon the powerful Vosk and Kaldi libraries, ensuring high accuracy and performance without requiring an internet connection. Developers can easily integrate these features into their Android projects, with pre-built binaries available in the releases section to streamline the development process. It's an ideal solution for creating mobile applications that require on-device voice command processing, transcription, or user authentication through voice, providing a reliable and efficient way to handle speech data locally.

vstar is an open-source project offering a PyTorch implementation of the research paper "V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs." This tool is designed for researchers and developers working with multimodal large language models, specifically focusing on enhancing visual search capabilities. It includes pre-trained models for both VQA LLM and visual search, along with comprehensive training datasets derived from LAION-CC-SBU, COCO, and GQA. Users can set up a local Gradio demo for interactive use and evaluate models using the V*Bench benchmark. The project also provides detailed instructions for pre-training and instruction tuning of the VQA LLM, making it a valuable resource for advancing research in guided visual search within LLMs.

HiVT (Hierarchical Vector Transformer) is an open-source implementation of a multi-agent motion prediction model, published in CVPR 2022. This repository provides the official code for training and evaluating the HiVT model, which is designed to predict the future movements of multiple agents in complex environments, such as those encountered in autonomous driving. Users can leverage pretrained models (HiVT-64 and HiVT-128) or train their own using the provided scripts and the Argoverse Motion Forecasting Dataset. The project includes detailed instructions for setup, data preparation, training, and evaluation, making it a valuable resource for researchers and developers in the field of autonomous systems.

Cetvel is a comprehensive tool designed to serve as a unified benchmark for evaluating Turkish Large Language Models (LLMs). Developed by KUIS-AI, this application enables researchers and developers to assess and compare the performance of different Turkish language models across a variety of linguistic tasks and datasets. Users can gain insights into how models perform, facilitating informed decisions for model selection and development. The tool is built with Streamlit, ensuring an interactive and user-friendly experience, and is licensed under the MIT license, promoting open access and collaboration within the AI community. It is hosted as a Hugging Face Space, making it easily accessible for anyone interested in Turkish LLM evaluation.

Melty is an innovative, open-source code editor specifically engineered to enhance AI-driven development workflows. It deeply integrates large language models into its core, enabling advanced AI collaboration for various tasks such as pair programming and multi-file code modifications. This tool significantly boosts developer productivity by allowing AI to comprehend the full context of a codebase and execute terminal commands. Its open-source nature promotes community contributions and flexibility, making it a powerful solution for developers looking to leverage AI in their coding practices.