New AI tools - Open Source

This repository contains code for three papers related to evaluating large language models on planning and reasoning about change. It includes benchmarking tools and analysis for assessing the planning abilities of large language models. The latest addition evaluates and enhances the planning and scheduling capabilities of a specific language reasoning model. The repository provides a static test set leaderboard showcasing model performance on various tasks with natural language and planning domain prompts.

Grounded-VideoLLM is a Video Large Language Model specialized in fine-grained temporal grounding. It excels in tasks such as temporal sentence grounding, dense video captioning, and grounded VideoQA. The model incorporates an additional temporal stream, discrete temporal tokens with specific time knowledge, and a multi-stage training scheme. It shows potential as a versatile video assistant for general video understanding. The repository provides pretrained weights, inference scripts, and datasets for training. Users can run inference queries to get temporal information from videos and train the model from scratch.

LLM-Planner is a tool for few-shot grounded planning for embodied agents using large language models. It includes a high-level prompt generator and kNN dataset, allowing users to generate high-level plans for tasks by bringing their low-level controller and an LLM. The tool has been used in various research projects and provides implementation examples from different conferences. Users can cite the tool using the provided information and the tool is available under the MIT License. For questions or issues, users can contact Luke Song.

AgentSquare is an official implementation for the paper 'AgentSquare: Automatic LLM Agent Search in Modular Design Space'. It provides code, prompts, and results for automatic LLM agent search. The tool allows users to set up OpenAI API key, install dependencies, and run various tasks such as ALFworld, Webshop, M3Tooleval, and Sciworld. Users can also contribute new modules to the modular design challenge by standardizing LLM agents with recommended I/O interfaces. The tool aims to offer a platform for fully exploiting successful agent designs and consolidating efforts of the LLM agent research community.

GPT Author is a command-line tool designed to help users write long form, multi-chapter stories by providing a story prompt and generating a synopsis and subsequent chapters using ChatGPT. Users can review and make changes to the generated content before finalizing the story output in Markdown and HTML formats. The tool aims to unleash storytelling genius by combining human input with AI-generated content, offering a seamless writing experience for creating engaging narratives.

LLMOCR is a tool that utilizes a local Large Language Model (LLM) to extract text from images. It offers a user-friendly GUI and supports GPU acceleration for faster inference. The tool is cross-platform, compatible with Windows, macOS ARM, and Linux. Users can prompt the LLM to process images in a customized way. The processing is done locally on the user's machine, ensuring data privacy and security. LLMOCR requires Python 3.8 or higher and KoboldCPP for installation and operation.

CAD-Recode is a 3D CAD reverse engineering method implemented in Python using the CadQuery library. It transforms point clouds into 3D CAD models by leveraging a pre-trained model and additional linear layers. The repository includes an inference demo for users to generate CAD models from point clouds. CAD-Recode has achieved state-of-the-art performance in CAD reconstruction benchmarks such as DeepCAD, Fusion360, and CC3D. Researchers and engineers can utilize this tool to reverse engineer CAD code from point clouds efficiently.

Abliteration is a tool that allows users to create abliterated models using transformers quickly and easily. It is not a tool for uncensorship, but rather for making models that will not explicitly refuse users. Users can clone the repository, install dependencies, and make abliterations using the provided commands. The tool supports adjusting parameters for stubborn models and offers various options for customization. Abliteration can be used for creating modified models for specific tasks or topics.

LLM4EC is an interdisciplinary research repository focusing on the intersection of Large Language Models (LLM) and Evolutionary Computation (EC). It provides a comprehensive collection of papers and resources exploring various applications, enhancements, and synergies between LLM and EC. The repository covers topics such as LLM-assisted optimization, EA-based LLM architecture search, and applications in code generation, software engineering, neural architecture search, and other generative tasks. The goal is to facilitate research and development in leveraging LLM and EC for innovative solutions in diverse domains.

1Backend is a flexible and scalable platform designed for running AI models on private servers and handling high-concurrency workloads. It provides a ChatGPT-like interface for users and a network-accessible API for machines, serving as a general-purpose backend framework. The platform offers on-premise ChatGPT alternatives, a microservices-first web framework, out-of-the-box services like file uploads and user management, infrastructure simplification acting as a container orchestrator, reverse proxy, multi-database support with its own ORM, and AI integration with platforms like LlamaCpp and StableDiffusion.

PlayWord is a tool designed to supercharge web test automation experience with AI. It provides core features such as enabling browser operations and validations using natural language inputs, as well as monitoring interface to record and dry-run test steps. PlayWord supports multiple AI services including Anthropic, Google, and OpenAI, allowing users to select the appropriate provider based on their requirements. The tool also offers features like assertion handling, frame handling, custom variables, test recordings, and an Observer module to track user interactions on web pages. With PlayWord, users can interact with web pages using natural language commands, reducing the need to worry about element locators and providing AI-powered adaptation to UI changes.

The ArXiv MCP Server acts as a bridge between AI assistants and arXiv's research repository, enabling AI models to search for and access papers programmatically through the Message Control Protocol (MCP). It offers features like paper search, access, listing, local storage, and research prompts. Users can install it via Smithery or manually for Claude Desktop. The server provides tools for paper search, download, listing, and reading, along with specialized prompts for paper analysis. Configuration can be done through environment variables, and testing is supported with a test suite. The tool is released under the MIT License and is developed by the Pearl Labs Team.

Polis is an AI powered sentiment gathering platform that offers a more organic approach than surveys and requires less effort than focus groups. It provides a comprehensive wiki, main deployment at https://pol.is, discussions, issue tracking, and project board for users. Polis can be set up using Docker infrastructure and offers various commands for building and running containers. Users can test their instance, update the system, and deploy Polis for production. The tool also provides developer conveniences for code reloading, type checking, and database connections. Additionally, Polis supports end-to-end browser testing using Cypress and offers troubleshooting tips for common Docker and npm issues.

AI Server is a self-hosted private gateway that orchestrates AI requests through a single integration, allowing control over AI providers like LLM, Diffusion, and image transformation. It dynamically delegates requests across various providers, including LLM APIs, Media APIs, and Comfy UI with FFmpeg Agents. The tool also offers built-in UIs for tasks like chat, text-to-image, image-to-text, image upscaling, speech-to-text, and text-to-speech. Additionally, it provides admin UIs for managing AI and media providers, API key access, and monitoring background jobs and AI requests.

Well-Architected Infrastructure as Code (IaC) Analyzer is a project demonstrating how generative AI can evaluate infrastructure code for alignment with best practices. It features a modern web application allowing users to upload IaC documents, complete IaC projects, or architecture diagrams for assessment. The tool provides insights into infrastructure code alignment with AWS best practices, offers suggestions for improving cloud architecture designs, and can generate IaC templates from architecture diagrams. Users can analyze CloudFormation, Terraform, or AWS CDK templates, architecture diagrams in PNG or JPEG format, and complete IaC projects with supporting documents. Real-time analysis against Well-Architected best practices, integration with AWS Well-Architected Tool, and export of analysis results and recommendations are included.

ONE is a modern web and AI agent development toolkit that empowers developers to build AI-powered applications with high performance, beautiful UI, AI integration, responsive design, type safety, and great developer experience. It is perfect for building modern web applications, from simple landing pages to complex AI-powered platforms.

Describer is a tool that analyzes codebases using AI to generate architectural overviews, documentation, explanations, bug reports, and more. It scans all files in a directory and uses Google's Gemini AI to provide insights such as markdown architectural overviews, codebase summaries, code pattern analysis, codebase structure documentation, bug identification, and test idea generation. The tool respects .gitignore rules by default but allows users to include/exclude specific files or patterns for analysis.

AI-UBB is a project related to Artificial Intelligence discipline in the second year of the Faculty of Mathematics and Computer Science at Babes-Bolyai University in Cluj-Napoca. The project involves a team of students working on various aspects of AI under the guidance of their professors.

Next-generation AI translation tool that provides high-quality, precise translations for various common file formats with a single click. It is based on cutting-edge large language models, offering exceptional translation quality with minimal operation, supporting multiple document formats and languages. Features include multi-format compatibility, global language translation, one-click rapid translation, flexible translation engines, and LAN sharing for efficient collaborative work.

MarkFlowy is a lightweight and feature-rich Markdown editor with built-in AI capabilities. It supports one-click export of conversations, translation of articles, and obtaining article abstracts. Users can leverage large AI models like DeepSeek and Chatgpt as intelligent assistants. The editor provides high availability with multiple editing modes and custom themes. Available for Linux, macOS, and Windows, MarkFlowy aims to offer an efficient, beautiful, and data-safe Markdown editing experience for users.

This project aims to integrate mainstream open-source large models to achieve the coordination and cooperation between different types of large models, providing comprehensive and flexible AI content generation services.

LLM Chain is a PHP library for building LLM-based features and applications. It provides abstractions for Language Models and Embeddings Models from platforms like OpenAI, Azure, Google, Replicate, and others. The core feature is to interact with language models via messages, supporting different message types and content. LLM Chain also supports tool calling, document embedding, vector stores, similarity search, structured output, response streaming, image processing, audio processing, embeddings, parallel platform calls, and input/output processing. Contributions are welcome, and the repository contains fixture licenses for testing multi-modal features.

Xianyu AutoAgent is an AI customer service robot system specifically designed for the Xianyu platform, providing 24/7 automated customer service, supporting multi-expert collaborative decision-making, intelligent bargaining, and context-aware conversations. The system includes intelligent conversation engine with features like context awareness and expert routing, business function matrix with modules like core engine, bargaining system, technical support, and operation monitoring. It requires Python 3.8+ and NodeJS 18+ for installation and operation. Users can customize prompts for different experts and contribute to the project through issues or pull requests.

InfiniStore is an open-source high-performance KV store designed to support LLM Inference clusters. It provides high-performance and low-latency KV cache transfer and reuse among inference nodes. In addition to inference clusters, it can be used as a standalone KV store for integration with LLM training or inference services. InfiniStore is currently integrated with vLLM via LMCache and is in progress for integration with SGLang and other inference engines.

llm-resources is a repository providing resources to get started with Large Language Models (LLMs). It includes videos on Neural Networks and LLMs, free courses, prompt engineering guides, explored frameworks, AI assistants, and tips on making RAG work properly. The repository also contains important links and updates related to LLMs, AWS, RAG, agents, model context protocol, and more. It aims to help individuals with a basic understanding of NLP and programming knowledge to explore and utilize LLMs effectively.

ExLlamaV2 is an inference library designed for running local LLMs on modern consumer GPUs. The library supports paged attention via Flash Attention 2.5.7+, offers a new dynamic generator with features like dynamic batching, smart prompt caching, and K/V cache deduplication. It also provides an API for local or remote inference using TabbyAPI, with extended features like HF model downloading and support for HF Jinja2 chat templates. ExLlamaV2 aims to optimize performance and speed across different GPU models, with potential future optimizations and variations in speeds. The tool can be integrated with TabbyAPI for OpenAI-style web API compatibility and supports a standalone web UI called ExUI for single-user interaction with chat and notebook modes. ExLlamaV2 also offers support for text-generation-webui and lollms-webui through specific loaders and bindings.

OneKE is a flexible dockerized system for schema-guided knowledge extraction, capable of extracting information from the web and raw PDF books across multiple domains like science and news. It employs a collaborative multi-agent approach and includes a user-customizable knowledge base to enable tailored extraction. OneKE offers various IE tasks support, data sources support, LLMs support, extraction method support, and knowledge base configuration. Users can start with examples using YAML, Python, or Web UI, and perform tasks like Named Entity Recognition, Relation Extraction, Event Extraction, Triple Extraction, and Open Domain IE. The tool supports different source formats like Plain Text, HTML, PDF, Word, TXT, and JSON files. Users can choose from various extraction models like OpenAI, DeepSeek, LLaMA, Qwen, ChatGLM, MiniCPM, and OneKE for information extraction tasks. Extraction methods include Schema Agent, Extraction Agent, and Reflection Agent. The tool also provides support for schema repository and case repository management, along with solutions for network issues. Contributors to the project include Ningyu Zhang, Haofen Wang, Yujie Luo, Xiangyuan Ru, Kangwei Liu, Lin Yuan, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Jun Zhou, Lanning Wei, Da Zheng, and Huajun Chen.

Data Prep Kit accelerates unstructured data preparation for LLM app developers. It allows developers to cleanse, transform, and enrich unstructured data for pre-training, fine-tuning, instruct-tuning LLMs, or building RAG applications. The kit provides modules for Python, Ray, and Spark runtimes, supporting Natural Language and Code data modalities. It offers a framework for custom transforms and uses Kubeflow Pipelines for workflow automation. Users can install the kit via PyPi and access a variety of transforms for data processing pipelines.

TopicGPT is a repository containing scripts and prompts for the paper 'TopicGPT: Topic Modeling by Prompting Large Language Models' (NAACL'24). The 'topicgpt_python' package offers functions to generate high-level and specific topics, refine topics, assign topics to input text, and correct generated topics. It supports various APIs like OpenAI, VertexAI, Azure, Gemini, and vLLM for inference. Users can prepare data in JSONL format, run the pipeline using provided scripts, and evaluate topic alignment with ground-truth labels.

OpenManus-RL is an open-source initiative focused on enhancing reasoning and decision-making capabilities of large language models (LLMs) through advanced reinforcement learning (RL)-based agent tuning. The project explores novel algorithmic structures, diverse reasoning paradigms, sophisticated reward strategies, and extensive benchmark environments. It aims to push the boundaries of agent reasoning and tool integration by integrating insights from leading RL tuning frameworks and continuously updating progress in a dynamic, live-streaming fashion.

LLMII is a tool that uses a local AI model to label metadata and index images without relying on cloud services or remote APIs. It runs a visual language model on your computer to generate captions and keywords for images, enhancing their metadata for indexing, searching, and organization. The tool can be run multiple times on the same image files, allowing for adding new data, regenerating data, and discovering files with issues. It supports various image formats, offers a user-friendly GUI, and can utilize GPU acceleration for faster processing. LLMII requires Python 3.8 or higher and operates directly on image file metadata fields like MWG:Keyword and XMP:Identifier.

StockTrading AI is a small model stock automatic trading system that integrates with securities platforms, implements automated stock trading, utilizes QuartZ for scheduled tasks to update data daily, employs DL4J framework for LSTM model guidance on stock buying with T+1 short-term trading strategy, utilizes K8S+GithubAction for DevOps, and supports distributed offline training. Future optimizations include obtaining more historical stock data for incremental model training and tuning model hyperparameters to improve price trend prediction accuracy. The system provides various page displays for profit data statistics, trade order queries, stock price viewing, model prediction performance, scheduled task scheduling, and real-time log tracking.

NeoPass is a free Chrome extension designed for students taking tests on exam portals like Iamneo and Wildlife Ecology NPTEL. It provides features such as NPTEL integration, NeoExamShield bypass, AI chatbot with stealth mode, AI search answers/code, MCQ solving, tab switching bypass, pasting when restricted, and remote logout. Users can install the extension by following simple steps and use shortcuts for quick access to features. The tool is intended for educational purposes only and promotes academic integrity.

Learn-AI-Assisted-Python-Programming is a book that introduces readers to the world of AI-assisted programming, focusing on using tools like GitHub Copilot and ChatGPT to create and optimize Python programs. The book guides users, even those with no prior coding experience, on how to leverage AI assistants to quickly turn their ideas into reality without getting bogged down in low-level programming details. Readers will learn to generate code using natural language prompts, fine-tune code manually or with AI assistance, test programs with AI, and automate tedious tasks. The book aims to accelerate the learning journey of Copilot programming and provide a user-friendly and thoughtful approach for beginners.

Nosia is a platform that allows users to run an AI model on their own data. It is designed to be easy to install and use. Users can follow the provided guides for quickstart, API usage, upgrading, starting, stopping, and troubleshooting. The platform supports custom installations with options for remote Ollama instances, custom completion models, and custom embeddings models. Advanced installation instructions are also available for macOS with a Debian or Ubuntu VM setup. Users can access the platform at 'https://nosia.localhost' and troubleshoot any issues by checking logs and job statuses.

Aioshelly is an asynchronous library designed to control Shelly devices. It is currently under development and requires Python version 3.11 or higher, along with dependencies like bluetooth-data-tools, aiohttp, and orjson. The library provides examples for interacting with Gen1 devices using CoAP protocol and Gen2/Gen3 devices using RPC and WebSocket protocols. Users can easily connect to Shelly devices, retrieve status information, and perform various actions through the provided APIs. The repository also includes example scripts for quick testing and usage guidelines for contributors to maintain consistency with the Shelly API.

MCPSharp is a .NET library that helps build Model Context Protocol (MCP) servers and clients for AI assistants and models. It allows creating MCP-compliant tools, connecting to existing MCP servers, exposing .NET methods as MCP endpoints, and handling MCP protocol details seamlessly. With features like attribute-based API, JSON-RPC support, parameter validation, and type conversion, MCPSharp simplifies the development of AI capabilities in applications through standardized interfaces.

media-stack is a self-hosted media ecosystem that combines media management, streaming, AI-powered recommendations, and VPN. It includes tools like Radarr for movie management, Sonarr for TV show management, Prowlarr for torrent indexing, qBittorrent for downloading media, Jellyseerr for media requests, Jellyfin for media streaming, and Recommendarr for AI-powered recommendations. The stack can be deployed with or without a VPN and offers detailed configuration steps for each tool.

RKLLama is a server and client tool designed for running and interacting with LLM models optimized for Rockchip RK3588(S) and RK3576 platforms. It allows models to run on the NPU, with features such as running models on NPU, partial Ollama API compatibility, pulling models from Huggingface, API REST with documentation, dynamic loading/unloading of models, inference requests with streaming modes, simplified model naming, CPU model auto-detection, and optional debug mode. The tool supports Python 3.8 to 3.12 and has been tested on Orange Pi 5 Pro and Orange Pi 5 Plus with specific OS versions.

NeuroSync Player is a real-time AI endpoint server that combines text-to-speech and NeuroSync generations. It includes code for various AI endpoints such as speech-to-text, text-to-speech, embedding, and vision. The tool allows users to connect their llm to Twitch and YouTube, enabling the llm-powered metahuman to respond to viewers in real-time. Additionally, it offers features like push-to-talk, face animation integration, and support for blendshapes generated from audio inputs for Unreal Engine 5. Users can train and fine-tune their own models using NeuroSync Trainer Lite, with simplified loss functions and mixed precision for faster training. The tool also supports data augmentation to help with fine detail reproduction.

WhiskeyAI is a Next.js project that serves as a starting point for developing web applications. It includes a development server for live previewing changes and utilizes next/font for optimizing and loading the Geist font family. The project encourages contributions and feedback from users, providing resources for learning Next.js and deploying applications on the Vercel platform.

PilottAI is a Python framework for building autonomous multi-agent systems with advanced orchestration capabilities. It provides enterprise-ready features for building scalable AI applications. The framework includes hierarchical agent systems, production-ready features like asynchronous processing and fault tolerance, advanced memory management with semantic storage, and integrations with multiple LLM providers and custom tools. PilottAI offers specialized agents for various tasks such as customer service, document processing, email handling, knowledge acquisition, marketing, research analysis, sales, social media, and web search. The framework also provides documentation, example use cases, and advanced features like memory management, load balancing, and fault tolerance.

Shandu is an advanced AI research system that automates comprehensive research processes using language models, web scraping, and iterative exploration to generate well-structured reports with citations. It features intelligent state-based workflow, deep exploration, multi-source information synthesis, enhanced web scraping, smart source evaluation, content analysis pipeline, comprehensive report generation, parallel processing, adaptive search strategy, and full citation management.

ChemicalQDevice innovates new LLM/LLM agent pharmaceutical industry applications regarding cancer drug cost containment, clinical decision support, cancer signaling pathways, bioprocess engineering, biosynthesis, characterization, or drug synthesis. OpenAI, Anthropic, Gemini, or xAI direct chat proprietary software are utilized to generate LLM reports and propose detailed solutions. AI governance is employed with relevant software implementations, model bias amplification mitigation, and generation traceability analyses.

MLX LM is a Python package designed for generating text and fine-tuning large language models on Apple silicon using MLX. It offers integration with the Hugging Face Hub for easy access to thousands of LLMs, support for quantizing and uploading models to the Hub, low-rank and full model fine-tuning capabilities, and distributed inference and fine-tuning with `mx.distributed`. Users can interact with the package through command line options or the Python API, enabling tasks such as text generation, chatting with language models, model conversion, streaming generation, and sampling. MLX LM supports various Hugging Face models and provides tools for efficient scaling to long prompts and generations, including a rotating key-value cache and prompt caching. It requires macOS 15.0 or higher for optimal performance.

Manifold is a powerful platform for workflow automation using AI models. It supports text generation, image generation, and retrieval-augmented generation, integrating seamlessly with popular AI endpoints. Additionally, Manifold provides robust semantic search capabilities using PGVector combined with the SEFII engine. It is under active development and not production-ready.

The oba live tool is a small tool for Douyin small shops and Kuaishou Baiying live broadcasts. It features multiple account management, intelligent message assistant, automatic product explanation, AI automatic reply, and AI intelligent assistant. The tool requires Windows 10 or above, Chrome or Edge browser, and a valid account for Douyin small shops or Kuaishou Baiying. Users can download the tool from the Releases page, connect to the control panel, set API keys for AI functions, and configure auto-reply prompts. The tool is licensed under the MIT license.

WenXin-Starter is a spring-boot-starter for Baidu's 'WenXin Workshop' large model, facilitating quick integration of Baidu's AI capabilities. It provides complete integration with WenXin Workshop's official API documentation, supports WenShengTu, built-in conversation memory, and supports conversation streaming. It also supports QPS control for individual models and queuing mechanism, with upcoming plugin support.

This repository provides Terraform configurations to automatically set up Google Cloud resources and deploy Dify in a highly available configuration. It includes features such as serverless hosting, auto-scaling, and data persistence. Users need a Google Cloud account, Terraform, and gcloud CLI installed to use this tool. The configuration involves setting environment-specific values and creating a GCS bucket for managing Terraform state. The tool allows users to initialize Terraform, create Artifact Registry repository, build and push container images, plan and apply Terraform changes, and cleanup resources when needed.

Open Autonomy is a framework for creating agent services that run as a multi-agent-system and offer enhanced functionalities on-chain. It enables executing complex operations like machine-learning algorithms in a decentralized, trust-minimized, transparent, and robust manner.

anki_packager is an intelligent tool for generating high-quality Anki flashcards for English vocabulary. It integrates multiple curated dictionaries, provides automated learning experiences, supports various features like Google TTS pronunciation and AI models for word summarization and story generation, offers convenient data import from other sources, ensures a good command-line interface, and can be run using Docker. Each flashcard includes detailed learning resources such as definitions, tenses, AI-generated roots for mnemonic aids, phrases, example sentences, word differentiations, and English explanations with AI-generated stories.

Docling simplifies document processing, parsing diverse formats including advanced PDF understanding, and providing seamless integrations with the general AI ecosystem. It offers features such as parsing multiple document formats, advanced PDF understanding, unified DoclingDocument representation format, various export formats, local execution capabilities, plug-and-play integrations with agentic AI tools, extensive OCR support, and a simple CLI. Coming soon features include metadata extraction, visual language models, chart understanding, and complex chemistry understanding. Docling is installed via pip and works on macOS, Linux, and Windows environments. It provides detailed documentation, examples, integrations with popular frameworks, and support through the discussion section. The codebase is under the MIT license and has been developed by IBM.

Surf is a Next.js application that integrates E2B's desktop sandbox with OpenAI's API to create an AI agent that can perform tasks on a virtual computer through natural language instructions. It provides a web interface for users to start a virtual desktop sandbox environment, send instructions to the AI agent, watch AI actions in real-time, and interact with the AI through a chat interface. The application uses Server-Sent Events (SSE) for seamless communication between frontend and backend components.

Xata Agent is an open source tool designed to monitor PostgreSQL databases, identify issues, and provide recommendations for improvements. It acts as an AI expert, offering proactive suggestions for configuration tuning, troubleshooting performance issues, and common database problems. The tool is extensible, supports monitoring from cloud services like RDS & Aurora, and uses preset SQL commands to ensure database safety. Xata Agent can run troubleshooting statements, notify users of issues via Slack, and supports multiple AI models for enhanced functionality. It is actively used by the Xata team to manage Postgres databases efficiently.

A toolkit for computational chemistry research, featuring tools to facilitate automated workflows. Includes tools for NMR prediction, dynamic catalysis research, proton transfer analysis, amorphous oxides structure analysis, reweighting, and more. Users can install 'ai2-kit' via pip and explore various domain-specific and general tools for processing system data and filtering structures by model deviation.

Sports-Betting-ML-Tools-NBA is a repository containing machine learning and market analysis tools for NBA games. It features a game prediction model trained on 20,000+ games with 500+ data points per game, pre-game analysis with player stats, injuries, and Vegas odds, custom model training with configurable parameters, real-time score updates, and performance tracking. Users can analyze player stats, remove injured players, check Vegas odds and injury reports, review last game performance, and generate game score predictions. The repository also allows users to configure model training parameters, monitor training via Tensorboard, track performance metrics like win/loss percentage, spread accuracy, and profit/loss calculations, and access core statistics per player and team metrics.

Easy Dataset is a specialized application designed to streamline the creation of fine-tuning datasets for Large Language Models (LLMs). It offers an intuitive interface for uploading domain-specific files, intelligently splitting content, generating questions, and producing high-quality training data for model fine-tuning. With Easy Dataset, users can transform domain knowledge into structured datasets compatible with all OpenAI-format compatible LLM APIs, making the fine-tuning process accessible and efficient.

LLM4DB is a repository focused on the intersection of Large Language Models (LLM) and Database technologies. It covers various aspects such as data processing, data analysis, database optimization, and data management for LLM. The repository includes works on data cleaning, entity matching, schema matching, data discovery, NL2SQL, data exploration, data visualization, configuration tuning, query optimization, and anomaly diagnosis using LLMs. It aims to provide insights and advancements in leveraging LLMs for improving data processing, analysis, and database management tasks.

AI-LLM-ML-CS-Quant-Overview is a repository providing overview notes on AI, Large Language Models (LLM), Machine Learning (ML), Computer Science (CS), and Quantitative Finance. It covers various topics such as LangGraph & Cursor AI, DeepSeek, MoE (Mixture of Experts), NVIDIA GTC, LLM Essentials, System Design, Computer Systems, Big Data and AI in Finance, Econometrics and Statistics Conference, C++ Design Patterns and Derivatives Pricing, High-Frequency Finance, Machine Learning for Algorithmic Trading, Stochastic Volatility Modeling, Quant Job Interview Questions, Distributed Systems, Language Models, Designing Machine Learning Systems, Designing Data-Intensive Applications (DDIA), Distributed Machine Learning, and The Elements of Quantitative Investing.

The LLM Engineer Toolkit is a curated repository containing over 120 LLM libraries categorized for various tasks such as training, application development, inference, serving, data extraction, data generation, agents, evaluation, monitoring, prompts, structured outputs, safety, security, embedding models, and other miscellaneous tools. It includes libraries for fine-tuning LLMs, building applications powered by LLMs, serving LLM models, extracting data, generating synthetic data, creating AI agents, evaluating LLM applications, monitoring LLM performance, optimizing prompts, handling structured outputs, ensuring safety and security, embedding models, and more. The toolkit covers a wide range of tools and frameworks to streamline the development, deployment, and optimization of large language models.

Interaqt is a project that aims to separate application business logic from its specific implementation by providing a structured data model and tools to automatically decide and implement software architecture. It liberates individuals and teams from implementation specifics, performance requirements, and cost demands, allowing them to focus on articulating business logic. The approach is considered optimal in the era of large language models (LLMs) as it eliminates uncertainty in generated systems and enables independence from engineering involvement unless specific capabilities are required.

This repository provides an easy-to-use solution for running inference servers on Slurm-managed computing clusters using vLLM. All scripts in this repository run natively on the Vector Institute cluster environment. Users can deploy models as Slurm jobs, check server status and performance metrics, and shut down models. The repository also supports launching custom models with specific configurations. Additionally, users can send inference requests and set up an SSH tunnel to run inference from a local device.

Personal AI assistant/agent in your terminal, with tools for using the terminal, running code, editing files, browsing the web, using vision, and more. A great coding agent that is general-purpose to assist in all kinds of knowledge work, from a simple but powerful CLI. An unconstrained local alternative to ChatGPT with 'Code Interpreter', Cursor Agent, etc. Not limited by lack of software, internet access, timeouts, or privacy concerns if using local models.

A project that utilizes large models to help with Code Review on Gitlab, aimed at improving development efficiency. The project is customized for Gitlab and is developing a Multi-Agent plugin for collaborative review. It integrates various large models for code security issues and stays updated with the latest Code Review trends. The project architecture is designed to be powerful, flexible, and efficient, with easy integration of different models and high customization for developers.

This repository contains code for manipulating Large Language Models (LLMs) to increase the visibility of specific content or products in search engine recommendations. By adding a Strategic Text Sequence (STS) to a product's information page, the target product's rank in the LLM's recommendation can be optimized. The code includes scripts for generating and evaluating the STS, as well as plotting the results. The tool requires NVIDIA A100 GPUs for optimization and can be run in a Conda environment.

Wave Executor is a cutting-edge Roblox script executor designed for advanced script execution, optimized performance, and seamless user experience. Fully compatible with the latest Roblox updates, it is secure, easy to use, and perfect for gamers, developers, and modding enthusiasts looking to enhance their Roblox gameplay.

The OpenAI Agents SDK is a lightweight framework for building multi-agent workflows. It includes concepts like Agents, Handoffs, Guardrails, and Tracing to facilitate the creation and management of agents. The SDK is compatible with any model providers supporting the OpenAI Chat Completions API format. It offers flexibility in modeling various LLM workflows and provides automatic tracing for easy tracking and debugging of agent behavior. The SDK is designed for developers to create deterministic flows, iterative loops, and more complex workflows.

The MCP Java SDK is a set of projects that provide Java SDK integration for the Model Context Protocol. It enables Java applications to interact with AI models and tools through a standardized interface, supporting both synchronous and asynchronous communication patterns.

Zero is an open-source AI email solution that allows users to self-host their email app while integrating external services like Gmail. It aims to modernize and enhance emails through AI agents, offering features like open-source transparency, AI-driven enhancements, data privacy, self-hosting freedom, unified inbox, customizable UI, and developer-friendly extensibility. Built with modern technologies, Zero provides a reliable tech stack including Next.js, React, TypeScript, TailwindCSS, Node.js, Drizzle ORM, and PostgreSQL. Users can set up Zero using standard setup or Dev Container setup for VS Code users, with detailed environment setup instructions for Better Auth, Google OAuth, and optional GitHub OAuth. Database setup involves starting a local PostgreSQL instance, setting up database connection, and executing database commands for dependencies, tables, migrations, and content viewing.

Iffy is a tool for intelligent content moderation at scale, allowing users to keep unwanted content off their platform without the need to manage a team of moderators. It features a Moderation Dashboard to view and manage all moderation activities, User Lifecycle for automatically suspending users with flagged content, Appeals Management for efficient handling of user appeals, and Powerful Rules & Presets to create custom moderation rules based on unique business needs. Users can choose between the managed Iffy Cloud or the free self-hosted Iffy Community version, each offering different features and setups.

Enhance coding efficiency with expert-led GitHub Copilot course for C#/.NET developers. Learn to integrate AI-powered coding assistance, automate testing, and boost collaboration using Visual Studio Code and Copilot Chat. From autocompletion to unit testing, cover essential techniques for cleaner, faster, smarter code.

Aioreactive is a Python library that brings ReactiveX functionality to asyncio using async and await. It is built on the Expression functional library and aims to provide a simple, clean, and async-based approach to reactive programming in Python. The library supports Python 3.10+ and focuses on using plain old functions for operators, running on the asyncio event loop, and providing implicit synchronous back-pressure for event processing.

The Google Gen AI JavaScript SDK is an experimental SDK for TypeScript and JavaScript developers to build applications powered by Gemini. It supports both the Gemini Developer API and Vertex AI. The SDK is designed to work with Gemini 2.0 features. Users can access API features through the GoogleGenAI classes, which provide submodules for querying models, managing caches, creating chats, uploading files, and starting live sessions. The SDK also allows for function calling to interact with external systems. Users can find more samples in the GitHub samples directory.

GROMACS Copilot is an agent designed to automate molecular dynamics simulations for proteins in water using GROMACS. It handles system setup, simulation execution, and result analysis automatically, providing outputs such as RMSD, RMSF, Rg, and H-bonds. Users can interact with the agent through prompts and API keys from DeepSeek and OpenAI. The tool aims to simplify the process of running MD simulations, allowing users to focus on other tasks while it handles the technical aspects of the simulations.

AI-LLM-ML-CS-Quant-Readings is a repository dedicated to taking notes on Artificial Intelligence, Large Language Models, Machine Learning, Computer Science, and Quantitative Finance. It contains a wide range of resources, including theory, applications, conferences, essentials, foundations, system design, computer systems, finance, and job interview questions. The repository covers topics such as AI systems, multi-agent systems, deep learning theory and applications, system design interviews, C++ design patterns, high-frequency finance, algorithmic trading, stochastic volatility modeling, and quantitative investing. It is a comprehensive collection of materials for individuals interested in these fields.

LLMs in Production is a repository for the book with Manning Publications, containing chapter listings and setup instructions. It provides environments for each chapter, linters, formatters, and tests. The scripts are designed to be run from the project root.

Nekro Agent is an AI chat plugin and proxy execution bot that is highly scalable, offers high freedom, and has minimal deployment requirements. It features context-aware chat for group/private chats, custom character settings, sandboxed execution environment, interactive image resource handling, customizable extension development interface, easy deployment with docker-compose, integration with Stable Diffusion for AI drawing capabilities, support for various file types interaction, hot configuration updates and command control, native multimodal understanding, visual application management control panel, CoT (Chain of Thought) support, self-triggered timers and holiday greetings, event notification understanding, and more. It allows for third-party extensions and AI-generated extensions, and includes features like automatic context trigger based on LLM, and a variety of basic commands for bot administrators.

DistillKitPlus is an open-source toolkit designed for knowledge distillation (KLD) in low computation resource settings. It supports logit distillation, pre-computed logits for memory-efficient training, LoRA fine-tuning integration, and model quantization for faster inference. The toolkit utilizes a JSON configuration file for project, dataset, model, tokenizer, training, distillation, LoRA, and quantization settings. Users can contribute to the toolkit and contact the developers for technical questions or issues.

LLaSA_training is a repository focused on training models for speech synthesis using a large amount of open-source speech data. The repository provides instructions for finetuning models and offers pre-trained models for multilingual speech synthesis. It includes tools for training, data downloading, and data processing using specialized tokenizers for text and speech sequences. The repository also supports direct usage on Hugging Face platform with specific codecs and collections.

This is a no-nonsense async Scala client for OpenAI API supporting all the available endpoints and params including streaming, chat completion, vision, and voice routines. It provides a single service called OpenAIService that supports various calls such as Models, Completions, Chat Completions, Edits, Images, Embeddings, Batches, Audio, Files, Fine-tunes, Moderations, Assistants, Threads, Thread Messages, Runs, Run Steps, Vector Stores, Vector Store Files, and Vector Store File Batches. The library aims to be self-contained with minimal dependencies and supports API-compatible providers like Azure OpenAI, Azure AI, Anthropic, Google Vertex AI, Groq, Grok, Fireworks AI, OctoAI, TogetherAI, Cerebras, Mistral, Deepseek, Ollama, FastChat, and more.

Search-R1 is a tool that trains large language models (LLMs) to reason and call a search engine using reinforcement learning. It is a reproduction of DeepSeek-R1 methods for training reasoning and searching interleaved LLMs, built upon veRL. Through rule-based outcome reward, the base LLM develops reasoning and search engine calling abilities independently. Users can train LLMs on their own datasets and search engines, with preliminary results showing improved performance in search engine calling and reasoning tasks.

llm-gemini is a plugin that provides API access to Google's Gemini models. It allows users to configure and run various Gemini models for tasks such as generating text, processing images, transcribing audio, and executing code. The plugin supports multi-modal inputs including images, audio, and video, and can output JSON objects. Additionally, it enables chat interactions with the model and supports different embedding models for text processing. Users can also run similarity searches on embedded data. The plugin is designed to work in conjunction with LLM and offers extensive documentation for development and usage.

Claudine is an AI agent designed to reason and act autonomously, leveraging the Anthropic API, Unix command line tools, HTTP, local hard drive data, and internet data. It can administer computers, analyze files, implement features in source code, create new tools, and gather contextual information from the internet. Users can easily add specialized tools. Claudine serves as a blueprint for implementing complex autonomous systems, with potential for customization based on organization-specific needs. The tool is based on the anthropic-kotlin-sdk and aims to evolve into a versatile command line tool similar to 'git', enabling branching sessions for different tasks.

Trubrics is a Python client for event tracking and analyzing LLM interactions. It offers fast and non-blocking queuing system with automatic flushing to Trubrics API. Users can track events and LLM interactions, adjust logging verbosity, and configure flush intervals and batch sizes. The tool simplifies tracking user interactions and analyzing data for LLM applications.

Jina-Serve is a framework for building and deploying AI services that communicate via gRPC, HTTP and WebSockets. It provides native support for major ML frameworks and data types, high-performance service design with scaling and dynamic batching, LLM serving with streaming output, built-in Docker integration and Executor Hub, one-click deployment to Jina AI Cloud, and enterprise-ready features with Kubernetes and Docker Compose support. Users can create gRPC-based AI services, build pipelines, scale services locally with replicas, shards, and dynamic batching, deploy to the cloud using Kubernetes, Docker Compose, or JCloud, and enable token-by-token streaming for responsive LLM applications.

OmniAI provides a unified Ruby API for integrating with multiple AI providers, streamlining AI development by offering a consistent interface for features such as chat, text-to-speech, speech-to-text, and embeddings. It ensures seamless interoperability across platforms and effortless switching between providers, making integrations more flexible and reliable.

OpenHealth is an AI health assistant that helps users manage their health data by leveraging AI and personal health information. It allows users to consolidate health data, parse it smartly, and engage in contextual conversations with GPT-powered AI. The tool supports various data sources like blood test results, health checkup data, personal physical information, family history, and symptoms. OpenHealth aims to empower users to take control of their health by combining data and intelligence for actionable health management.

BeeAI is an open platform that helps users discover, run, and compose AI agents from any framework and language. It offers a framework-agnostic approach, allowing seamless integration of AI agents regardless of the language or platform. Users can build complex workflows using simple building blocks, explore a catalog of powerful agents with integrated search, and benefit from the BeeAI ecosystem with first-class support for Python and TypeScript agent developers.

Probe is an AI-friendly, fully local, semantic code search tool designed to power the next generation of AI coding assistants. It combines the speed of ripgrep with the code-aware parsing of tree-sitter to deliver precise results with complete code blocks, making it perfect for large codebases and AI-driven development workflows. Probe is fully local, keeping code on the user's machine without relying on external APIs. It supports multiple languages, offers various search options, and can be used in CLI mode, MCP server mode, AI chat mode, and web interface. The tool is designed to be flexible, fast, and accurate, providing developers and AI models with full context and relevant code blocks for efficient code exploration and understanding.

Google GenerativeAI (Gemini) is an unofficial C# .Net SDK based on REST APIs for accessing Google Gemini models. It offers a complete rewrite of the previous SDK with improved performance, flexibility, and ease of use. The SDK seamlessly integrates with LangChain.net, providing easy methods for JSON-based interactions and function calling with Google Gemini models. It includes features like enhanced JSON mode handling, function calling with code generator, multi-modal functionality, Vertex AI support, multimodal live API, image generation and captioning, retrieval-augmented generation with Vertex RAG Engine and Google AQA, easy JSON handling, Gemini tools and function calling, multimodal live API, and more.

Bedrock Engineer is an autonomous software development agent application that utilizes Amazon Bedrock. It allows users to customize, create/edit files, execute commands, search the web, use a knowledge base, utilize multi-agents, generate images, and more. The tool provides an interactive chat interface with AI agents, file system operations, web search capabilities, project structure management, code analysis, code generation, data analysis, agent and tool customization, chat history management, and multi-language support. Users can select and customize agents, choose from various tools like file system operations, web search, Amazon Bedrock integration, and system command execution. Additionally, the tool offers features for website generation, connecting to design system data sources, AWS Step Functions ASL definition generation, diagram creation using natural language descriptions, and multi-language support.

LLMVoX is a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming Text-to-Speech (TTS) system designed to convert text outputs from Large Language Models into high-fidelity streaming speech with low latency. It achieves significantly lower Word Error Rate compared to speech-enabled LLMs while operating at comparable latency and speech quality. Key features include being lightweight & fast with only 30M parameters, LLM-agnostic for easy integration with existing models, multi-queue streaming for continuous speech generation, and multilingual support for easy adaptation to new languages.

Dispider is an implementation enabling real-time interactions with streaming videos, providing continuous feedback in live scenarios. It separates perception, decision-making, and reaction into asynchronous modules, ensuring timely interactions. Dispider outperforms VideoLLM-online on benchmarks like StreamingBench and excels in temporal reasoning. The tool requires CUDA 11.8 and specific library versions for optimal performance.

HuggingArxiv is a tool designed to push research papers related to large language models from Arxiv. It helps users stay updated with the latest developments in the field of large language models by providing notifications and access to relevant papers.

Factorio Learning Environment is an open source framework designed for developing and evaluating LLM agents in the game of Factorio. It provides two settings: Lab-play with structured tasks and Open-play for building large factories. Results show limitations in spatial reasoning and automation strategies. Agents interact with the environment through code synthesis, observation, action, and feedback. Tools are provided for game actions and state representation. Agents operate in episodes with observation, planning, and action execution. Tasks specify agent goals and are implemented in JSON files. The project structure includes directories for agents, environment, cluster, data, docs, eval, and more. A database is used for checkpointing agent steps. Benchmarks show performance metrics for different configurations.

This repository collects various LLM, AI-related models, applications, and datasets, including LLM-Chat for dialogue models, LLMs for large models, so-vits-svc for sound-related models, stable-diffusion for image-related models, and virtual-digital-person for generating videos. It also provides resources for deep learning courses and overviews, AI competitions, and specific AI tasks such as text, image, voice, and video processing.

Gitleaks is a tool for detecting secrets like passwords, API keys, and tokens in git repos, files, and whatever else you wanna throw at it via stdin. It can be installed using Homebrew, Docker, or Go, and is available in binary form for many popular platforms and OS types. Gitleaks can be implemented as a pre-commit hook directly in your repo or as a GitHub action. It offers scanning modes for git repositories, directories, and stdin, and allows creating baselines for ignoring old findings. Gitleaks also provides configuration options for custom secret detection rules and supports features like decoding encoded text and generating reports in various formats.

Co-LLM-Agents is a repository containing codes for the paper 'Building Cooperative Embodied Agents Modularly with Large Language Models'. The project focuses on developing cooperative embodied agents using large language models, with a specific emphasis on the ThreeDWorld Multi-Agent Transport environment. The repository provides implementations, installation instructions, and example scripts for running experiments with the CoELA model. It extends the ThreeDWorld Transport Challenge into a multi-agent setting, enabling agents to transport target objects using containers and communicate with each other. Additionally, it includes the Communicative Watch-And-Help challenge, where agents can send messages to each other while performing tasks such as preparing meals, washing dishes, and setting up dinner tables.

The 'judges' repository is a small library designed for using and creating LLM-as-a-Judge evaluators. It offers a curated set of LLM evaluators in a low-friction format for various use cases, backed by research. Users can use these evaluators off-the-shelf or as inspiration for building custom LLM evaluators. The library provides two types of judges: Classifiers that return boolean values and Graders that return scores on a numerical or Likert scale. Users can combine multiple judges using the 'Jury' object and evaluate input-output pairs with the '.judge()' method. Additionally, the repository includes detailed instructions on picking a model, sending data to an LLM, using classifiers, combining judges, and creating custom LLM judges with 'AutoJudge'.

LM Studio Python SDK provides a convenient API for interacting with LM Studio instance, including text completion and chat response functionalities. The SDK allows users to manage websocket connections and chat history easily. It also offers tools for code consistency checks, automated testing, and expanding the API.