BALROG is a benchmark tool designed to evaluate agentic Long-Longitudinal Memory (LLM) and Vision-Language Memory (VLM) capabilities using reinforcement learning environments. It provides a comprehensive assessment of agentic abilities, supports both language and vision-language models, integrates with popular AI APIs, and allows for easy integration of custom agents, new environments, and models.

Devika is an advanced AI software engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika utilizes large language models, planning and reasoning algorithms, and web browsing abilities to intelligently develop software. Devika aims to revolutionize the way we build software by providing an AI pair programmer who can take on complex coding tasks with minimal human guidance. Whether you need to create a new feature, fix a bug, or develop an entire project from scratch, Devika is here to assist you.

VisualWebArena is a benchmark for evaluating multimodal autonomous language agents through diverse and complex web-based visual tasks. It builds on the reproducible evaluation introduced in WebArena. The repository provides scripts for end-to-end training, demos to run multimodal agents on webpages, and tools for setting up environments for evaluation. It includes trajectories of the GPT-4V + SoM agent on VWA tasks, along with human evaluations on 233 tasks. The environment supports OpenAI models and Gemini models for evaluation.

Simply is a minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models. It is quick to fork and hack for fast iteration, with minimal abstractions and dependencies for a simple and self-contained codebase. Users can easily implement new architectures, optimizers, training losses, etc., in a few hours. Simply allows users to get started with hacking quickly, providing example commands for local testing and running on Google Cloud TPUs. The main dependencies include Jax for model and training, Orbax for checkpoint management, and Grain for data pipeline. Users can install dependencies, set up model checkpoints and datasets, and cite the tool if found helpful.

A comprehensive guide to building Retrieval Augmented Generation (RAG)-based LLM applications for production. This guide covers developing a RAG-based LLM application from scratch, scaling the major components, evaluating different configurations, implementing LLM hybrid routing, serving the application in a highly scalable and available manner, and sharing the impacts LLM applications have had on products.

OSWorld is a benchmarking tool designed to evaluate multimodal agents for open-ended tasks in real computer environments. It provides a platform for running experiments, setting up virtual machines, and interacting with the environment using Python scripts. Users can install the tool on their desktop or server, manage dependencies with Conda, and run benchmark tasks. The tool supports actions like executing commands, checking for specific results, and evaluating agent performance. OSWorld aims to facilitate research in AI by providing a standardized environment for testing and comparing different agent baselines.

Knowledge Graph of Thoughts (KGoT) is an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively. The KGoT system consists of three main components: the Controller, the Graph Store, and the Integrated Tools, each playing a critical role in the task-solving process.

SambaNova AI Starter Kits is a collection of open-source examples and guides designed to facilitate the deployment of AI-driven use cases for developers and enterprises. The kits cover various categories such as Data Ingestion & Preparation, Model Development & Optimization, Intelligent Information Retrieval, and Advanced AI Capabilities. Users can obtain a free API key using SambaNova Cloud or deploy models using SambaStudio. Most examples are written in Python but can be applied to any programming language. The kits provide resources for tasks like text extraction, fine-tuning embeddings, prompt engineering, question-answering, image search, post-call analysis, and more.

The Microsoft Health Intelligence Machine Learning Toolbox is a repository that provides low-level and high-level building blocks for Machine Learning / AI researchers and practitioners. It simplifies and streamlines work on deep learning models for healthcare and life sciences by offering tested components such as data loaders, pre-processing tools, deep learning models, and cloud integration utilities. The repository includes two Python packages, 'hi-ml-azure' for helper functions in AzureML, 'hi-ml' for ML components, and 'hi-ml-cpath' for models and workflows related to histopathology images.

This repository provides AI tools for developers through Docker containers, enabling agentic workflows. It allows users to create complex workflows using Dockerized tools and Markdown, leveraging various LLM models. The core features include Dockerized tools, conversation loops, multi-model agents, project-first design, and trackable prompts stored in a git repo.

The AI Scientist is a comprehensive system for fully automatic scientific discovery, enabling Foundation Models to perform research independently. It aims to tackle the grand challenge of developing agents capable of conducting scientific research and discovering new knowledge. The tool generates papers on various topics using Large Language Models (LLMs) and provides a platform for exploring new research ideas. Users can create their own templates for specific areas of study and run experiments to generate papers. However, caution is advised as the codebase executes LLM-written code, which may pose risks such as the use of potentially dangerous packages and web access.

ForecastBench is a dynamic benchmark tool for evaluating LLM forecasting accuracy with human comparison groups. It provides a contamination-free environment and serves as a proxy for general intelligence. The tool offers leaderboards and datasets updated nightly, along with instructions for submitting models. Users can explore detailed information on the wiki and cite the tool using the provided BibTeX citation. Developers can set up the tool locally, run GCP Cloud Functions, and contribute to the project by following specific guidelines.

Open Deep Research is an open-source project that serves as a clone of Open AI's Deep Research experiment. It utilizes Firecrawl's extract and search method along with a reasoning model to conduct in-depth research on the web. The project features Firecrawl Search + Extract, real-time data feeding to AI via search, structured data extraction from multiple websites, Next.js App Router for advanced routing, React Server Components and Server Actions for server-side rendering, AI SDK for generating text and structured objects, support for various model providers, styling with Tailwind CSS, data persistence with Vercel Postgres and Blob, and simple and secure authentication with NextAuth.js.

AgentIQ is a flexible library designed to seamlessly integrate enterprise agents with various data sources and tools. It enables true composability by treating agents, tools, and workflows as simple function calls. With features like framework agnosticism, reusability, rapid development, profiling, observability, evaluation system, user interface, and MCP compatibility, AgentIQ empowers developers to move quickly, experiment freely, and ensure reliability across agent-driven projects.

Library for connecting AI agents to Todoist, enabling them to access and modify a Todoist account on the user's behalf. Tools can be used through an MCP server or integrated into other projects for AI conversational interfaces. Reusable tools allow for complete workflows, balancing flexibility and efficiency for LLMs. Early-stage project with more tools planned. Designed to provide a small set of tools for various AI interfaces.

Hashbrown is a lightweight and efficient hashing library for Python, designed to provide easy-to-use cryptographic hashing functions for secure data storage and transmission. It supports a variety of hashing algorithms, including MD5, SHA-1, SHA-256, and SHA-512, allowing users to generate hash values for strings, files, and other data types. With Hashbrown, developers can quickly implement data integrity checks, password hashing, digital signatures, and other security features in their Python applications.

BALROG is a benchmark tool designed to evaluate agentic Long-Longitudinal Memory (LLM) and Vision-Language Memory (VLM) capabilities using reinforcement learning environments. It provides a comprehensive assessment of agentic abilities, supports both language and vision-language models, integrates with popular AI APIs, and allows for easy integration of custom agents, new environments, and models.

Labelbox is a data-centric AI platform for enterprises to develop, optimize, and use AI to solve problems and power new products and services. Enterprises use Labelbox to curate data, generate high-quality human feedback data for computer vision and LLMs, evaluate model performance, and automate tasks by combining AI and human-centric workflows. The academic & research community uses Labelbox for cutting-edge AI research.

Promptfoo is a tool for testing and evaluating LLM output quality. With promptfoo, you can build reliable prompts, models, and RAGs with benchmarks specific to your use-case, speed up evaluations with caching, concurrency, and live reloading, score outputs automatically by defining metrics, use as a CLI, library, or in CI/CD, and use OpenAI, Anthropic, Azure, Google, HuggingFace, open-source models like Llama, or integrate custom API providers for any LLM API.

Vespa is a platform that performs operations such as selecting a subset of data in a large corpus, evaluating machine-learned models over the selected data, organizing and aggregating it, and returning it, typically in less than 100 milliseconds, all while the data corpus is continuously changing. It has been in development for many years and is used on a number of large internet services and apps which serve hundreds of thousands of queries from Vespa per second.

The Vertex AI SDK for Python is a library that provides a convenient way to use the Vertex AI API. It offers a high-level interface for creating and managing Vertex AI resources, such as datasets, models, and endpoints. The SDK also provides support for training and deploying custom models, as well as using AutoML models. With the Vertex AI SDK for Python, you can quickly and easily build and deploy machine learning models on Vertex AI.

ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

Flower is a framework for building federated learning systems. It is designed to be customizable, extensible, framework-agnostic, and understandable. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.