AI Agents & Automation

e3nn is an open-source, modular framework designed to facilitate the development of neural networks with Euclidean symmetry. It provides fundamental mathematical operations such as tensor products and spherical harmonics, essential for building E(3) equivariant neural networks. The library is under active development, with breaking changes indicated by version number increments. It is recommended to install using pip, and users can contribute to its development or seek help through discussions and bug reports on GitHub. The framework is backed by research papers on Euclidean Neural Networks and e3nn itself, with BibTeX entries available for citation.

embetter is an open-source Python library designed to provide useful embeddings for scikit-learn pipelines, making it easy to quickly build proof of concepts for machine learning tasks. It offers scikit-learn compatible embeddings for both computer vision and text data, simplifying the integration of advanced embedding techniques into existing workflows. The library is particularly helpful for bulk labeling efforts and plays well with tools like scikit-partial for handling out-of-core datasets. It includes components for grabbing data from pandas DataFrames, various encoders for images (TimmEncoder, ColorHistogramEncoder) and text (SentenceEncoder, MatryoshkaEncoder), and multi-modal models like ClipEncoder. Additionally, it supports finetuning components and external embedding providers requiring API keys, such as Cohere and OpenAI.

DyNet is a powerful open-source neural network library, primarily developed by Carnegie Mellon University, with contributions from many others. Written in C++ and offering Python bindings, it's engineered for efficiency on both CPU and GPU architectures. A key differentiator is its ability to handle dynamic neural network structures, which can adapt and change for each training instance. This makes DyNet particularly well-suited for complex natural language processing tasks, where it has been successfully applied to build state-of-the-art systems for syntactic parsing, machine translation, and morphological inflection. The toolkit provides comprehensive documentation, tutorials for both C++ and Python, and examples to help users get started with its auto-batching feature and other functionalities.

DropoutUncertaintyExps is an open-source project containing the experimental code for the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning." The repository provides a framework for researchers to replicate and build upon the uncertainty experiments, with adaptations reflecting community feedback and bug fixes. It is based on José Miguel Hernández-Lobato's work on probabilistic backpropagation for scalable learning of Bayesian Neural Networks. The code utilizes datasets from the UCI machine learning repository, with specific data splits to ensure comparability of results. It details the methodology for hyperparameter tuning using grid-search and reports RMSE and log-likelihood metrics for various datasets, offering a valuable resource for academic research in deep learning uncertainty.

finetrainers is a work-in-progress library from Hugging Face designed for scalable and memory-optimized training of diffusion models. It provides support for various commonly used training algorithms, including DDP, FSDP-2, HSDP, and CP. Key features include LoRA and full-rank finetuning, conditional control training, and memory-efficient single-GPU training. The library also supports multiple attention backends like flash, flex, sage, and xformers, along with auto-detection of common dataset formats. It's built to handle combined image/video datasets, multi-resolution bucketing, and offers memory-efficient precomputation. finetrainers is recommended for use with PyTorch 2.5.1 or above for optimal performance and reproducibility.

ExLlamaV3 is an inference library specifically designed for running Large Language Models (LLMs) locally on modern consumer-class GPUs. Its headline feature is the new EXL3 quantization format, which is based on QTIP from Cornell RelaxML, allowing for efficient model conversion in a single step. The library supports flexible tensor-parallel and expert-parallel inference setups, and provides an OpenAI-compatible server via TabbyAPI for local or remote inference. It also includes features like continuous, dynamic batching, HF Transformers plugin support, speculative decoding, and 2-8 bit cache quantization. ExLlamaV3 aims to make advanced quantization techniques more accessible and less resource-intensive, enabling users to run large models like Llama-3.1-70B with minimal VRAM.

FlexFlow Train is an open-source deep learning framework designed to accelerate distributed deep neural network (DNN) training. It achieves this by automatically searching for and implementing efficient parallelization strategies. The tool helps optimize the training process, reducing the time required for model development and improving overall efficiency. It supports various deep learning models and hardware configurations, making it a versatile solution for researchers and developers working with large-scale DNNs. The project is developed and maintained by teams from several prominent institutions, including CMU, Facebook, Los Alamos National Lab, MIT, Stanford, and UCSD.

open-llms is a comprehensive GitHub repository that serves as a curated list of open Large Language Models (LLMs) explicitly licensed for commercial use, including Apache 2.0, MIT, and OpenRAIL-M. This resource is invaluable for developers, researchers, and businesses looking to integrate open-source LLMs into their applications without licensing concerns. The repository details each model's release date, available checkpoints, associated research papers or blog posts, parameter sizes, context lengths, and specific licenses. It also includes a dedicated section for open LLMs tailored for code generation, offering insights into models like SantaCoder, CodeGen2, and StarCoder. Contributions to the list are welcomed, ensuring it remains up-to-date with the latest commercially viable open LLM releases.

Acumino provides AI-powered robot models specifically designed for dexterous industrial automation. By training its AI on extensive robot interaction data, Acumino facilitates the seamless deployment of intelligent robot workers capable of performing complex tasks with high precision. This technology is engineered to offer scalable, reliable, and cost-efficient solutions, significantly enhancing operational efficiency and unlocking substantial return on investment in various industrial environments. Acumino's focus is on transforming manufacturing and logistics through advanced robotics.

FunASR is a fundamental end-to-end speech recognition toolkit designed to bridge the gap between academic research and industrial applications. It offers a comprehensive suite of features including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization, and multi-talker ASR. The toolkit provides convenient scripts and tutorials for both inference and fine-tuning of pre-trained models. FunASR boasts a vast collection of academic and industrial pre-trained models available on ModelScope and Hugging Face, including the highly accurate and efficient Paraformer-large. Recent updates include support for large models like Fun-ASR-Nano-2512 (31 languages), Whisper-large-v3-turbo, and Qwen-Audio multimodal models, alongside continuous improvements in real-time and offline transcription services, memory optimization, and multi-platform support.

free-llm-api-resources is a comprehensive list of services that provide free access or trial credits for API-based Large Language Model (LLM) usage. This resource is invaluable for developers, researchers, and students looking to experiment with LLMs without initial financial commitment. The list details various providers like OpenRouter, Google AI Studio, NVIDIA NIM, Mistral, HuggingFace, and others, specifying their free tiers, usage limits, and available models. It also includes providers offering trial credits such as Fireworks, Baseten, and AI21. The tool emphasizes legitimate services, explicitly excluding those that reverse-engineer existing chatbots, ensuring users find reliable and ethical resources for their projects.

PromptWizard is an open-source, task-aware, agent-driven framework designed for optimizing prompts used with Large Language Models (LLMs). It features a self-evolving mechanism where the LLM itself generates, critiques, and refines its own prompts and in-context learning examples. This iterative feedback loop ensures continuous improvement in task performance. The framework focuses on holistic optimization by evolving both instructions and examples, generating synthetic, diverse, and task-aware examples. It also supports self-generated Chain of Thought (CoT) steps and offers various scenarios for prompt optimization, including with and without training data, and the generation of synthetic examples. Users can configure hyperparameters and integrate with custom datasets, making it a flexible tool for developers and researchers working with LLMs.

GeoTorchAI is a comprehensive spatiotemporal deep learning framework designed for machine learning practitioners. Built on top of PyTorch and Apache Sedona, it facilitates the easy and efficient implementation of deep learning models for various applications. The framework supports both raster imagery datasets, such as satellite imagery classification and segmentation, and spatiotemporal non-imagery datasets for prediction tasks like traffic volume, taxi/bike flow, and weather forecasting. GeoTorchAI includes modules for deep learning and data preprocessing, offering ready-to-use raster and grid datasets, PyTorch layers for popular models, and various transformation operations. It also supports scalable preprocessing on Apache Spark and Apache Sedona, making it a robust solution for large-scale spatiotemporal data analysis.

Avanza Innovations is a global technology company focused on nascent technologies such as Blockchain, Artificial Intelligence, and Robotic Process Automation (RPA). They provide comprehensive services including consultancy, implementation, and program execution management. The company leverages its multi-award-winning blockchain platform, CIPHER, and its AI engine, IMPULSE, to deliver solutions for digital government transformation, financial regulation, trade, and supply chain management. Avanza Innovations also assists organizations in transitioning to Web 3.0, offering strategy, ideation, implementation, and tokenomics expertise. Their solutions cater to a wide range of sectors including government, real estate, healthcare, telecommunication, and finance, aiming to drive digital transformation and efficiency.

AltaML specializes in building vertical AI solutions with an agentic-first approach, aiming to provide organizations with a competitive advantage and a faster return on investment. The company offers services like AI Navigator for strategic AI pathing, AI Foundations for establishing essential skills and systems, and the Agentic AI Lab for prototyping agent-driven solutions. They also have GovLab, tailored for public sector AI needs. AltaML supports industries such as Energy and Industrial Operations, Public Sector, and Health, focusing on mission-critical AI, trusted public services, and compliant healthcare solutions. Their AltaForge platform streamlines the AI development journey from concept to implementation, ensuring smoother deployments and higher success rates.

R-KV is a novel method for redundancy-aware KV cache compression specifically designed for large language models (LLMs) that rely on chain-of-thought (CoT) or self-reflection for reasoning tasks. It addresses the issue of bloated key-value (KV) caches during inference by ranking tokens on-the-fly for both importance and non-redundancy, retaining only the most informative and diverse ones. This approach allows for significant memory savings, up to 90%, and improved throughput (up to 6.6x) during long CoT generation, often with zero or even negative accuracy loss. R-KV is a plug-and-play, training-free solution that acts as a lightweight wrapper for any autoregressive LLM, making it easy to integrate into existing inference pipelines or RL roll-outs.

SGLang is a high-performance serving framework designed for large language models and multimodal models, focusing on low-latency and high-throughput inference. It supports a wide range of hardware, including NVIDIA, AMD, Intel, Google TPUs, and Ascend NPUs, and is compatible with most Hugging Face models and OpenAI APIs. Key features include RadixAttention for prefix caching, a zero-overhead CPU scheduler, prefill-decode disaggregation, speculative decoding, continuous batching, paged attention, and various parallelism techniques. SGLang also supports structured outputs, chunked prefill, quantization, and multi-LoRA batching. It is an open-source project with an active community, adopted by leading enterprises and institutions, and serves as a proven rollout backend for training frontier models.

Self-Refine is an innovative AI research tool designed to empower Large Language Models (LLMs) with the ability to self-correct and enhance their output. The core mechanism involves LLMs generating feedback on their initial work, using this feedback to refine the output, and repeating this process iteratively. This iterative refinement process leads to improved quality and accuracy across various tasks. The tool provides examples and setups for diverse applications, including acronym generation, dialogue response generation, code readability improvement, and tasks like Commongen, GSM-8k, and Yelp. It utilizes 'prompt-lib' for querying LLMs and offers distinct prompt types for initialization, feedback generation, and iteration, making it a versatile platform for exploring self-improving AI systems.

JetBot is an open-source, educational AI robot built on the NVIDIA Jetson Nano platform. Designed to be affordable, it serves as an excellent entry point into AI robotics for enthusiasts and students. The platform includes comprehensive tutorials that guide users from fundamental robotic movements to advanced AI applications like collision avoidance. Its interactive programming interface, accessible via a web browser, simplifies the learning process. By building and utilizing JetBot, users gain practical, hands-on experience essential for developing new AI projects and understanding the principles of artificial intelligence in a tangible way. The project fosters a growing community for support and collaboration.

RynnVLA-002 is an autoregressive action world model developed by Alibaba-Damo Academy, designed to unify action and image understanding and generation within a single framework. It integrates Vision-Language-Action (VLA) models and world models, building upon its predecessor, WorldVLA. Key enhancements in RynnVLA-002 include a continuous Action Transformer, wrist camera input and generation capabilities, and state input. The model has demonstrated high performance, achieving a 97.4% success rate on the LIBERO benchmark. It offers both VLA model capabilities for generating actions from text instructions and image observations, and World Model capabilities for predicting future frames based on current frames and actions. The project provides models, training code, and evaluation code for both LIBERO simulation and real-world LeRobot experiments.

SOMAS implements a Multi-Agent System (MAS) framework specifically designed for human-machine collaborative crisis response. It leverages vision-language models (VL) and reinforcement learning (RL) to significantly enhance safety and reliability in critical situations. The framework features real-time task execution with modular task chains, built-in safety rules, and human oversight. It also includes a simulation training system with an experience replay library for risk prediction and optimization, alongside a dynamic trust mechanism that balances task utility and safety constraints through RL. SOMAS offers a dual-mode architecture for online execution and offline simulation, and has developed the first fine-tuned safe LLM and training dataset for emergency scenarios, demonstrating improved helpfulness and reduced risk response rates.

SQLite-Vector is a cross-platform, ultra-efficient SQLite extension designed to integrate vector search directly into embedded databases. It operates seamlessly across iOS, Android, Windows, Linux, and macOS, utilizing minimal memory (defaulting to just 30MB). This tool eliminates the need for complex preindexing, allowing for immediate vector search on existing data stored as BLOBs in ordinary SQLite tables. It supports various vector types including Float32, Float16, BFloat16, Int8, UInt8, and 1Bit, alongside highly optimized distance functions like L2, Cosine, and Dot Product. SQLite-Vector is ideal for Edge AI applications, enabling offline, privacy-preserving AI workloads with real-time performance directly on devices.

Hellbender Inc. specializes in crafting cutting-edge Computer Vision solutions, offering advanced AI vision systems and industrial AI cameras. They provide mission-critical hardware and software infrastructure for AI-driven perception systems, engineered for the edge in autonomy, robotics, and industrial applications. Their services include design, development, and turn-key manufacturing, with a focus on producing high-quality hardware in America. Hellbender also offers Computer Vision as a Service (CVaaS) for bespoke systems, addressing complex problems. They are a Raspberry Pi Design Partner and emphasize their commitment to employees, community, and the environment.

Dalitics specializes in AI and predictive analytics, transforming real-world data into actionable insights to drive business growth and maximize ROI. The company offers comprehensive support to businesses of all sizes, providing expertise in predictive analytics, customer insights, and tailored intricate analyses using both financial and non-financial data. Their approach is personalized, involving issue identification, objective definition, data gathering and privacy, AI model construction and training, and continuous feedback loops for improvement. Key solutions include AI models for churn prediction, cross-selling and upselling, credit scoring systems for Romanian companies, and the Elcano Financial Health Check for in-depth financial analysis.