AI Agents & Automation

tokenizers is an open-source library developed by Hugging Face, offering highly optimized and versatile tokenizers for natural language processing tasks. Implemented primarily in Rust, it boasts exceptional performance, capable of tokenizing a gigabyte of text on a server's CPU in less than 20 seconds. The library supports training new vocabularies and tokenizing text using popular models like Byte-Pair Encoding, WordPiece, and Unigram. It includes features such as alignment tracking during normalization, ensuring that the original sentence segments corresponding to tokens can always be retrieved. Additionally, it handles pre-processing steps like truncation, padding, and adding special tokens required by various models, making it suitable for both research and production environments.

Collate is a privacy-first AI reader designed for Mac users, enabling them to chat with, summarize, and extract insights from PDF documents entirely offline. This local-first approach ensures that all processing runs directly on your device, guaranteeing complete privacy as your documents never leave your computer. It supports both Apple Silicon (M1, M2, M3) and Intel Macs running macOS 13.1 or later. Users can ask questions, get instant summaries, and receive citation-backed answers with automatic highlighting. Collate also supports multi-PDF chat for comparative research, folder organization, and the ability to export summaries and conversations in various formats like PDF, rich text, or email. It's completely free to download and use, with no subscription fees or usage limits.

Trajectory Transformer is an open-source code release that implements offline reinforcement learning as a sequence modeling problem. Based on the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem," this tool provides a framework for training models to predict trajectories. It includes scripts for training transformers on various datasets and for planning with these models. The project also offers pretrained models for multiple datasets, allowing users to quickly experiment and reproduce results. It supports installation via conda or Docker, and provides utilities for running jobs on Azure, making it suitable for researchers and engineers in reinforcement learning and robotics.

TASO, the Tensor Algebra SuperOptimizer for Deep Learning, significantly enhances the performance of deep neural network models. It achieves this by automatically generating and verifying graph transformations to build a vast search space of computation graphs equivalent to the original DNN model. Employing a cost-based search algorithm, TASO discovers highly optimized computation graphs, leading to up to a 3x performance improvement over graph optimizers in current deep learning frameworks. It supports optimizing pre-trained models in ONNX, TensorFlow, and PyTorch formats, and offers a Python interface for arbitrary DNN architectures. Optimized graphs can be exported to ONNX for use in existing deep learning frameworks, maintaining original model accuracy.

Texar is a comprehensive toolkit designed to support a broad range of machine learning tasks, with a particular focus on natural language processing and text generation. Built on TensorFlow, it offers a rich library of modular and easy-to-use ML components and functionalities, enabling both researchers and practitioners to rapidly prototype and experiment with models. Key features include support for pre-trained models like BERT, GPT2, and XLNet, and full customizability at multiple abstraction levels. Texar is versatile, supporting various tasks, models, algorithms, data processing, and evaluation methods, from encoder-decoder architectures to reinforcement learning and adversarial learning. It emphasizes modularity for maximum re-use and clean APIs, based on a principled decomposition of learning, inference, and model architecture. The toolkit also supports distributed model training with multiple GPUs and provides extensive documentation and examples.

torch-template-for-deep-learning is an open-source project providing PyTorch implementations of a wide array of classical backbone Convolutional Neural Networks (CNNs), alongside essential tools for deep learning development. It includes various data enhancement techniques like Cutout and Mixup, a collection of torch loss functions such as Focal Loss and Dice Loss, and numerous attention mechanisms including SE Attention and Self Attention. The template also features deployment modes for PyTorch models, conversion utilities from TensorFlow to PyTorch, and Class Activation Mapping (CAM) methods. This comprehensive resource aims to simplify and accelerate the development of deep learning applications by offering readily available and well-structured components.

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.

This tool entry describes a robust security framework for managing multiple AI agents using a single markdown file per agent. It outlines how Ultrathink, an e-commerce store run autonomously by AI agents, governs its eight specialized agents. The core of the system involves defining per-role tool restrictions in YAML frontmatter within each agent's markdown instruction file, limiting what each agent can access, modify, or destroy. A shared CLAUDE.md file establishes project-wide rules that all agents inherit, ensuring hard constraints like mandatory security reviews. The system also incorporates daily automated audits performed by a security agent, which reviews instruction files and code changes to catch vulnerabilities and capability creep. This file-based governance prioritizes rapid evolution and auditability over cryptographic signing for internal systems.

iVoz Ai offers an advanced AI Voice Agent designed to empower businesses across various sectors by automating lead generation and customer interactions. This tool enables instant AI voice agents and real-time solutions, redefining business communication. It integrates seamlessly with existing CRM systems, ensuring a smooth and hassle-free experience. iVoz Ai helps businesses save up to 70% on costs by only charging for answered calls, making it a cost-effective solution for acquiring superior leads. The platform supports multilingual interactions with auto language detection and industry-specific vocabulary, catering to diverse customer bases in industries like real estate, insurance, financial services, healthcare, and education.

Show Facebook Computer Vision Tags is a simple browser extension for Chrome and Firefox designed to make users aware of the automated image tagging performed by Facebook's Deep ConvNet. Since April 2016, Facebook has been adding alt tags to uploaded images, populated with keywords describing their content. This extension overlays these generated tags directly onto photos in your Facebook timeline, allowing you to see what objects, activities, locations, and events Facebook's AI identifies. While these tags improve accessibility for blind users, the extension's primary goal is to highlight the extensive data extraction capabilities of major internet companies from user photographs, prompting users to consider their digital privacy. It's a straightforward tool for anyone curious about the information Facebook gleans from their visual content.

Functionary is a powerful language model designed to interpret and execute functions and plugins, offering advanced tool-use capabilities. It intelligently determines when to trigger functions, whether in parallel or serially, and can effectively understand and utilize their outputs. Function definitions are provided using JSON Schema Objects, mirroring the approach of OpenAI GPT function calls. The platform supports various deployment options, including vLLM, SGLang, and Text-Generation-Inference (TGI) servers, with Docker compatibility for ease of setup. Functionary also offers LoRA support for fine-tuning and dynamic adapter serving, along with OpenAI-compatible API usage for seamless integration into existing workflows. It includes features like code interpretation and multi-turn conversations, making it a versatile solution for developers building AI agents.

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.

Seed1.5-VL is a powerful and efficient vision-language foundation model developed by the ByteDance Seed Team. It is engineered to advance general-purpose multimodal understanding and reasoning, demonstrating state-of-the-art performance across numerous public benchmarks. The model features a relatively modest architecture, comprising a 532M vision encoder and a 20B active parameter MoE LLM, yet it excels in complex reasoning tasks, OCR, diagram understanding, visual grounding, 3D spatial understanding, and video comprehension. Seed1.5-VL also shows strong capabilities in interactive agent tasks like GUI control and gameplay, making it versatile for various applications. The project provides a usage cookbook with diverse code samples to help developers effectively leverage its API.

The Language Model Council Website provides a platform for in-depth exploration and analysis of large language models, specifically focusing on their performance in emotional intelligence tasks. Users can delve into detailed evaluations by selecting various scenarios, different models, and specific judges. This allows for a comprehensive comparison of how different AI models respond to emotionally nuanced prompts and how human judges assess these responses. The platform is designed to offer insights into the capabilities and limitations of current language models in understanding and generating emotionally intelligent text, making it a valuable resource for researchers and AI enthusiasts alike.

File AI is an AI-native data preparation and automation platform designed to unify data capture, governance, and orchestration into auditable AI workflows. It transforms unstructured data into trusted intelligence across various enterprise functions. The platform features fileForge, an AI-native data intelligence engine, alongside purpose-built solutions like fileLedger for financial operations automation and fileShield for intelligent case management in regulated environments. Key capabilities include multimodal AI OCR, classification, schema extraction, SOP-driven workflow engines, and over 100 ERP and system integrations. File AI aims to build the foundation for agentic AI at scale, providing the context, validation, and control needed for AI agents to act with confidence in real enterprise workflows.

NovaPlan AI is an intelligent study planning tool specifically designed for students. It leverages artificial intelligence to help users effectively organize their coursework, manage upcoming deadlines, and optimize their overall learning schedules. The platform creates personalized academic plans, taking into account individual learning styles and specific course requirements to ensure a tailored and efficient study experience. By automating the planning process, NovaPlan aims to reduce stress and improve academic performance for students.

Simd is a free, open-source C++ image processing and machine learning library designed for C and C++ programmers. It offers a wide array of high-performance algorithms, including pixel format conversion, image scaling and filtration, statistical information extraction, motion detection, object detection, classification, and neural network functionalities. The library is highly optimized, utilizing various SIMD CPU extensions such as SSE, AVX, AVX-512, and AMX for x86/x64, NEON for ARM, and HVX for Hexagon architectures. Simd provides both a C API and C++ classes for ease of access, supporting dynamic and static linking across Windows and Linux with MSVS, G++, and Clang compilers. It also includes a Python wrapper for broader accessibility.

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.

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.

Semantra is a multipurpose command-line tool designed for semantic search across local documents, including text and PDF files. Unlike traditional keyword matching, Semantra allows users to query by meaning, providing a more intuitive and powerful search experience. It processes documents locally, launching a web search application for interactive querying. This tool is particularly useful for individuals needing to sift through large volumes of information, such as journalists analyzing leaked documents, researchers exploring academic papers, or students engaging with literature. Semantra prioritizes privacy and security by performing all analysis on the user's computer, and it offers configurable options for embedding models and search parameters.

HtmlToClaude is a browser extension designed to enhance interactions with Claude AI by enabling seamless capture of HTML content directly from web pages. This tool simplifies the process of feeding web-based information into Claude, making it highly efficient for tasks that require referencing online data. It's particularly useful for researchers who need to analyze web content or content creators looking to integrate external information into their AI-generated drafts. By bridging the gap between web browsing and AI interaction, HtmlToClaude helps users leverage the vast amount of information available online to enrich their AI conversations and outputs.

SPO (Self-Supervised Prompt Optimization) is an AI tool hosted on Hugging Face Spaces designed to enhance the performance of language models by optimizing user prompts. It allows users to create or select templates, configure various settings, and initiate an optimization process to achieve better responses from AI models. This application is particularly useful for prompt engineers and researchers looking to fine-tune their interactions with large language models, ensuring more accurate and relevant outputs through a self-supervised learning approach. The tool aims to streamline the prompt engineering workflow, making it easier to experiment with and improve prompt effectiveness.

Zamp provides advanced digital employees, specifically its AI agent named Pace, designed to handle operational work that humans shouldn't have to do. Pace learns from existing business processes, integrates with various systems, and uses feedback to automate manual tasks with high accuracy. It can extract documents, automate browser actions, make decisions, and communicate, getting up to speed within four weeks. Zamp emphasizes enterprise-grade security, offering end-to-end encryption, audit trails, and SOX compliance, making it suitable for leading public companies and financial institutions. The platform aims to free human teams to focus on strategic growth and innovation by handling 99% of operational work.

Ichigo Llama3.1 S Instruct is a Hugging Face Space designed to convert spoken audio into text. Users can easily interact with the application by either uploading an audio file or recording directly within the interface. Once the audio input is provided, the tool processes the spoken content and produces a corresponding text transcript. This application serves as a straightforward solution for anyone needing to transcribe audio, offering a direct way to experiment with language models and prototype AI applications that involve speech-to-text functionality. Its simplicity makes it accessible for various users looking to leverage AI for audio transcription tasks.