AI Agents & Automation

Navan AI is an autonomous AI development platform designed to transform Product Requirements Documents (PRDs) into production-ready, tested code. It leverages a Smart Agent Manager (SAM) to orchestrate specialized AI agents through strict Test-Driven Development (TDD) cycles, ensuring quality software delivery without direct human intervention. The platform features a TDD pipeline with RED-GREEN-REFACTOR methodology, where agents like Titan (Test Architect) write failing tests, Dyna (Developer) implements code to pass them, and Argus (Code Reviewer) refactors. SAM acts as the master orchestrator, managing state and enforcing quality gates. Key benefits include autonomous execution, guaranteed TDD enforcement, built-in quality gates, state tracking, smart retries, and automatic documentation generation, accelerating software delivery with built-in quality.

ai-knowledge-graph is an open-source AI-powered tool designed to generate interactive knowledge graphs from unstructured text documents. It leverages large language models (LLMs) to extract Subject-Predicate-Object (SPO) triplets, identify entities, and infer relationships. Key features include automatic text chunking for processing large documents, LLM-assisted entity standardization to ensure consistent naming, and relationship inference to discover connections not explicitly stated. The tool supports any OpenAI-compatible API endpoint, offering flexibility with various LLMs like Ollama, LM Studio, and OpenAI. It generates an interactive HTML visualization with features like color-coded communities, node sizing by importance, and distinct representations for original versus inferred relationships, making complex information easily digestible.

Mobile-use is an open-source AI agent designed to automate mobile device interactions using natural language commands. It allows users to control Android and iOS apps, performing tasks from sending messages to navigating complex interfaces, just like a human. Key features include natural language control, UI-aware automation, and data scraping capabilities, allowing extraction of structured information from any app. The tool is highly extensible and customizable, supporting various LLMs. It has achieved top performance on the AndroidWorld benchmark, demonstrating its effectiveness in mobile automation. Developers can get started via a platform quickstart or by setting up the environment from source, with support for physical Android phones, Android simulators, and iOS simulators.

SAMTok offers a unified mask-token interface specifically designed for Multimodal Large Language Models (MLLMs). This tool enables users to upload an image and provide a text description to automatically generate precise segmentation masks, highlighting specific objects or areas within the image. Beyond automated segmentation, SAMTok also provides functionality for users to manually create custom masks, offering greater control and flexibility in their image analysis tasks. Hosted on Hugging Face Spaces, SAMTok is accessible for various applications, including AI education and development involving MLLMs, by facilitating a consistent and intuitive interaction method.

Small Hours offers Night Watch, a zero-dependency DevOps agent designed to enhance operational efficiency. This agent runs diagnostics, inspects cloud and log signals, and correlates issues with code changes, providing automated root cause analysis. It supports a quick start with simple setup and commands for asking questions, running runbooks, and managing sessions. The tool requires Go 1.23+ and a provider key for OpenAI, Anthropic, or Google APIs, with optional support for cloud CLIs like AWS, gcloud, and Sentry-CLI. It's an open-source solution, allowing for flexible configuration and testing.

qwq-32b-preview-abliterated-q4_k_m.gguf is a language model demo powered by the LLaMA.cpp backend, designed for conversational AI interactions. Users can input messages and receive detailed responses, with options to customize conversation parameters such as temperature and maximum tokens. This tool provides a platform for engaging with a powerful AI model, making it suitable for exploring language generation capabilities and understanding AI-driven conversations. While the current status indicates a build error, its intended functionality focuses on interactive dialogue and customizable AI responses.

Tickles.Ai offers an NSFW AI chatbot platform designed for adult-themed interactions, providing a space for explicit conversations and immersive roleplay scenarios without filters or limits. Users can explore a wide array of AI characters, each with unique personalities and backstories, ranging from anime-inspired figures to realistic personas. The platform emphasizes uncensored chat, allowing for various forms of interaction including roleplay and AI sexting. It features a diverse character library, enabling users to discover, connect, and build relationships with their AI companions.

Dhibot offers an all-in-one AI chatbot solution designed to significantly improve customer support and website engagement. By providing advanced AI chat features, Dhibot helps businesses streamline their customer interactions and enhance the overall user experience on their websites. The platform focuses on delivering interactive support, making it easier for visitors to find information and get assistance. Dhibot is built to be a comprehensive tool for businesses looking to leverage AI for better customer service and more dynamic website engagement.

Starlight AI provides an intelligent orchestration layer designed to automate administrative tasks within public services. By sitting above existing systems, it streamlines workflows and reduces the burden of admin work on frontline staff. This allows public service workers to dedicate more time and resources to direct human interaction and critical service delivery, rather than being bogged down by paperwork and repetitive tasks. The platform aims to enhance efficiency and improve the overall quality of public service operations by leveraging AI for automation.

Tavern of Azoth is an innovative AI-powered RPG platform designed for creating and playing story-driven campaigns. Users can generate a wide array of unique game elements, including creatures, characters, merchants, and equipment, enhancing the depth and variety of their adventures. The platform supports both solo play and multiplayer sessions with up to three friends, all guided by an intelligent AI Game Master. This setup allows players to explore, interact with the world, and shape the narrative in real-time, offering a dynamic and personalized role-playing experience.

WhisperLiveKit is an open-source, self-hosted speech-to-text solution designed for ultra-low-latency transcription and real-time speaker identification. It leverages state-of-the-art simultaneous speech research, including Simul-Whisper and Streaming (SOTA 2025) with AlignAtt policy, and NLLW (2025) for simultaneous translation to and from 200 languages. Unlike standard Whisper models, WhisperLiveKit intelligently buffers and incrementally processes audio to maintain context and accuracy. It offers various API compatibilities, including OpenAI-compatible REST API and Deepgram-compatible WebSocket, making it a versatile drop-in replacement for existing systems. The tool also supports advanced features like Voxtral Mini for multilingual speech processing and Sortformer for real-time speaker diarization.

CleanSweep is an AI agent designed to optimize cloud spending by identifying and terminating unused cloud resources across AWS and Azure. This desktop application automatically detects orphaned snapshots, unused IP addresses, and idle instances, helping users reduce their cloud bills by up to 30%. The tool operates with a strong emphasis on safety, initially running in a "Read-Only" mode where it identifies potential deletions without executing them. Users must approve every termination, ensuring control and preventing accidental data loss. Key features include a "Zombie Resource Killer" for EC2 instances and Load Balancers with zero traffic, and a "Snapshot Cleanup" function for old AWS EBS snapshots no longer attached to active volumes. CleanSweep also boasts zero-data retention and read-only access for enhanced security.

Explainable-Vision-Language-Model is a tool hosted on Hugging Face that generates videos to illustrate the attention mechanisms of multimodal models. It allows users to upload an image and provide a text prompt. The tool then processes this input to create a video that visually demonstrates which parts of the image the model focuses on as it generates the corresponding text. This capability is particularly useful for researchers, developers, and data scientists who need to understand, debug, and improve the interpretability of their vision-language models. By providing a clear visual explanation of model behavior, it helps in identifying biases, understanding decision-making processes, and enhancing model performance.

Haystack Game of Thrones QA is an AI-powered question-answering tool specifically designed for the Game of Thrones universe. Users can input questions about the popular book and television series and receive detailed answers. The tool leverages a knowledge base derived from Game of Thrones documents to provide responses, complete with context and relevance scores, ensuring accurate and informative output. This makes it a valuable resource for fans, researchers, or anyone seeking specific information about characters, events, or lore within the Game of Thrones world.

dataMatters GmbH specializes in developing KIoT (AI-powered IoT) and Smart City solutions aimed at fostering sustainable urban development. Their platform facilitates the creation and deployment of AI models and applications, managing the entire process from sensor data acquisition to user-facing applications. The company focuses on real-world economic applications, leveraging technologies like LoRaWAN for efficient data transmission. By integrating AI with IoT, dataMatters GmbH helps cities and organizations implement intelligent systems that contribute to a more sustainable future, addressing challenges in urban environments through innovative technology.

RediMinds, Inc. specializes in providing bespoke AI solutions and digital engineering services, empowering industry leaders to transform challenges into opportunities. The company focuses on strategic AI enablement, pioneering partnerships, and operational AI innovations to help businesses achieve transformative innovation with the power of AI and evolving technology. RediMinds aims to take away the guesswork in reaching digital goals faster, offering services like AI-driven industry transformations and IAM solutions. They also provide access to in-depth studies and next-gen AI news, supported by their work with the National Science Foundation and multiple peer-reviewed scientific journals.

Huihui Ai DeepSeek R1 Distill Qwen 32B Abliterated is a Hugging Face Space that allows users to interact with and test a specific large language model. By entering text or a prompt, users can receive detailed and informative responses or continuations, making it a versatile tool for various applications. It's particularly useful for tasks such as creative writing, conducting research by generating summaries or explanations, and brainstorming new ideas. The platform is designed to be accessible, providing a direct interface to explore the capabilities of the DeepSeek R1 Distill Qwen 32B model. This tool offers a practical way to experience advanced AI language generation without needing complex setups.

Huihui Ai Mistral Small 24B Instruct 2501 Abliterated is a Hugging Face Space that provides an interface to interact with the Mistral-Small-24B-Instruct-2501-abliterated language model. Users can generate text by inputting prompts, making it a valuable tool for exploring the capabilities of this specific AI model. The application is hosted on Hugging Face, requiring users to sign in with their Hugging Face account to access its functionalities. This platform is ideal for developers, researchers, and AI enthusiasts who wish to experiment with and evaluate advanced language models without needing to set up complex environments.

Llama 3.2 Vision Free is an AI chatbot hosted on Hugging Face Spaces, providing users with access to a vision-enabled language model. This tool allows for interaction with an advanced AI that can process and understand visual information alongside text. While the specific functionalities are not detailed, such models are typically used for tasks like image description, visual question answering, and multimodal content generation. The platform is offered for free, making it accessible for various applications, including educational exploration and research into AI capabilities.

Length generalization via BLOOM is a free-to-use AI tool hosted on Hugging Face, designed to showcase the capabilities of the BLOOM language model. Users can interact with the model by entering logical problems or queries, along with text examples, to receive generated solutions. This platform serves as an interactive scratchpad for exploring how BLOOM processes and responds to various inputs, making it suitable for content generation, task automation, and educational purposes. It offers a straightforward interface for experimenting with large language models without requiring complex setup or technical expertise.

LLaVA-NeXT-Interleave-Demo is an AI chatbot demo hosted on Hugging Face Spaces, developed by lmms-lab. It provides a platform for users to engage with the LLaVA-NeXT model, which is a multimodal AI capable of understanding and generating responses based on various forms of input. The tool is primarily intended for research and experimentation within the field of multimodal AI, offering a hands-on experience with advanced conversational AI technology. While the current live website indicates a runtime error, suggesting it may not be fully operational at this moment, its purpose is to showcase the capabilities of the LLaVA-NeXT model.

Llama3.1 Instruct O1 is an AI chatbot available as a Hugging Face Space, developed by sambanovasystems. It enables users to interact with Llama 3.1 models by entering questions in a chat box. A key feature is the ability to select different Llama 3.1 models and configure the number of reasoning steps the AI can utilize, allowing for detailed observation of the AI's thought process. The tool also supports optional API key integration. This platform is particularly useful for developers and researchers interested in testing and understanding instruction-following language models, offering a transparent view of the AI's reasoning.

Voicepanel is an AI-powered platform designed to revolutionize product feedback and market research. It enables users to collect nuanced feedback over voice or video, moving beyond traditional surveys. The tool leverages AI to conduct hundreds of feedback sessions, automatically translating questions and responses in over 35 languages, and adaptively probing on specific topics. Voicepanel offers rapid recruitment from a built-in panel of 30M+ consumers and professionals, or allows users to bring their own. It provides interactive analysis with real-time reports, quantitative thematic analysis, highlight reels, and a 'chat with your data' feature for instant, evidence-backed answers. This allows teams to launch products with confidence, backed by quantified reactions and actionable recommendations.

LORA-Low-rank-Adaptation is a Hugging Face Space dedicated to the exploration and implementation of Low-Rank Adaptation (LoRA) techniques within AI models. This tool serves as a platform for developers and machine learning engineers to experiment with and understand how LoRA can be applied to optimize and fine-tune large language models and other AI architectures. While the live content indicates a configuration error and a missing Gradio version, the underlying purpose is to facilitate work with low-rank adaptation. It is hosted on Hugging Face, a popular platform for sharing and collaborating on machine learning projects, making it accessible to a broad technical audience interested in advanced AI model optimization.