AI Agents & Automation

DeepLab is a technology company focused on empowering businesses with deep intelligence through custom machine learning solutions. They offer expertise in designing and developing scalable ML infrastructure, employing cutting-edge technology to productize ideas and facilitate fast experimentation. DeepLab also provides production-grade algorithmic solutions for products serving billions of users, optimizing KPIs and delivering competitive advantages. The company continuously invests in core machine learning and deep learning research, pushing boundaries in areas like Transfer and Continual Learning, as well as applications such as Computer Vision and Language. Their services include building innovative AI-powered solutions for recommender systems, cybersecurity, fraud detection, pricing optimization, and automotive driver behavior modeling.

Pandata offers AI design and development services tailored for high-risk industries such as healthcare, life sciences, financial services, defense, and energy. Their expertise lies in creating robust, fair, and trustworthy AI solutions that address the unique challenges of these sectors, including maintaining safety, ensuring compliance, and minimizing risk. Services include AI Discovery & Design to establish strategic value and use cases, AI Development for building and scaling models, and specialized High Risk Industry AI Solutions. Pandata also provides advisory services and resources like their blog and 'Trusted AI Digest' to help organizations adopt AI responsibly. They have a proven track record, having worked with over 60 clients on more than 100 multi-year projects.

RAGs is a Streamlit application designed to simplify the creation of Retrieval Augmented Generation (RAG) pipelines. Users can describe their task and desired RAG system parameters using natural language, such as specifying data sources like local files or web pages, and defining parameters like top-k retrieval or summarization. The tool provides a configuration view to inspect and modify generated parameters, offering full control over the RAG setup. Once configured, a standard chatbot interface allows users to query the RAG agent over their data. It supports various LLMs and embedding models, including OpenAI, Anthropic, Replicate, and HuggingFace, making it a flexible solution for developers and data scientists looking to implement RAG systems.

RAGxplorer is an open-source tool designed to help users visualize their Retrieval Augmented Generation (RAG) pipelines. It provides a framework for building visual representations of RAG systems, aiding in the understanding, debugging, and optimization of these complex AI architectures. Users can install it as a Python package and leverage its functionalities to load documents, embed them, and visualize query responses within their RAG setup. The tool also offers a Streamlit demo for quick exploration and interaction. RAGxplorer is particularly useful for developers and data scientists working with LLMs and RAG, offering a clear way to see how information is retrieved and augmented.

Dia2 2B is an advanced AI tool developed by Nari Labs, designed for real-time streaming conversational audio. Users can input a back-and-forth script and optionally add short voice prompt files for each speaker to condition the model. By adjusting a few sampling sliders, the tool generates a single audio file that voices the entire conversation. This capability makes it ideal for creating dynamic and natural-sounding dialogues without needing the complete text input upfront, offering a flexible solution for various audio generation needs.

Open Innovation AI delivers advanced infrastructure orchestration and AI tools designed for efficiency, security, and scalability. Its Core AI Platform, OI Cluster Manager, provides enterprise-grade AI infrastructure orchestration with full resource control, supporting GPU-agnostic, multi-cluster, and hybrid multi-cloud deployments. The AI Application Suite includes OI Agents for building and deploying agentic LLM workflows, OI Chat for sovereign and on-prem LLM-powered chat interfaces, and OI Code for secure AI coding assistance. Additionally, OI AI Security offers end-to-end security testing for AI models and RAG applications. The platform emphasizes data sovereignty, security by design, and rapid deployment of AI workloads, making it suitable for public sector, telecommunication, and banking & finance industries.

Gemma Fine Tuning is a web-based application hosted on Hugging Face Spaces, designed to simplify the process of fine-tuning Google's Gemma models. Users can upload and preprocess their own datasets, configure various model parameters, and initiate the training of Gemma models. A key feature is the ability to export the fine-tuned models in multiple formats, making them versatile for different deployment scenarios. This tool provides an accessible interface for individuals and researchers looking to customize large language models for specific tasks or domains without extensive coding knowledge.

self_drive is an open-source project focused on building an AI-powered autonomous driving car using Raspberry Pi and TensorFlow. The project outlines a comprehensive process, starting from hardware assembly and motor control to camera debugging and road data acquisition. Users can manually control the car to collect data on a custom-built track, process this data using Python scripts, and then train a deep learning model. The trained model is then deployed on the Raspberry Pi to enable the car to autonomously navigate the track. The project emphasizes the importance of track design and data quality, and it details the use of the NVIDIA end-to-end Model for neural network architecture. It also mentions ongoing improvements like transfer learning, handling lighting issues, and addressing data class imbalance.

Veritone is a human-centered AI technology leader providing innovative AI solutions across diverse industries such as media and entertainment, legal and compliance, and government. The platform, aiWARE, tokenizes unstructured data like video, audio, and text into AI-ready tokens, powering smarter models and automated workflows. Veritone helps businesses accelerate decision-making, improve efficiency, and unlock extraordinary potential by transforming media into actionable data. Its offerings include solutions for public safety productivity, retail talent acquisition, and custom AI development, enabling organizations to achieve measurable business outcomes and grow revenue.

SceneGraphParser (sng_parser) is a Python toolkit designed to convert natural language sentences into symbolic scene graphs. Inspired by the Stanford Scene Graph Parser, this purely Python-based tool provides an intuitive user interface and a flexible, configurable design. It parses sentences to create graphs where nodes represent nouns (including modifiers like determiners or adjectives) and edges define relations between these nouns. The project is actively developed, with APIs subject to change, and encourages community contributions for identifying failure or corner cases in its rule-based parsing approach. It was developed for the research paper "Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations."

sd-webui-agent-scheduler is an open-source scheduling agent designed to enhance generative AI image workflows. As an extension for Automatic1111/Vladmandic Stable Diffusion Web UI, it allows users to enqueue prompts, settings, and controlnets, managing them through a dedicated AgentScheduler tab. Key features include the ability to reorder, pause, resume, and prioritize tasks, as well as view generation results and history. Users can also edit queued tasks, rename them, and update basic parameters like prompts, samplers, and checkpoints. The extension supports queuing with all available checkpoints or a subset, and offers API access for advanced integration and automation, including callback functionality for task completion.

IIIT Innovation In IT develops tailor-made IT systems to boost the businesses of their partners. They focus on leveraging software to increase the efficiency of business processes, from customer outreach to multi-dimensional analyses. Their expertise spans Big Data, Data Science, R&D, Custom Software, Machine Learning, Deep Learning, Artificial Intelligence, Business Intelligence, Agile Programming, and User Experience Design. They offer pioneering products and solutions that have revolutionized businesses and increased profits for their partners, alongside a backlog of innovative ideas for future start-ups.

GPT4o mini Reply is a browser extension designed to streamline customer service operations by leveraging artificial intelligence to generate quick, polite, and personalized responses. It allows users to create complete and professional replies to customer inquiries in seconds. By simply selecting the text requiring a response, the AI handles the rest, making it ideal for professionals looking to optimize their time and ensure high-quality customer service. Key features include AI-powered response generation, customizable instructions for responses, personalized greetings and signatures, and URL whitelisting for extension activation. This tool helps users efficiently manage customer interactions and improve response times.

sd-webui-lcm is an extension designed to seamlessly integrate the Latent Consistency Model (LCM) into AUTOMATIC1111 Stable Diffusion WebUI. This allows users to leverage LCMs for rapid image and video generation directly within their existing Stable Diffusion setup. The tool currently supports the LCM_Dreamshaper_v7 checkpoint and offers functionalities for both image-to-image (Img2Img) and video-to-video (Vid2Vid) conversions. It's a barebone implementation, welcoming contributions, and provides clear instructions for installation and troubleshooting common issues like `torch.cuda.OutOfMemoryError` or `ImportError` related to `diffusers` versions.

Gradio Demo, developed by Gorilla LLM (UC Berkeley), is a platform designed to demonstrate the power of large language models (LLMs) in interacting with a vast array of APIs. This tool is built on the Gradio framework, making it accessible as a Hugging Face Space. It enables users to explore how LLMs can automate complex tasks by leveraging external APIs, providing a practical example of AI agents in action. The project is open-source under the Apache 2.0 license, promoting community contributions and commercial use. While the live demo currently experiences a runtime error, its core purpose is to illustrate the potential of AI-driven API interaction for developers and researchers.

WithSpark.ai is an AI-powered dating assistant designed to enhance the online dating experience. It offers intelligent tools and suggestions to help users optimize their dating profiles, making them more appealing and effective. The platform also assists in crafting engaging and meaningful conversations, aiming to foster genuine connections rather than superficial interactions. By leveraging artificial intelligence, WithSpark.ai provides personalized guidance, helping users navigate the complexities of modern dating apps and improve their chances of finding compatible partners. The tool focuses on empowering users with the confidence and communication skills needed to succeed in the digital dating landscape.

OptiComm.ai is an advanced AI platform designed to transform business operations by predicting individual customer needs and future orders. It goes beyond traditional demand forecasting by identifying what, when, and how much each customer will order next. The platform integrates deep neural prediction with real-world employee expertise and external signals to deliver intelligent insights. These insights are then translated into actionable steps for sales teams via a Sales Intelligence Platform and AI Voice Agents, enabling businesses to proactively recover lost orders, boost revenue, and act before demand materializes. Key features include next order prediction, a sales intelligence dashboard, AI-powered voice agents, and advanced cross-sell recommendations based on buying patterns and trends.

OptiSol Business Solutions leverages generative AI to empower businesses across various industries, focusing on accelerating innovation, scaling efficiently, and creating future-ready products. Their services encompass building digital products faster with GenAI-driven teams, modernizing legacy applications and infrastructure, and harnessing GenAI and analytics for data unification and insights. OptiSol also specializes in Global Capability Centers (GCCs) in India, offering GenAI engineers and agentic AI capabilities. They provide a suite of GenAI accelerators like elsAi for AI app development, Unicus AI for due diligence and compliance, Scanflow for vision intelligence in quality control, and elsai ESG for simplified ESG data management and reporting. Additionally, they offer modernization tools like iBEAM for converting Oracle Reports to Jasper and migrating Oracle databases to PostgreSQL.

FireRedTTS2 is an AI-powered text-to-speech (TTS) system designed for generating long-form, multi-speaker dialogue. Users can create dynamic conversations by uploading short reference audio and corresponding text for each speaker, or by selecting random voices. The tool then allows for the input of dialogue using speaker tags like [S1] and [S2]. This capability makes FireRedTTS2 suitable for applications requiring stable, natural speech with reliable speaker switching and context-aware prosody, such as podcast creation or chatbot voice generation. It focuses on delivering a seamless experience for multi-speaker audio content.

Skill Seekers is a universal preprocessing layer for AI systems, transforming diverse data sources into structured knowledge assets. It can ingest documentation websites, GitHub repositories, PDFs, videos, Jupyter Notebooks, and 10+ other source types. The tool then analyzes, structures, and enhances this data, generating AI-powered SKILL.md files and exporting them to 16 platform-specific formats, including Claude, Gemini, OpenAI, LangChain, and LlamaIndex. This significantly accelerates data preparation for AI skill builders, RAG pipelines, and AI coding assistants, reducing manual effort from days to minutes. Key features include smart SPA discovery, OCR for scanned PDFs, video extraction with visual frame analysis, deep code analysis, and automatic conflict detection between documented APIs and actual code.

GPT-OSS-120B on AMD MI300X is an AI chatbot hosted on Hugging Face Spaces, designed to run on AMD MI300X GPUs. This tool offers a simple chat interface where users can input questions or requests and receive spoken-language responses from the GPT-OSS-120B model. It provides flexibility by allowing users to adjust the system prompt and temperature, enabling customization of the AI's behavior and output. This makes it suitable for experimentation and research with large language models, offering a platform to explore different conversational AI scenarios and model responses. The tool is open-source, licensed under Apache 2.0, promoting accessibility and collaborative development within the AI community.

Rapid Acceleration Partners offers an AI orchestration and hyperautomation platform designed for enterprises to automate complex processes and AI workflows at scale. The platform enables businesses to deploy smarter, safer, and more transparent AI workflows, handling end-to-end automation even for messy, exception-ridden processes. It can digitize and distill knowledge from various formats like PDFs, emails, Excel, and ERPs, breaking data silos and capturing intelligence. The platform also allows for the orchestration and real-time management of AI agents across different functions, ensuring full data ownership and governance. With features like an AI Governance Dashboard, observability, guardrails, and hallucination prevention, it provides powerful controls and complete visibility for responsible, privacy-first, and scalable AI deployment.

FLUXllama gpt-oss is an AI tool hosted on Hugging Face Spaces, designed for generating high-resolution images from text descriptions. It leverages FLUX 4-bit Quantization for efficient image model processing. Users can provide a short text prompt, and the application will create a corresponding image. For richer and more detailed results, the tool includes an AI that can first improve the user's initial prompt with additional artistic and descriptive elements. This makes it suitable for experimentation with advanced image generation techniques and for users looking to produce visually enhanced outputs from concise inputs.

Silero Models provides a comprehensive suite of pre-trained text-to-speech (TTS) models designed for ease of use and high performance. The models are fully end-to-end, offering natural-sounding speech across a large library of voices. A key differentiator is its one-line usage, making integration and deployment straightforward. It boasts impressive speed on both CPU and GPU, catering to various computational environments. For the Russian language, the models include advanced features like automated stress and homograph resolution. Installation is flexible, allowing use via PyTorch Hub, pip, or manual caching. The platform supports a wide array of languages, particularly focusing on Cyrillic and Indic languages, with ongoing development for new versions and features.