AI Agents & Automation

PEAQOCK is a dynamic company specializing in innovative solutions across Data Science, Artificial Intelligence, and Machine Learning. The company provides a range of tailored solutions specifically designed for the banking, insurance, and retail industries. With a focus on leveraging advanced AI and ML technologies, PEAQOCK aims to help businesses in these sectors streamline their operations, enhance decision-making, and drive growth. Their offerings are built to address complex data challenges and deliver actionable insights, making them a valuable partner for organizations looking to harness the power of their data.

Shivacha Technologies is a digital solutions agency specializing in scalable AI and Web3 product development. They offer end-to-end services, from product strategy to deployment, across AI, fintech, and blockchain ecosystems. Their expertise includes custom blockchain solutions like exchanges, tokenization platforms, DeFi systems, smart contracts, and AI product development for automation, machine learning, and predictive analytics. Shivacha also provides ready-to-launch digital products such as crypto exchange platforms, neobanking solutions, and AI SaaS platforms. They serve a global clientele, focusing on delivering high-performance, secure, and compliant solutions for startups to enterprises.

Skim AI Technologies offers comprehensive machine learning and artificial intelligence solutions, catering to businesses from entrepreneurs to large enterprises. They specialize in AI advisory, investor due diligence, and AI as a Service, providing custom ML/AI/Agentic AI solutions. The platform helps businesses understand their data, identify opportunities, and scale operations by applying AI across various industries like Media, Medical, Content Creation, Crypto & Blockchain, Legal, EdTech, and Food & Beverage. Skim AI assists with problem definition, design, build, deployment, optimization, and maintenance of ML models on cloud platforms, and offers optional training for in-house management. They also provide customizable APIs and out-of-the-box tools for quick operationalization.

Super Protocol offers a confidential computing platform designed for AI agents and applications, ensuring data privacy and verifiable execution. It allows users to run multi-party inference and fine-tuning across various infrastructures without exposing sensitive data or models. The platform utilizes hardware-sealed execution environments (TEEs) where workloads run inside protected memory, making data invisible to providers or even Super Protocol itself. Key features include cryptographic proofs for verifying code and configuration before data processing, joint computation without exposing raw inputs, and a vendor-agnostic approach using standard Kubernetes and containers. It addresses challenges like trust, control, scale, and access in AI operations, providing a robust solution for sensitive AI workloads.

Víkonnekt is a market-leading expert in AI implementation and software development, offering services to integrate AI products into company workflows. They partner with industry leaders in finance, legal, and the public sector to deploy value-driven AI solutions, leveraging expertise in Machine Learning and Generative AI. Víkonnekt focuses on creating intelligent full-stack applications that enhance interaction and collaboration, from design to deployment. They also provide startup services, including free consulting to define MVP requirements and craft technical specifications for grant applications. Their approach emphasizes sustainable AI, considering environmental, social, and economic factors.

WizeWerks is a boutique consulting firm dedicated to helping businesses leverage AI and LLM technologies for transformation. They focus on delivering customized solutions, moving beyond one-size-fits-all approaches to address the unique challenges of each client. WizeWerks emphasizes continuous innovation in methodologies and technologies, particularly in the fast-evolving fields of AI and digital transformation. The firm utilizes in-house built AI tools to streamline delivery and ensure consistency, offering services that range from generative AI architecture and impact assessment to custom technology development and ethical AI integration. Their operational model relies on highly experienced consultants providing hands-on expertise, ensuring measurable outcomes and long-term success for clients, especially within the insurance industry.

Browserless provides a robust platform for browser automation and web scraping, designed to bypass bot detection and CAPTCHAs. It features BrowserQL, a specialized language for stealthy automation and structured data extraction, alongside Browsers as a Service (BaaS) for running existing Puppeteer or Playwright scripts remotely. The platform offers REST APIs for common tasks like generating PDFs, screenshots, and smart scraping. Key capabilities include session persistence, auto-solving CAPTCHAs, and the ability to click hidden elements. Browserless ensures scalability with managed browser pools, handling load balancing and memory leaks, making it ideal for developers and businesses needing reliable, large-scale web interactions.

pgvecto.rs is a Postgres extension designed for scalable, low-latency, and hybrid-enabled vector search directly within PostgreSQL databases. Built with Rust and based on pgrx, it allows users to integrate vector similarity search functions without revolutionizing their existing database infrastructure. Key features include support for up to 65535 vector dimensions, dynamic SIMD instruction dispatching for optimized performance, and additional data types like binary vectors, FP16, and INT8. It offers filtering capabilities with its VBASE method for combined vector search and relational queries, and provides Write-Ahead Logging (WAL) support for data. The tool supports squared Euclidean distance, negative dot product, and cosine distance operators for vector comparisons, making it a robust solution for integrating advanced vector search into PostgreSQL.

rag-stack is an open-source solution designed to deploy a private ChatGPT alternative securely within your Virtual Private Cloud (VPC). It functions as a corporate oracle by connecting to your organization's knowledge base, enabling Retrieval Augmented Generation (RAG). This technique augments LLM capabilities by retrieving information from external systems, providing context beyond their training data. rag-stack supports open-source LLMs such as Llama 2, Falcon, and GPT4All, offering a more reliable, faster, and cost-effective alternative to fine-tuning models. It includes a server and UI for PDF upload, allowing users to chat over their documents using Qdrant as a vector database. Deployment options are available for Google Cloud, AWS, and Azure.

RAGLite is a comprehensive Python toolkit designed for Retrieval-Augmented Generation (RAG), offering flexible integration with DuckDB or PostgreSQL databases. It allows users to choose any LLM provider via LiteLLM, including local llama-cpp-python models, and supports various rerankers like FlashRank. The toolkit emphasizes lightweight, permissive open-source dependencies and includes features like PDF to Markdown conversion, multi-vector chunk embedding, and optimal semantic chunking. RAGLite also provides adaptive and programmable RAG pipelines, self-query capabilities, and optional integrations for a ChatGPT-like frontend, Pandoc for document conversion, Mistral OCR for high-quality document processing, and Ragas for evaluation.

Qwen-Agent is a comprehensive framework designed for developing advanced LLM applications, built upon the capabilities of Qwen models (version 3.0 and above). It offers robust features such as function calling, multi-character planning (MCP), a secure code interpreter, and Retrieval Augmented Generation (RAG). The framework also includes practical applications like a Browser Assistant and a Chrome extension, enhancing its utility for various development needs. Developers can leverage its atomic components, including LLMs with function calling and customizable tools, to create sophisticated agents. Qwen-Agent supports both DashScope model services and self-deployed OpenAI-compatible API services, providing flexibility in model integration. It also offers a convenient Gradio-based GUI for rapid deployment and interaction with agents.

SENEX Intelligent Chain is an innovative platform that merges Artificial Intelligence with Blockchain technology, creating what they term an "Intelligent Chain." This approach prioritizes data privacy and security by distributing data processing across a decentralized network, ensuring that only the data owner can access their complete information. The platform aims to provide secure and authentic environments, empowering users with AI that operates safely over Blockchain. SENEX offers AI-powered solutions designed to tackle complex problems across diverse industries, from healthcare to finance, by delivering faster, more accurate, and efficient systems. It also features customized tokens to expand user capabilities and is built on the principle of anonymity, protecting user data and process information without requiring user effort.

python-genai is Google's official Python SDK for integrating generative AI models into applications. It provides developers with the tools to leverage Google's powerful Gemini Developer API and Vertex AI APIs directly within their Python projects. This SDK simplifies the process of incorporating advanced AI capabilities, such as code generation, into various applications. It is designed to help developers build intelligent features and automate tasks by providing a robust and easy-to-use interface to Google's generative AI services, making it a valuable resource for enhancing Python-based solutions with cutting-edge AI.

AgentForge is an LLM-native workflow orchestration platform designed to simplify automation by using intelligent AI agents that understand natural language. Instead of building complex workflows, users can describe their desired processes in plain English, and AgentForge will forge the AI workforce to execute them. The platform aims to replace traditional, complex automation tools with a more intuitive, AI-driven approach. Examples of its capabilities include processing invoices from Gmail to QuickBooks, converting Slack messages to Jira tickets, and syncing Stripe customers to a CRM with a welcome flow, demonstrating its versatility across various business operations.

rag-demystified is an open-source project that provides an LLM-powered advanced Retrieval-Augmented Generation (RAG) pipeline built from scratch. It aims to demystify the inner workings of advanced RAG pipelines, which are often obscured by frameworks like LlamaIndex and Haystack. The project breaks down complex RAG processes, such as the Sub-question Query Engine, into their core components, illustrating how each step is powered by a single LLM call with carefully crafted prompt templates. It highlights the challenges associated with advanced RAG pipelines, including question sensitivity and cost dynamics, offering insights into potential failure cases and the impact of prompt engineering. This tool is ideal for developers and researchers looking to understand and build robust RAG systems.

FastbuildAI is an open-source AI framework designed to accelerate and customize the development of AI applications. It provides a comprehensive set of tools and resources, enabling developers to build AI solutions efficiently. The framework emphasizes rapid prototyping and offers flexibility for tailoring applications to specific needs. By leveraging FastbuildAI, users can streamline their AI development workflows, reduce time-to-market, and create scalable and robust AI-powered systems. Its open-source nature fosters community collaboration and continuous improvement, making it a valuable asset for both individual developers and teams working on complex AI projects.

Prompt Manager Pro offers a comprehensive solution for individuals and teams struggling with disorganized AI prompts. It introduces a 4-layer prompt library architecture, including a structured folder system, tagging, version control, and metadata schema, to ensure instant retrieval and continuous improvement of prompts. The tool also features template-based prompt scaling, allowing users to transform one-off prompts into reusable templates with variable slots, generating numerous high-quality variations efficiently. For teams, it supports collaboration with shared prompt libraries, role-based permissions, approval workflows, and usage analytics, ensuring a streamlined and controlled environment for prompt management.

Aicody is an Artificial Intelligence and Robotics Engineering company dedicated to delivering advanced AI products and services to businesses. They specialize in integrating Artificial Intelligence innovation with practical, real-world solutions. The company focuses on cutting-edge research and technology, providing businesses with sophisticated tools and services. While the live content is brief, the meta descriptions highlight their commitment to AI and robotics engineering, offering advanced products and services. Their work involves exploring and developing new AI frameworks and distributed training infrastructure to meet complex business needs.

artea.com srl offers consulting services and innovative technological solutions to help businesses leverage Artificial Intelligence, algorithms, and Big Data Engineering. The company specializes in creating robust architectures for integrating enterprise applications and data, forming the foundation for high-quality data warehouses and data lakes that enable AI. They provide strategic and technological consulting covering the entire data lifecycle, working with both proprietary platforms and market technologies. Additionally, artea.com develops proprietary solutions tailored to client needs, focusing on quick-win projects and rapid experimentation. Their expertise spans advanced technological platforms, including open source and market-leading solutions for Big Data and AI management.

Credal offers a comprehensive control plane for enterprise AI agents, enabling organizations to build, govern, and deploy AI agents and Model Context Protocol (MCP) servers from a single platform. It features an agent registry that eliminates agent sprawl with built-in governance, ensuring all agents operate within defined enterprise controls and data policies. The platform supports various deployment options including cloud-hosted, single-tenant cloud, and on-premises, catering to diverse data residency and security requirements. Credal integrates with numerous enterprise systems like Salesforce, Jira, Slack, and Google Drive, inheriting user permissions to ensure agents only access authorized data. It provides robust security features such as SOC 2 Type II compliance, HIPAA-ready configurations, full audit logging, and proactive risk detection, making it ideal for regulated industries.

Vertex AI Creative Studio is a web application showcasing Google Cloud's generative media APIs, including Veo, Lyria, Chirp, Gemini 2.5 Flash Image Generation (nano-banana), and Gemini TTS. It offers custom workflows and techniques for creative exploration and inspiration, featuring capabilities like image generation (Gemini 3.1 Flash, Imagen 3, Imagen 4, Virtual Try-On), video generation (Veo 3.1, Veo 3, Veo 2), music creation (Lyria), and speech synthesis (Chirp 3 HD, Gemini Text to Speech). The platform also includes advanced workflows such as Character Consistency, Shop the Look, Starter Pack Moodboard, and Interior Designer, alongside an asset library. It's built using Mesop, an open-source Python framework for rapid AI app development, and is intended for demonstration purposes.

Isaacus is a legal AI research company dedicated to setting the standard for effective, efficient, and scalable foundational legal AI. Their flagship products, Kanon 2 Reranker and Kanon 2 Embedder, are recognized as the most accurate legal information retrieval models globally, ranking first on Legal RAG Bench and the Massive Legal Embedding Benchmark (MLEB). Additionally, the Kanon 2 Enricher model is a pioneering hierarchical graphitization tool that converts unstructured documents into rich, structured knowledge graphs with sub-second latency. Isaacus is also behind semchunk, a widely used semantic chunking algorithm. The company focuses on solving real-world problems faced by legal tech professionals, offering solutions for complex legal queries and document enrichment, with a forthcoming Blackstone Graph service for accessing legal documents.

Genius Voice specializes in developing intelligent AI agents designed to transform business operations. Their core focus is on conversational AI, enabling businesses to automate repetitive tasks and enhance efficiency. From strategic planning to full implementation, Genius Voice builds advanced AI solutions tailored to specific business needs. They advocate for open-source software, believing in collaborative innovation where everyone can benefit from shared advancements. This approach allows them to deliver cutting-edge AI solutions that streamline workflows and drive significant business transformation.

Rerender_A_Video is an official PyTorch implementation for zero-shot text-guided video-to-video translation, presented at SIGGRAPH Asia 2023. This framework adapts large text-to-image diffusion models to the video domain, addressing the challenge of maintaining temporal consistency across frames. It operates in two main parts: key frame translation, which uses an adapted diffusion model with hierarchical cross-frame constraints for coherence, and full video translation, which propagates these key frames using temporal-aware patch matching and frame blending. The tool is highly flexible, compatible with existing image diffusion techniques like ControlNet and LoRA for customized translations, and requires no training or fine-tuning. It supports both WebUI and command-line inference, offering advanced options for resolution, ControlNet integration, SDEdit, and various Stable Diffusion models.