AI Agents & Automation

Speech is an open-source Python package designed to facilitate research and development in end-to-end models for automatic speech recognition (ASR). It provides implementations of various ASR architectures, including sequence-to-sequence models with attention mechanisms, Connectionist Temporal Classification (CTC), and the RNN Sequence Transducer. Built on PyTorch, this tool allows researchers and developers to experiment with and build advanced speech-to-text systems. The software is specifically tested for Python 3.6 and does not provide backward compatibility for Python 2.7, ensuring a modern development environment. It includes examples for model configurations and datasets, making it easier to get started with training and evaluating ASR models.

NAX Group offers an enterprise AI software platform designed to streamline the development and deployment of custom AI applications. The platform focuses on leveraging automation to build, deploy, and run these applications efficiently. This approach aims to significantly reduce operational costs, accelerate the time it takes for businesses to realize value from their AI investments, and ultimately create a competitive advantage. By providing a comprehensive solution for managing the AI lifecycle, NAX Group enables organizations to integrate advanced AI capabilities into their operations without extensive manual intervention, fostering innovation and efficiency across various business functions.

Syllotips is an AI solution designed to empower AI agents by leveraging the undocumented knowledge of a company's top employees. It facilitates continuous improvement of AI agent reasoning, planning, and retrieval, specifically for automating customer, field, and sales support. The platform is built for enterprise teams, emphasizing reliability, security, and seamless integration. Key features include a governed memory system that involves business process owners in AI improvement, human-in-the-loop agents that adapt based on user interactions, and integration with existing CRM and ERP systems. Syllotips is Azure-first, offering enterprise-grade security, compliance certifications like SOC 2 Type II, GDPR, ISO 27001, and ISO 9001, and native Azure AD integration. It aims to reduce average handling time, increase conversion rates, and lower operating costs for businesses.

Muks Robotics is India’s leading AI humanoid robotics company, specializing in building autonomous enterprise humanoids. Their 'Spaceo' line of humanoids, including M1, PRO, and PRIME models, are designed to address labor shortages and automate dangerous or repetitive tasks across various industries. The humanoids are powered by Fusion Max, a Vision-Audio-Language-Action AI model with 2 billion optimized parameters, trained on real-world data. Key features include autonomous task execution, advanced navigation, multimodal communication, human-centered modular design, and built-in safety systems, ensuring reliable performance in real-world environments. Muks Robotics aims to enable humanity’s future on Earth and beyond by providing intelligent, adaptable workforce solutions.

Conversica provides AI Agents designed to initiate and manage customer conversations across various channels like email, SMS, and chat. These agents are trained on specific policies, tone, and workflows to ensure brand-safe and accurate communication. The platform helps businesses generate demand by engaging leads from events, ads, and content, and by managing ABM programs and inbound inquiries. It also enhances customer service by instantly answering common questions, updating customer details, and managing billing issues. Conversica's AI Agents are deeply integrated into existing tech stacks, allowing them to take actions like sending assets, scheduling meetings, and triggering workflows, all while scaling to handle 1.5 billion conversations for over 2,000 teams.

Hostcomm offers a comprehensive, integrated contact center platform designed for UK businesses, featuring AI voice agents, cloud contact center software, and remote visual assistance. The platform aims to reduce vendor fatigue by consolidating multiple services into one UK GDPR compliant system, hosted in AWS London. Key offerings include the Persona AI voice agent for inbound and outbound calls in over 30 languages, a multi-channel cloud contact center with predictive dialer, and OnSight Remote Visual Assistance that allows experts to see through a customer's smartphone camera without app downloads. Hostcomm has been trading since 2004, is PCI DSS Level 1 certified, and serves over 500 UK organizations, including BT and HMRC.

Geminus offers the world's first generative engineering platform, designed to automatically integrate data, physics, and computation for the autonomous control of complex cyber-physical systems. This platform aims to ignite a new revolution in industrial productivity and efficiency by pioneering real-time intelligence for complex industrial systems. It provides engineering foundational models tailored for industrial enterprises, accelerating the next industrial revolution by unlocking transformational insights from siloed information. The platform enables fast decisions at the speed of real-time operations, robust and accurate predictions with quantified uncertainty, and scalable model creation, deployment, and retraining. Geminus serves various industries including Oil and Gas, Space, Defense, Semiconductors, Utilities, and Renewable Energy.

Aegra offers an open-source, self-hosted AI agent backend, serving as a direct alternative to LangGraph Platform (now LangSmith Deployments). Built with FastAPI and PostgreSQL, it provides developers with zero vendor lock-in and complete control over their agent infrastructure. Key features include Agent Protocol compliance, a robust worker architecture with Redis job queue for horizontal scaling and crash recovery, human-in-the-loop capabilities, and real-time SSE streaming. It supports persistent state via PostgreSQL checkpoints, configurable authentication (JWT, OAuth, Firebase), unified observability through OpenTelemetry, and semantic storage with pgvector. Aegra is compatible with existing LangGraph SDK code and integrates with tools like Agent Chat UI, LangGraph Studio, and CopilotKit, making it ideal for building and deploying scalable AI agents.

agenticSeek offers a 100% local alternative to cloud-based AI assistants, ensuring complete privacy by running entirely on your hardware. This voice-enabled AI assistant can autonomously browse the web, extract information, fill forms, and write/debug code in multiple languages like Python, C, Go, and Java. It intelligently selects the best agent for a given task and can break down complex projects into manageable steps. Designed for local reasoning models, agenticSeek keeps all data on your device, eliminating cloud dependency and monthly bills. It supports various local LLM providers like Ollama and LM Studio, and can also be configured to use API-based providers if local hardware is insufficient.

Agent-S is an open-source framework designed to enable autonomous interaction with computers through an Agent-Computer Interface. Its mission is to build intelligent GUI agents capable of learning from past experiences and performing complex tasks autonomously. The framework has seen significant advancements, with Agent S3 being the first to surpass human-level performance on OSWorld. It supports various models and providers, including Azure OpenAI, Anthropic, Gemini, Open Router, and vLLM inference, and can be configured with grounding models like UI-TARS-1.5-7B. Agent-S offers a local coding environment for tasks requiring code execution, such as data processing and system automation, providing flexibility for technical users.

Ai-Agent-Skills offers a curated library of agent skills and a comprehensive package for users to build and manage their own. It acts as a universal installer for Agent Skills-compatible agents, allowing users to browse, add, and install skills. The tool organizes skills into 'shelves' like frontend, backend, and workflow, and supports both 'house copies' (local folders) and 'cataloged upstream' skills (metadata-only, installed from source). It provides a command-line interface (CLI) and a text-based user interface (TUI) for managing libraries, including features for adding, cataloging, vendoring, syncing, and building documentation for skills. Users can also create and share managed team libraries over GitHub.

NeuBird AI is an AI SRE agent designed to provide autonomous incident resolution for SRE, platform, DevOps, and on-call teams. It connects to existing observability, monitoring, and incident management tools like DataDog, Splunk, Prometheus, PagerDuty, and ServiceNow. The platform analyzes telemetry across IT environments, identifies and investigates issues, correlates signals, pinpoints root causes, and suggests actionable remediation in real-time. Unlike traditional automation, NeuBird AI reasons contextually and learns from experience, continuously optimizing production systems and preventing issues before they impact services. It offers flexible pricing, including a pay-as-you-go model and enterprise plans, with a focus on investigation-centric billing.

Payman AI is an agentic AI platform designed for financial institutions to automate banking transactions. It enables the execution of payments, transfers, and account analysis through voice or text interfaces, leveraging a bank's existing infrastructure. The platform ensures full visibility, configurable controls, and complete audit trails for every transaction. Payman AI focuses on understanding customer intent beyond keywords, applying bank-specific rules automatically, and providing a seamless customer experience across various channels like voice, mobile, web, and SMS. It is built with robust safety and security features, including SOC 2 certification, compliance readiness (KYC, BSA, AML), and immutable audit trails, making it suitable for regulated environments. The system integrates quickly with core banking systems like FIS, Fiserv, Jack Henry, and digital platforms such as Narmi and Q2.

Pet Care - Smart AI Assistant is a mobile application designed to leverage artificial intelligence for comprehensive pet wellness management. The tool aims to provide pet owners with personalized plans and actionable insights, ensuring their companions' optimal happiness and health. Users can effectively track various health metrics, schedule important appointments, and receive AI-powered advice on critical aspects such as diet, behavior, and general pet care. This assistant simplifies the complexities of pet ownership by offering tailored guidance and organizational features, making it easier to maintain a pet's well-being.

LetMePark is a mobile application designed to revolutionize urban parking through advanced technology. It offers automated entry and payment in over 400 parking facilities in Spain and more than 1000 across Europe, with automatic public street parking payment coming soon. The app provides proactive suggestions for underground parking and allows voice-activated parking searches via Alexa. LetMePark integrates with connected car systems, enabling drivers to find and access parking directly from their vehicle's dashboard. It aims to reduce the time and frustration associated with finding parking, offering a unified solution for various parking scenarios, including automatic access, reservations, and even suggestions for free outdoor parking zones.

vector-admin is an open-source, self-hostable tool suite designed for comprehensive vector database management. It offers a universal user interface to simplify interactions with various vector databases such as Pinecone, Chroma, Qdrant, and Weaviate. Users can view, update, and delete individual text chunks of embeddings, copy entire documents or namespaces without re-embedding costs, and upload new documents directly. The tool also supports migrating existing vector databases to different types or instances. While no longer actively maintained by Mintplex Labs, it remains functional for most providers and is cloud deployment ready, offering features like multi-user instance support and cost-saving measures for large documents.

RegGenome provides high-quality regulatory data by transforming fragmented, unstructured regulation into machine-readable, machine-consumable source-linked data. This structured data is designed to power the next generation of compliance, GRC, and regulatory systems, enabling earlier signal detection, reliable change tracking, and audit-ready outputs. The platform offers three modular layers: AI-optimised Data for faster compliance tools, a Control & Obligations Library for accelerating control mapping, and a Policy Intelligence Suite for evidence-based benchmarking and framework assessments. RegGenome serves solution providers and regulators, helping them reduce content development overheads, accelerate feature delivery, and align regulatory publishing with digitisation and AI. Founded at the University of Cambridge, its data is built for trust and reviewed with regulators.

TYD XChat is designed to enhance the user experience with ChatGPT Web by providing robust prompt management and editing capabilities. This tool allows users to organize, refine, and iterate on their prompts more effectively, leading to improved interactions and more precise outputs from ChatGPT. It caters to individuals who frequently use ChatGPT for various tasks and need a structured way to handle their prompts. By offering advanced editing features, TYD XChat helps users optimize their queries, ensuring they get the most out of their AI conversations. This makes it an invaluable asset for anyone looking to streamline their workflow and achieve better results with conversational AI.

MetaBrain Labs Inc. offers a platform for developing sensor-integrated AI agents that connect people, systems, and live data to guide intelligent conversations. These agents are designed for real-time data ingestion from various sensors, including wearables, clinical devices, and IoT. The platform provides a blueprint for deploying sensor-aware AI agents, offering hands-on enablement and patent-backed rights to operate. It focuses on adaptive conversational intelligence, context-aware, task-driven dialogue, and flexible, scalable deployment options. Unlike generic language models, MetaBrain Labs' agents are task-oriented systems driven by live data and proprietary logic to solve real-world problems dynamically, ensuring ownership and customization for the user.

LangChain provides a comprehensive engineering platform and open-source frameworks designed for developers to build, test, and deploy reliable AI agents. The platform, LangSmith, offers robust tools for observability, allowing users to trace agent execution and understand complex interactions. It also includes evaluation capabilities to score and improve agent performance using real-world usage data and human feedback. For deployment, LangSmith supports shipping and scaling agents in production with features like memory, conversational threads, and durable checkpointing. Additionally, LangChain offers open-source frameworks like deepagents, langchain, and langgraph for building various types of agents, from quick-start prototypes to reliable production systems with low-level control.

Mantyx is an advanced agent platform designed to orchestrate, manage, and facilitate the sharing and evolution of AI agents within an organization. It provides a centralized environment for developers and enterprises to deploy, monitor, and control their AI agent ecosystem efficiently. Users can give agents their tools, webhooks, and integrations, and delegate tasks using MCP and A2A functionalities, with optional memory. The platform simplifies the complexities associated with multi-agent systems, enabling seamless collaboration among teams working on AI-driven projects. Mantyx offers a consistent workspace from free to production, making it accessible without requiring sales calls, and supports agent lifecycle management from deployment to performance tracking.

Wizerr AI is a hardware intelligence platform designed for electronics companies, offering an AI-native infrastructure that transforms component and supply data into real-time, engineer-grade decisions. It leverages a continuously evolving Component Intelligence Graph built from millions of electronic component datasheets and supply signals. Key features include a BOM Optimizer for streamlining component selection, identifying functional equivalents beyond part numbers, and finding compatible second sources with defensible comparisons. The platform provides real-time commercial insights, including pricing, stock, lead times, and risk information, enabling informed choices for engineering and procurement teams. Wizerr AI also offers a deep matching engine for pin-to-pin, package, and electrical matches, datasheet chat and comparison, and collaboration tools for sharing results and persistent workspaces. It's built for deep component intelligence with a patent-pending ELX engine and domain-tuned AI, providing explainable intelligence with confidence scores.

Factagora is a verifiable knowledge platform designed to combat AI hallucinations by transforming unstructured text into structured, verifiable knowledge. It features DeepVerify for word-by-word fact verification, an API with 6 purpose-built endpoints for fact-checking and research, and an Agent Debate system where AI agents autonomously research, argue, and challenge claims to surface contradictions and missing evidence. The platform also builds Temporal Knowledge Graphs (TKG) to track how facts evolve over time, ensuring accurate data management. Factagora is built for anyone who needs to ensure the accuracy of information, from journalists and legal professionals to AI consultants and enterprise knowledge teams, integrating seamlessly into existing workflows.

Pomodoro Club is a comprehensive productivity tool designed to help users master the Pomodoro Technique and enhance their focus during deep work sessions. It features a customizable Pomodoro timer with smart notifications and streak tracking to maintain motivation. The platform offers curated focus music playlists, including lo-fi beats and ambient soundscapes, scientifically designed to boost concentration. Users can gain insights into their productivity patterns through analytics and weekly email reports. Additionally, it supports dark mode, syncs progress across devices, and offers a WhatsApp integration for task management without needing to download an app. Pomodoro Club is free to use, making it accessible for anyone looking to improve their time management and focus.