AI Agents & Automation

Assert AI is a global leader in computer vision, offering AI-powered image and video analytics solutions to revolutionize industries. The platform transforms existing cameras into powerful data-gathering tools, providing real-time insights to boost productivity, ensure product quality, and enhance workplace safety. Assert AI's solutions are designed for simple setup and quick results, integrating seamlessly with existing security camera networks. With operations in India, the US, and the Middle East, Assert AI helps businesses identify and resolve root causes of compromised safety, quality, and and productivity through real-time AI insights. Their offerings include solutions for occupational health & safety, product quality monitoring, guest experience, and productivity & throughput improvement.

Anemll (pronounced like "animal") is an open-source project designed to accelerate the porting of Large Language Models (LLMs) to tensor processors, with a primary focus on the Apple Neural Engine (ANE). It offers a comprehensive, open-source pipeline for model conversion and inference, enabling seamless integration and on-device inference for low-power applications on edge devices. This is crucial for autonomous applications requiring privacy and security without an internet connection. Key components include LLM conversion tools, an ANE Profiler, a Swift reference implementation, Python sample code, and iOS/macOS sample applications. The library supports various LLM architectures like Gemma 3, LLaMA, Qwen, and DeepSeek, providing pre-converted models and extensive testing infrastructure.

Amazon Bedrock AgentCore Samples provides a comprehensive collection of examples and tutorials to help developers understand, implement, and integrate Amazon Bedrock AgentCore capabilities into their applications. This tool is designed to accelerate AI agents into production by offering the scale, reliability, and security critical for real-world deployment. It is both framework-agnostic (supporting Strands Agents, CrewAI, LangGraph, LlamaIndex, etc.) and model-agnostic, allowing users to bring their preferred Large Language Models. Key features include a secure, serverless runtime for deploying agents, a gateway to convert APIs and Lambda functions into MCP-compatible tools, managed memory infrastructure, and built-in tools like Code Interpreter and Browser Tool. The repository also offers resources for deployment automation, observability, evaluation, and fine-grained access control with Cedar policies.

ai-sdk-tools offers a comprehensive suite of utilities designed to streamline the development of production-ready AI applications using the Vercel AI SDK. Key functionalities include robust state management to eliminate prop drilling and enhance performance in chat components, and powerful debugging tools for inspecting tool calls, messages, and execution flows directly within your application. It also supports structured, type-safe artifact streaming from AI tools to React components, enabling the creation of interactive dashboards and analytics. The toolkit features multi-agent orchestration with automatic handoffs and routing, universal caching for expensive operations, and a persistent memory system for AI agents with multiple storage backend options.

Ascend.io is an agentic data engineering platform designed to build, manage, and optimize data pipelines with the assistance of AI agents. It helps data engineers and leaders ship data products faster by combining a metadata foundation, event-driven automation, and AI agents. The platform enables users to build pipelines 10x faster, automate orchestration with rich metadata and event-driven triggers, and observe with confidence through real-time insights. Key features include AI agents like Otto for code generation and troubleshooting, unified metadata collection, and a DataAware Automation Engine that optimizes compute and reduces costs by eliminating unnecessary reprocessing. It supports both SQL and Python in a single workspace with version control and offers robust governance features.

Ratnafy Agency is a 360° digital solutions agency based in Tunisia, providing a comprehensive suite of services to drive innovation and growth for businesses. Their offerings include AI-powered marketing strategies, web and mobile development, and branding services. They specialize in the integration and implementation of AI-APIs into web and mobile applications, alongside designing, developing, and maintaining final applications. Ratnafy also provides traditional marketing services such as creating strategies and executing campaigns, as well as developing strong brand identities. They aim to help clients bring their ideas to life with tailored marketing plans and solutions, emphasizing expertise, responsibility, creativity, and transparency.

airunner is an all-in-one, offline-first platform designed for local AI inference, functioning as a desktop application, headless server, and Python library. It enables users to run Large Language Models (LLMs), Text-to-Speech (TTS), Speech-to-Text (STT), and image generation models directly on their own hardware. Key features include real-time voice conversations with LLMs, configurable custom AI agents with RAG-enhanced knowledge, and visual workflows built with a drag-and-drop LangGraph builder. For image generation, it supports Stable Diffusion (SD 1.5, SDXL) and FLUX models, complete with drawing tools, LoRA, inpainting, and filters. The platform prioritizes privacy by running locally without external APIs by default, and uses GGUF and quantization for faster inference and lower VRAM usage. It also offers a headless API server for remote access and integration with other applications.

Datagrid AI is an agentic AI platform designed to automate and streamline workflows, particularly within the Built World industry. Unlike generic AI tools, Datagrid's agents reason, plan, and execute across your data and tools, providing data-backed insights grounded in project files. It interprets various formats including text, drawings, spreadsheets, and videos, performing calculations and surfacing critical information. Datagrid agents can act directly within your systems to draft RFIs, run compliance checks, fill out forms, and send updates, significantly reducing manual document handling and project delays. The platform emphasizes security, compliance, and data privacy, ensuring user inputs are never used for model training.

Open Agent Builder is an open-source visual workflow builder designed for creating AI agent pipelines, leveraging Firecrawl for web scraping and data extraction. It offers a drag-and-drop interface for designing complex agent workflows, which can then be executed with real-time streaming updates. The platform is ideal for tasks such as multi-step AI agent pipelines, automated research, content generation, data transformation, and web automation with human-in-the-loop approvals. Key features include 8 core node types, a template library, and support for the MCP protocol for extensible tool integration. It also incorporates a LangGraph execution engine for reliable state management and Clerk authentication for secure multi-user access.

Recipio is an AI-powered recipe organizer and cooking companion designed to help home cooks stop losing recipes and start cooking more efficiently. It allows users to save recipes from various online sources, including websites, blogs, and even images, with AI automatically extracting ingredients, instructions, and tagging them by cuisine. The platform centralizes all recipes, making them easy to find and manage. Key features include smart extraction, voice dictation for hands-free entry while cooking, and the ability to export ingredients to a shared shopping list. Recipio aims to simplify kitchen life for thousands of home cooks by providing a comprehensive solution for recipe management and meal planning.

npcpy is a comprehensive Python library designed for research and development in NLP, multimodal LLMs, Agents, ML, and Knowledge Graphs. It offers a flexible agent framework that supports both local and cloud providers, enabling users to build sophisticated AI applications. Key capabilities include multi-agent team orchestration, tool calling, and advanced functionalities like image, audio, and video generation. The library also facilitates knowledge graph integration and fine-tuning of models, making it a versatile solution for developers and researchers working with diverse AI technologies. It provides quick examples for creating personas, direct LLM calls, agent with tools, streaming, JSON output, and Pydantic structured output.

Raycaster is an AI-native workspace specifically designed for the biopharmaceutical industry, aiming to accelerate drug development by streamlining document management. It ensures that protocols, reports, Module 2/3, and quality documents remain consistent and synchronized with the underlying scientific data. The platform offers features like regulatory research across various documents, AI-powered drafting of protocols and reports, and impact analysis to trace changes across the entire dossier. Raycaster helps teams spend less time on document reconciliation and more on scientific interpretation, ultimately leading to stronger submissions with significantly reduced rework for clinical, CMC, regulatory, quality, and nonclinical teams.

MindPeer is a specialized intelligence tool designed for research analysts to produce actionable, decision-ready intelligence. It streamlines the research process by incorporating context elicitation, source evaluation, and expert oversight. The platform features an 'Intellibot' for structured interviews to define research questions, a curated source directory with reliability ratings, and uses Retrieval Augmented Generation (RAG) to extract answers from documents with sentence-level references. MindPeer delivers confidence-rated findings and explicit gap registers, ensuring leaders understand what is known, how confidently, and what remains unknown. It supports various high-stakes domains including national security, competitive intelligence, business development, and governance, risk & compliance.

Agency Swarm is an open-source framework designed for building multi-agent applications, leveraging and extending the OpenAI Agents SDK. It offers specialized features for creating, orchestrating, and managing collaborative swarms of AI agents, simplifying the creation of AI agencies by thinking about automation in terms of real-world organizational structures. Key features include customizable agent roles with tailored instructions and tools, full control over prompts, type-safe tools using Pydantic models, and orchestrated agent communication via a dedicated `send_message` tool. The framework also supports flexible state persistence for conversation history and is built for reliability and easy deployment in real-world environments.

PySpur is a visual development environment designed for AI engineers to rapidly build, iterate, and deploy AI agents. It addresses common challenges in agent development such as prompt tweaking, workflow visibility, and debugging raw outputs. Key features include human-in-the-loop capabilities for persistent workflows requiring approval, iterative tool calling with memory via Loops, and file upload for processing various document types. PySpur also supports structured outputs with a UI editor for JSON Schemas, RAG functionalities for parsing, chunking, embedding, and upserting data into vector databases, and multimodal support for video, images, audio, and text. It integrates with various tools like Slack and GitHub, offers automatic execution traces, and allows for one-click deployment as an API. The platform is Python-based and supports over 100 LLM providers, embedders, and vector DBs.

Agently is an open-source GenAI application development framework designed to build production-grade AI applications. It offers stable outputs through contract-first schema enforcement and automatic retries, testable orchestration with TriggerFlow, and observable actions via comprehensive logging of tool and sandbox calls. The framework supports structured streaming for instant event processing and provides a flexible Action Runtime for functions, MCP servers, and sandboxes. Agently's TriggerFlow enables serious workflow orchestration with concurrency, event-driven branching, human-in-the-loop interrupts, and execution persistence. It also includes robust session management for multi-turn memory and project-scale configuration management with hierarchical settings.

Polyrific provides AI solutions designed for insurance and other regulated industries, focusing on transforming underwriting, claims, and policy operations. Their platform, Polyrific Catalyst, offers persistent memory, agent orchestration, and governance infrastructure, ensuring enterprise AI is deployable and compliant. Key applications include SubmissionAdvisor™ for AI-powered submission pre-review, PolicyAdvisor™ for intelligent policy analysis, and QualityAdvisor™ for automating quality assurance in life insurance interviews. Polyrific emphasizes rapid deployment, with solutions going into production in weeks, not months, and offers full audit trails and explainable AI decisions crucial for regulated environments. The platform is model-agnostic and built with compliance as a foundational element.

Promptomatix is an AI-driven framework designed to automate and optimize large language model (LLM) prompts. It offers a structured approach to prompt optimization, aiming for consistency, cost-effectiveness, and high-quality outputs while reducing the manual trial-and-error typically associated with prompt engineering. The framework leverages DSPy and advanced optimization techniques to iteratively refine prompts based on task requirements, synthetic data, and user feedback. It features zero-configuration intelligence, automated dataset generation, task-specific optimization, real-time human feedback integration, and comprehensive session management. Promptomatix supports multiple LLM providers like OpenAI, Anthropic, and Cohere, and offers both CLI and API interfaces for flexible usage.

autoMate is an AI-driven local automation assistant designed to empower users to control their computers using natural language. It acts as a computer use agent, similar to Manus or Omniparser, allowing for local automation and integration with popular AI clients like OpenClaw, Claude Desktop, Cursor, and Cline. The tool provides a personal data warehouse for notes, files, reminders, and cross-session memory, addressing the common AI vendor limitation of not remembering information across different platforms. Users can leverage autoMate as a tool source within their preferred AI client or use its built-in web chat for standalone queries. It offers a wide range of functionalities including search, file management, scheduling reminders, and executing real-world tools, making it a versatile solution for enhancing productivity and automating tasks.

Integrately is an AI Agents & Automation tool designed to simplify app integration and workflow automation. With over 20 million ready-to-use automations for more than 1500 applications, it enables users to connect their favorite tools in just one click, eliminating the need for technical expertise. The platform boasts a user-friendly interface where users simply select an automation and activate it. Integrately is positioned as a more affordable alternative to other automation platforms, offering significant cost savings. It supports a wide range of apps across CRM, marketing, forms, and other categories, and even provides a service where their team can create custom automations at no extra cost. Key features include SmartConnect for automatic app connections, branching logic, webhooks, and multi-step automations.

Ritual is building the foundational infrastructure for autonomous intelligence, focusing on native compute, privacy, verification, coordination, and markets for long-lived AI agents. The platform addresses the challenges of AI persistence, coordination, and survival in dynamic environments, moving beyond single-call models to systems that plan, negotiate, transact, and coordinate over time. Ritual aims to empower AI agents to outlive their operators, manage their own finances, and maintain confidentiality under adversarial conditions. This infrastructure facilitates the emergence of new asset classes, non-human market participants, and composable institutions, driven by advancements in AI, mechanism design, systems, and cryptography.

Dentina.Ai is an intelligent AI dental receptionist designed to revolutionize dental practices by providing 24/7 scheduling and patient communication. It integrates directly with existing Practice Management Systems (PMS) to ensure seamless operations and prevent missed calls and lost revenue. The platform leverages AI to handle appointment scheduling, manage patient inquiries, and facilitate communication, aiming to boost efficiency and profitability for dental offices. Dentina.Ai offers a 30-day free trial, allowing practices to experience its benefits firsthand before committing. It is ideal for dental practices looking to automate their front office tasks and enhance patient engagement around the clock.

adk-js is an open-source, code-first TypeScript toolkit designed for developers to build, evaluate, and deploy sophisticated AI agents with flexibility and control. It allows for defining agent behavior, orchestration, and tool use directly in code, facilitating robust debugging, versioning, and deployment across various environments. Key features include a rich tool ecosystem for integrating pre-built tools, custom functions, and OpenAPI specs, as well as support for modular multi-agent systems. The toolkit is particularly useful for developers seeking fine-grained control and tight integration with Google Cloud services, offering a built-in development UI for testing and debugging agents.

AI Notebook - LM Podcast Maker, also known as PodcastLearn, is a mobile application developed by Inventive Otters SRL that converts PDF documents into narrated podcasts. This tool leverages AI to transform written content into dynamic, conversational audio, featuring two AI-generated hosts. It aims to make learning more accessible and enhance information retention by providing an auditory format for documents. Users can create quick summaries or in-depth discussions from their PDFs. The tool is part of Inventive Otters' suite of innovative mobile applications, focusing on making content more engaging and easier to consume on the go.