AI Agents & Automation

MInference is a powerful tool designed to significantly speed up the inference process for long-context Large Language Models (LLMs). By employing approximate and dynamic sparse attention calculations, MInference can reduce inference latency by up to 10x during the pre-filling stage on an A100 GPU, all while preserving model accuracy. It supports processing million-token prompts and has been integrated into various LLMs like Qwen2.5 and LLaMA-3.1. The framework also includes MMInference for multi-modality models and SCBench for evaluating long-context methods from a KV cache perspective, offering comprehensive solutions for optimizing LLM performance.

mflux is an open-source tool designed for running state-of-the-art generative image models natively on Apple Silicon Macs using the MLX framework. It offers line-by-line MLX ports of models from Huggingface Diffusers and Transformers libraries, focusing on a minimal and explicit implementation. Users can generate images via a command-line interface or Python API, with features like quantization, local model loading, and LoRA support. The tool supports various models including Z-Image, FLUX.2, FIBO, SeedVR2, Qwen Image, and Depth Pro, each with unique strengths in areas like speed, quality, prompt understanding, and upscaling. It also includes advanced capabilities such as text-to-image, image-to-image, LoRA finetuning, in-context editing, ControlNet, depth conditioning, and inpainting.

Mini CRM Vocal is a voice-powered task management application designed for professionals who need to quickly capture and organize information on the go. It allows users to add tasks simply by speaking, with the AI intelligently detecting and structuring details such as dates, recurrence, and addresses. This tool is particularly useful for sales representatives, freelancers, therapists, artisans, coaches, and entrepreneurs who frequently need to record notes, appointments, and locations without the time to type. Key features include intelligent dictation, automatic recurrence setup, address integration with maps, and a quick-add function for tasks. CRM Vocal aims to save time and prevent information loss by providing a simple, fluid, and efficient way to manage daily activities.

Multimodal-Toolkit is an open-source toolkit designed for integrating multimodal data, specifically text and tabular data, for classification and regression tasks. It leverages HuggingFace transformers as the foundational model for processing text features. The toolkit introduces a combining module that integrates outputs from the transformer with categorical and numerical features, generating rich multimodal features for downstream machine learning layers. This approach allows for the training of the combining module and transformer parameters based on supervised tasks. It supports various Hugging Face Transformers like BERT, ALBERT, DistilBERT, and RoBERTa, and includes methods for combining features such as concatenation, MLPs, and attention mechanisms. The toolkit also provides example datasets and working examples for quick implementation.

Naymt is a comprehensive mobile application designed to assist expectant parents in the challenging yet exciting task of naming their baby. The app provides a vast database of baby names, which users can explore using advanced filters based on style, origin, length, and meaning. A key feature is the "Name Genie," an AI-powered assistant that generates name ideas based on user input, such as favorite names, specific styles, or even feelings. Naymt also learns a user's naming style to offer personalized recommendations and allows users to discover their unique "Style DNA" through a questionnaire. Additionally, it offers curated collections, popularity rankings, and a visual photo tool called Naymr that suggests names matching the vibe of an uploaded image. The app supports collaborative naming with partner sharing and list management features, making the name-finding process easy, beautiful, and fun.

OpenDeepSearch is a lightweight yet powerful search tool designed for seamless integration with AI agents, particularly within the Hugging Face's SmolAgents ecosystem. It offers deep web search and retrieval, performing on par with or better than closed-source alternatives for single-hop and multi-hop queries. The tool features two modes of operation: Default Mode for quick, efficient, and low-latency searches, and Pro Mode for comprehensive web scraping, semantic reranking, and advanced post-processing, ideal for complex and multi-hop queries. OpenDeepSearch is highly configurable, supporting various search providers like Serper.dev and SearXNG, and reranking solutions such as Jina AI or self-hosted Infinity Embeddings. It also integrates efficiently with LiteLLM for diverse AI model support.

Console is an AI-Native ITSM platform designed to significantly reduce the IT support workload by automating the resolution of common requests. It leverages AI Agents to understand an organization's unique processes and policies, enabling it to auto-resolve over 50% of support requests directly within communication platforms like Slack and Microsoft Teams. The platform utilizes 'Playbooks' for step-by-step instructions, 'Access Policies' for self-serve app access, and integrates with existing 'Knowledge Bases' to provide relevant information. Console aims to free up IT teams from repetitive tasks, allowing them to focus on more strategic projects, and boasts rapid deployment, with many teams reaching production in three weeks or less.

pgvectorscale is a PostgreSQL extension designed to significantly boost vector search performance and provide cost-efficient storage for AI applications, building upon the capabilities of pgvector. It introduces key innovations such as StreamingDiskANN, an index type inspired by Microsoft's research, and Statistical Binary Quantization developed by Timescale for improved data compression. The tool also supports label-based filtered vector search, allowing for more precise and efficient results by combining vector similarity with label filtering. Benchmarks show pgvectorscale achieving substantially lower latency and higher query throughput compared to other solutions, all at a reduced cost when self-hosted. Developed in Rust using the PGRX framework, it offers a new avenue for community contributions to PostgreSQL's vector support.

Intelic, formerly Avalor AI, specializes in autonomy software for modern defense applications. Their flagship product, Nexus, is a platform-agnostic Command and Control (C2) system designed to unify diverse unmanned systems (UxVs) across air, land, and sea domains into a single operator interface. Nexus supports advanced features like enhanced visual navigation in GNSS-denied conditions, graceful degradation, and augmented reality POI navigation. It is built to integrate with various drones and ground vehicles using industry-standard protocols and is battle-tested in active conflict zones. Intelic emphasizes a human-in-the-loop philosophy, ensuring human operators maintain final authority over kinetic actions while offloading cognitive burden through high levels of autonomy.

ANTICIPATE offers an AI-based visual quality control system designed to automate and digitalize inspection processes in both manual and machine-based manufacturing. The system integrates intelligent camera systems and screens into existing assembly, packaging, and testing stations, guiding workers with precise instructions and verifying work results directly within the production process. For automated lines, it seamlessly integrates advanced camera systems and sensors into machinery and conveyor belts, enabling automated product quality inspection and comprehensive data collection for production analysis. ANTICIPATE addresses common challenges of manual inspection, such as high error rates, low inspection speed, and lack of documentation, while overcoming limitations of classic image processing systems like complex interfaces, high pseudo-reject rates, and poor scalability. The solution provides consistent, traceable inspection results, creating a reliable data foundation for root-cause analyses and process improvement. It is GDPR-compliant and can be deployed locally to ensure data security.

AI71 is an applied research team that creates AI solutions tailored for enterprises and governments globally. Their offerings include a suite of products such as Ask, which provides superhuman capabilities for tasks like finding answers in documents and automating HR, and SuperHive, an intelligence platform for construction with features like CAD/BIM validation and delay forecasting. They also offer Health, an automated revenue cycle solution for healthcare. Beyond products, AI71 provides QBrain advisory, combining strategic insight with technical expertise to ensure successful AI transformation and measurable impact for their partners.

Aideas offers a private AI platform designed for building custom AI models and agents while prioritizing data security and privacy. Users can create an on-chain identity and a private agent, leveraging their own data or prebuilt models from a marketplace. The platform ensures privacy through end-to-end encrypted relays and computes on encoded data, making requests invisible even to Aideas. Cryptographic receipts provide verifiable evidence of rule adherence without revealing data, with usage settled in $AIDA on the blockchain. Aideas is accessible for individuals, teams, and organizations, simplifying agent creation and allowing deployment locally, in the cloud, or within their secure environment. Agents evolve automatically through self-learning, with all updates auditable on-chain.

Open Deep Research is an open-source AI agent designed to perform deep web research by cloning Open AI's Deep Research experiment. Unlike its inspiration, it utilizes Firecrawl's extract and search capabilities to gather large amounts of web data, which is then processed by a reasoning model for analysis. Key features include real-time data feeding to the AI via search, structured data extraction from multiple websites, and advanced routing with Next.js App Router. It integrates with the AI SDK for generating text and structured objects, supporting various LLM providers like OpenAI, Anthropic, and Cohere. The tool also offers data persistence with Vercel Postgres and secure authentication via NextAuth.js, making it a robust solution for comprehensive web data analysis.

aiko is an AI-native consulting firm established in 2023 to address the challenges of artificial intelligence, combining business model understanding, technological expertise, and a scientific approach. Founded by experienced digital transformation entrepreneurs and an AI researcher, aiko assists companies in integrating AI into their core strategy. Their services include AI Plan for identifying opportunities, AI Build for developing and implementing AI solutions, AI Run for operationalizing and scaling AI tools, and AI Change for training teams on new AI-driven processes. They offer comprehensive support from data architecture audits and roadmap definition to MVP creation, model development, and ongoing maintenance and re-training.

NVIDIA PhysicsNeMo is an open-source deep-learning framework designed for building, training, fine-tuning, and inferring Physics AI models using state-of-the-art SciML methods. It provides Python modules to compose scalable and optimized training and inference pipelines, enabling real-time predictions by combining physics knowledge with data. The framework supports various model architectures like neural operators, GNNs, and transformers, and is optimized for NVIDIA GPUs, offering efficient scaling from single to multi-node GPU clusters. PhysicsNeMo is built on PyTorch, ensuring a familiar experience for users, and is highly extensible for customization and integration into existing workflows. It includes modules for models, data pipelines, distributed computing, data curation, and symbolic geometry/PDEs.

PINA is an open-source Python library designed to streamline and accelerate the development of Scientific Machine Learning (SciML) solutions. Built upon PyTorch, PyTorch Lightning, and PyTorch Geometric, it offers a modular and flexible framework for defining, experimenting with, and solving complex problems using various neural network architectures, including Physics-Informed Neural Networks (PINNs) and Neural Operators. PINA supports multi-device training for scalable performance and provides both high-level abstractions for quick model definition and granular control for expert users to fine-tune training and inference processes. It enables users to solve both data-driven and physics-informed problems efficiently.

Prophecis is a comprehensive, one-stop cloud-native machine learning platform developed by WeBank. It integrates various open-source machine learning frameworks and offers robust multi-tenant management capabilities for machine learning compute clusters. The platform provides full-stack container deployment and management services for production environments, supporting the entire machine learning lifecycle from data preprocessing and feature engineering to model training, evaluation, release, and deployment. Key components include Prophecis Machine Learning Flow for distributed modeling, MLLabis for development and exploration with Jupyter Lab integration, Model Factory for model storage and deployment, Data Factory for feature engineering, and Application Factory for CI/CD and DevOps tools.

Baseten is an AI infrastructure platform designed for deploying and scaling AI models in production environments. It offers a comprehensive inference platform that includes dedicated inference for high-scale workloads, allowing users to serve open-source, custom, and fine-tuned AI models on purpose-built infrastructure. The platform provides pre-optimized Model APIs for testing new workloads and evaluating the latest AI models, alongside the capability to run training jobs on inference-optimized infrastructure. Baseten emphasizes bleeding-edge performance research, cross-cloud high availability, and seamless developer workflows, ensuring fast model runtimes and 99.99% uptime. It supports rapid scaling across any cloud provider, with options for single-tenant, self-hosted, and hybrid deployments, catering to various security and latency requirements.

PPTAgent is an open-source agentic framework designed for reflective PowerPoint generation. It significantly improves presentation creation by focusing on content quality, visual appeal, and structural coherence, going beyond traditional text-to-slides methods. The tool employs a two-stage, edit-based approach inspired by human workflows, analyzing reference presentations to extract slide-level functional types and content schemas. It then drafts an outline and iteratively generates editing actions to create new slides. PPTAgent supports PPTX export and offline mode, and includes context management to prevent overflow. It also integrates with optional services like Tavily for web search and MinerU for PDF parsing to enhance generation quality, and offers text-to-image model configuration for improved image generation.

pixeltable is an open-source Python library designed to provide declarative, transactional data infrastructure for building multimodal AI applications. It offers incremental storage, transformation, indexing, retrieval, and orchestration of data, ensuring full operational integrity. The tool bundles its own transactional database, orchestration engine, and a local dashboard, requiring only a `pip install` for setup without external services like Docker. It supports various media types including images, video, audio, and documents, and integrates with over 30 AI providers like OpenAI, Anthropic, and Gemini. Key features include declarative computed columns for automated processing, built-in vector search for embedding indexes, and robust version control for data persistence and time travel, making it suitable for both prototyping and production AI workflows.

PipesHub is a fully extensible and explainable workplace AI platform designed for enterprise search and workflow automation. It addresses the challenge of scattered work data across various applications like Google Workspace, Microsoft 365, Slack, Jira, and Confluence by providing a natural language search interface. Users can quickly find information, get answers, and gain insights, with results properly cited using Knowledge Graphs and Page Ranking. Beyond search, PipesHub offers a No-Code interface for enterprises to build custom applications and AI agents. It supports flexible model integration, real-time or scheduled indexing, access-driven visibility, and secure deployments both on-premise and in the cloud.

BizzSoftware specializes in accelerating enterprise innovation by providing rapid, quality, secure, and affordable custom software solutions. They eliminate common IT department hurdles by offering end-to-end services including intuitive design, interactive prototyping, robust software engineering across various platforms, secure hosting and continuous monitoring, and proactive support. Their expertise extends to developing AI-powered platforms, as demonstrated by case studies in AI matchmaking for recruiting, AI-based lead generation and email marketing, and AI-driven inventory optimization for retail. BizzSoftware also revolutionized video content delivery for large enterprises and digitized project management processes with AI-powered feedback analysis. They are ISO 27001 certified, ensuring high standards of information security.

BrewVend Middle East specializes in AI-based cocktail and mocktail bartending robots, along with IoT-based food and drink automation robotics solutions. Their flagship product, "Brewmac," offers intelligent bartending, dispensing cocktails and mocktails automatically. They also provide Pudu Robots for services like robo-waiters and kitchen automation. BrewVend offers various solutions including AI automatic bartending, smart service robots, and smart bottle vending. Their services encompass AI & IoT-based robot and vending solutions, consulting, and flexible leasing or rental models for their robotics. They cater to the HORECA industry, aiming to streamline operations, create new revenue streams, and reduce operational costs through advanced technology.

Brex AI introduces intelligent finance through AI agents designed to eliminate finance busywork and accelerate financial impact. The platform features a Brex Assistant for employees to automate expense reports, categorize transactions, and answer policy questions. An Audit Agent monitors company expenses against internal policies, categorizing potential violations by risk level. A Review Agent auto-approves low-risk expenses, escalates exceptions, and follows up on compliance issues. Brex AI allows businesses to train agents with their expense policies and SOPs, ensuring real-time enforcement and continuous learning. It aims to provide more control through transparency and consistent policy enforcement, making finance faster and smarter.