AI Agents & Automation

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.

TPVFormer is an academic project offering a Tri-Perspective View (TPV) representation for vision-based 3D semantic occupancy prediction, serving as an alternative to Tesla's Occupancy Network for autonomous driving research. It addresses the limitations of traditional bird's-eye-view (BEV) representations by incorporating two additional perpendicular planes, allowing for a more fine-grained description of 3D scenes. The tool features a transformer-based TPV encoder (TPVFormer) to effectively obtain TPV features by aggregating image features. It demonstrates that camera inputs alone can achieve performance comparable to LiDAR-based methods on LiDAR segmentation tasks. The project also includes resources for semantic scene completion and comparisons with Tesla's Occupancy Network.

self-host-n8n-on-gcr provides a comprehensive guide for deploying n8n, a powerful workflow automation platform, on Google Cloud Run. This setup allows users to leverage n8n's capabilities without incurring monthly subscription fees, while also ensuring complete control over their data. The guide details a serverless deployment approach with per-use pricing, effectively eliminating the complexities and costs associated with traditional server maintenance. It covers essential steps including Google Cloud project setup, n8n preparation for Cloud Run, container repository configuration, Cloud SQL PostgreSQL instance creation for database persistence, and secure handling of sensitive data using Secret Manager. The guide also outlines the deployment process to Cloud Run, offering both official image and custom Docker image options, making it suitable for users seeking cost-effective and scalable automation solutions.

Sevensense offers Visual AI technology designed to empower mobile robots and industrial vehicles to operate effectively in complex, dynamic environments. Their core products, Alphasense Position and Alphasense Tracker, provide industry-grade Visual-SLAM (Simultaneous Localization and Mapping) for autonomous mobile robots (AMRs) and a real-time locating system (RTLS) for manually operated industrial trucks, respectively. This technology allows for unified mapping and spatial awareness across hybrid fleets, enhancing efficiency, reducing operational costs, and improving safety through collision prevention and predictive risk alerts. Sevensense's camera-based positioning eliminates the need for extensive infrastructure, facilitating quick deployment and easy fleet expansion. The system integrates seamlessly with existing FMS, WMS, and ERP systems, transforming vehicle movements into actionable data for smarter operations.

llama2-webui is an open-source tool designed for running Llama 2 models locally through a Gradio web UI. It offers broad compatibility, supporting all Llama 2 models (7B, 13B, 70B, GPTQ, GGML, GGUF, CodeLlama) and various backends like transformers, bitsandbytes (8-bit inference), AutoGPTQ (4-bit inference), and llama.cpp. The tool can be deployed on Linux, Windows, and Mac, utilizing either GPU or CPU resources. Developers can also leverage `llama2-wrapper` as a local Llama 2 backend for generative agents and applications, and it provides an OpenAI-compatible API for seamless integration with existing clients and libraries. Benchmarking scripts are included to evaluate performance on different devices.

AppSteer is a powerful low-code/no-code platform designed for building enterprise-grade applications quickly and efficiently. It integrates Agentic AI to transform data into actionable insights, automate tasks, and generate powerful dashboards, helping businesses make smarter, faster decisions. The platform offers a library of pre-customized applications and pre-built templates, along with 100 hours of free assistance to streamline development. AppSteer supports seamless integration with existing APIs and various third-party services, making it adaptable to diverse business needs. It caters to businesses of all sizes, from startups to large enterprises, providing scalable and reliable solutions for various industries including healthcare, education, FinTech, and retail.

Mapless AI offers a comprehensive solution for remote car operation, allowing full operational remote control of existing fleet vehicles. The technology focuses on providing optimized, low-latency connectivity between remote operators and vehicles, enabling navigation of complex scenarios and precise maneuvering. This system is designed for existing fleets, featuring scalable retrofits that combine software and automotive-grade hardware. The installation is temporary, reversible, and causes no cosmetic damage. Mapless AI also provides a Dispatch-as-a-Service option, where trained remote operators manage fleet vehicle dispatch on-demand, eliminating the need for clients to onboard their own driving staff. This technology is currently in use for services like fleet valet at Pittsburgh Airport and carshare rebalancing in Detroit.

Autocalls is an AI-powered voice agent platform designed to automate inbound and outbound phone calls and WhatsApp communications. It enables businesses to deploy AI voice agents that can autonomously make and receive calls, book meetings, qualify leads, and provide customer support. The platform supports over 100 languages and offers numbers in over 150 countries. Key features include a no-code interface, real-time analytics, CRM integration, and live transfers. Autocalls also provides white-label solutions, making it ideal for agencies looking to offer AI call automation under their own brand. With over 300 integrations and ElevenLabs voices, it offers a comprehensive and cost-effective solution for automating voice communications.

DI-drive is an open-source Decision Intelligence Platform specifically designed for Autonomous Driving simulation. It provides a unified entry point to apply Decision Intelligence across various driving simulation suits, supporting different simulators, datasets, and cases. The platform is built on DI-engine, a Reinforcement Learning platform, and currently integrates with popular simulators like Carla and MetaDrive. DI-drive enables users to run Imitation Learning, Reinforcement Learning, and GAIL experiments, offering a comprehensive environment for developing and evaluating autonomous driving policies. It includes a Model Zoo with pre-trained models and a Casezoo for scenario-based training and testing, making it a robust tool for advanced research and development in autonomous driving.

Conformer is an unofficial PyTorch implementation of the "Conformer: Convolution-augmented Transformer for Speech Recognition" model, originally presented at INTERSPEECH 2020. This tool is designed to leverage both Convolutional Neural Networks (CNNs) for local feature extraction and Transformers for capturing global interactions within audio sequences. By combining these architectures, Conformer achieves state-of-the-art accuracies in speech recognition tasks while maintaining parameter efficiency. The repository provides the core model code, allowing developers and researchers to integrate and train Conformer within their own speech processing pipelines. It requires Python 3.7 or higher, along with Numpy and PyTorch, and can be installed from the source code.

MatGL (Materials Graph Library) is an open-source graph deep learning library specifically designed for materials science. It leverages mathematical graphs to represent atomic collections, allowing for the development of surrogate models that consistently deliver exceptional performance in predicting material properties. The library aims to be an extensible platform for creating and sharing materials graph deep learning models. MatGL includes implementations of various architectures such as M3GNet, MEGNet, CHGNet, QET, and TensorNet, with a transition towards PyTorch Geometric (PyG) as the default backend. It offers pre-trained models, a command-line interface for quick relaxations and predictions, and integration with Hugging Face Hub for model sharing and loading. MatGL is a collaborative effort between Materialyze.AI and Intel Labs, forming part of the broader MatML ecosystem.

Anything V3.0 is an AI application hosted on Hugging Face Spaces by akhaliq. The tool is currently non-functional, displaying a runtime error related to an unexpected keyword argument in its `DPMSolverMultistepScheduler` initialization. This indicates a potential issue with its underlying code or dependencies. As a result, its intended capabilities, such as content generation or educational assistance, are not accessible at this time. The project is open source, allowing community members to inspect and potentially contribute to its resolution.

Maestro is a general-purpose workflow orchestrator developed by Netflix, offering a fully managed workflow-as-a-service (WAAS) for data platform users. It serves a diverse user base, including data scientists, data engineers, machine learning engineers, software engineers, content producers, and business analysts, for various use cases. Maestro is designed to be highly scalable and extensible, supporting both existing and new use cases while offering enhanced usability. It schedules hundreds of thousands of workflows and millions of jobs every day, operating with strict Service Level Objectives (SLOs) even during traffic spikes. The tool provides a Python SDK client for creating and managing workflows programmatically, and supports integration with AWS and Kubernetes.

chatgpt-conversation is an open-source tool designed to facilitate voice-based conversations with ChatGPT. It allows users to speak their queries and receive spoken replies from the AI model, offering a more natural and accessible interaction method. The tool requires local installation of dependencies like espeak, ffmpeg, portaudio19-dev, and python3-pyaudio, primarily on Ubuntu. Users need to configure it with a session token and install Python requirements. Once set up, it supports continuous conversation, allowing users to respond to ChatGPT without interruption. Future plans include features like interrupting ChatGPT mid-speech, silencing PyAudio errors, and developing a web-app version for improved text-to-speech and broader accessibility.

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.

Doc Scan - PDF Scanner is a comprehensive mobile application designed for iPhone and iPad, transforming these devices into versatile document scanners and PDF editors. Users can efficiently scan single or multi-page documents using their device's camera, with AI Recognition technology for auto-detection. The app offers robust editing features, allowing users to annotate, fill forms, add text and pictures, and apply digital signatures. It also includes OCR technology to extract text from scans, convert images to PDF, and merge multiple pages into a single document. Doc Scan supports various sharing options, including email, FAX, SMB, and cloud services like Dropbox and Google Drive, ensuring documents can be easily managed and distributed.

LitterBox provides a controlled sandbox environment specifically designed for security professionals, including malware developers and red teamers. It enables users to test evasion techniques against modern detection mechanisms, validate detection signatures before deployment, and analyze malware behavior in an isolated environment. The platform ensures payloads remain in-house, preventing exposure to external security vendors and confirming functionality without triggering production security controls. LitterBox features LLM-assisted analysis capabilities through the LitterBoxMCP server, offering advanced analytical insights using natural language processing. It supports both static and dynamic analysis, including file identification, entropy analysis, executable analysis for PE files, document analysis, and LNK analysis. Dynamic analysis offers runtime behavioral monitoring, memory inspection, and detection of techniques like process hollowing and code injection. The tool also includes HolyGrail for BYOVD analysis and Blender/FuzzyHash modules for code similarity and process comparison.

The supabase-mcp tool facilitates seamless integration between Supabase projects and AI assistants by implementing the Model Context Protocol (MCP). This protocol standardizes how Large Language Models (LLMs) communicate with Supabase, enabling AI assistants to directly interact with and perform tasks within Supabase projects. This capability is crucial for developers looking to build intelligent applications that leverage the robust backend services of Supabase with the advanced reasoning and data processing of AI. By providing a structured communication layer, supabase-mcp simplifies the development of AI-powered features, allowing for more efficient data handling, task automation, and dynamic application responses based on real-time data from Supabase.

Brave Browser & Search Engine offers a fast, private, and secure web browsing experience across desktop and mobile devices. It features an integrated ad blocker, tracker blocker, and fingerprinting protection, leading to significantly faster page load times and data savings. The browser also includes Brave Search, an independent and private search engine that doesn't profile users, and a built-in AI assistant called Leo AI for generating content and answering questions. For enhanced privacy, Brave offers a Firewall + VPN that protects all apps on a device, not just the browser. Users can also opt-in to Brave Rewards to earn Basic Attention Tokens (BAT) by viewing privacy-preserving ads, which can then be used to support content creators or for other rewards. Brave is built on the open-source Chromium Web core, ensuring a familiar yet more secure and private browsing environment.

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.

Dilseheal is an AI-powered hospital recommendation system designed to connect patients with the most suitable healthcare providers. It leverages artificial intelligence to recommend hospitals based on various factors including medical condition, financial status, valid user reviews, and hospital background checks. The platform aims to streamline the process of finding the right treatment by offering information about hospitals near the user. Beyond recommendations, Dilseheal allows users to track health issues through vaccination and monitoring records, and facilitates the creation, editing, and sharing of medical records for controlled collaboration between doctors. It emphasizes verified hospitals, expert consultation, 24/7 support, and a patient community.

Utter is a local-first dictation application designed for Mac and iPhone users, enabling them to transform spoken words into clear, polished text across any app. It boasts a speed up to four times faster than traditional typing, facilitating a seamless flow from thought to text. The app prioritizes privacy with on-device processing, ensuring audio is not stored or used for training, and no account is required. Key features include dictation in any app via a global shortcut, a searchable voice history, AI modes for tone and format adjustment, speaker-separated transcripts for meetings, and support for over 50 languages. It also offers offline functionality and file transcription for audio and video.

Wokelo is an agentic AI platform specifically designed for investment research and due diligence. It automates critical processes such as deal sourcing, due diligence, deal research, and strategy development. The platform utilizes proprietary AI agents trained on investment methodologies and provides access to an extensive database of over 20 million companies. Trusted by major firms like KPMG and SoftBank, Wokelo aims to enhance efficiency and accuracy for professionals in investment banking, private equity, venture capital, and management consulting by providing advanced tools for market analysis and strategic decision-making.

Job Genie is an AI-powered platform designed to streamline the job search process, replacing manual tracking methods like spreadsheets and documents. It offers a comprehensive suite of features for job seekers, including tools to discover recommended jobs, a Chrome Extension for saving listings, and an Application Hub with Kanban and Calendar views for progress tracking. The platform also provides smart follow-up reminders and robust AI-powered preparation tools such as AI Interview Prep, CV Matching, and an About Me Generator. Furthermore, Job Genie offers valuable insights into job search trends, conversion rates, drop-off funnels, and ghosted applications, helping users refine their strategy and improve their chances of landing their dream job. It aims to make the job search magical by centralizing all necessary tools in one application.