AI Agents & Automation

RLinf is a flexible and scalable open-source reinforcement learning (RL) infrastructure specifically designed for Embodied and Agentic AI. It acts as a robust backbone for next-generation training, supporting open-ended learning, continuous generalization, and limitless possibilities in intelligence development. The platform offers high flexibility for diverse RL training workflows, including PPO, GRPO, and SAC, while abstracting the complexities of distributed programming. Users can easily scale RL training across numerous GPU nodes without code modification. RLinf integrates with multiple backends like FSDP, HuggingFace, SGLang, vLLM, and Megatron, catering to both rapid prototyping and large-scale, efficient training. It supports a wide array of embodied AI simulators, VLA models, world models, and real-world robotics data collection, making it a comprehensive solution for advanced RL research and development.

Qwen3-VL is a multimodal large language model series developed by the Qwen team at Alibaba Cloud. This advanced model offers significant enhancements in text understanding and generation, visual perception and reasoning, extended context length, and improved spatial and video dynamics comprehension. It also features stronger agent interaction capabilities, including operating PC/mobile GUIs and generating code from images/videos. Available in Dense and MoE architectures, Qwen3-VL supports flexible deployment from edge to cloud, with Instruct and reasoning-enhanced Thinking editions. Key features include advanced spatial perception, long context and video understanding, enhanced multimodal reasoning for STEM/Math, upgraded visual recognition, and expanded OCR supporting 32 languages.

RoboticsDiffusionTransformer (RDT-1B) is a 1-billion parameter diffusion foundation model specifically designed for bimanual robotic manipulation. It is pre-trained on an extensive dataset of over 1 million multi-robot episodes, making it the largest to date. RDT-1B can predict the next 64 robot actions based on language instructions and RGB images from up to three views. The model is compatible with various modern mobile manipulators, supporting single-arm to dual-arm configurations, joint to EEF control, and position to velocity commands, including wheeled locomotion. This repository provides the official PyTorch implementation, including model checkpoints, training and sampling scripts, and an example for real-robot deployment on the ALOHA dual-arm robot, where it has achieved state-of-the-art performance in dexterity, zero-shot generalizability, and few-shot learning.

RamiGPT is an AI-powered offensive security agent built for autonomous privilege escalation. It integrates PwnTools and OpenAI capabilities to identify and exploit vulnerabilities, achieving root access on systems from VulnHub in remarkably short times, often under a minute. The tool is designed for cybersecurity professionals and security researchers, offering features like automated enumeration, integration with tools such as BeRoot and LinPEAS, and the ability to import and export instructions. Users need an OpenAI API key to utilize RamiGPT's capabilities, and it can be run either via Docker or locally with Python. RamiGPT emphasizes responsible use, strictly for educational and authorized security testing purposes.

SINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy. It allows users to deploy models that would otherwise be too large, drastically reducing memory usage. SINQ offers both calibration-free (SINQ) and calibrated (A-SINQ) versions, providing state-of-the-art performance. It is integrated into Hugging Face Transformers for simplified use and supports saving and reloading quantized models. SINQ boasts significantly faster quantization speeds compared to alternatives like HQQ and AWQ, making it an efficient solution for LLM optimization.

sleepless-agent is an open-source 24/7 AI agent designed to maximize the utility of Claude Code Pro. It operates as an AgentOS, processing tasks and ideas submitted via Slack, and managing them within isolated workspaces. The tool automates various development workflows, including creating Git commits and pull requests, and intelligently optimizes day/night usage thresholds for Claude Code Pro. It features continuous operation, Slack integration for task submission and interactive chat, hybrid autonomy for task processing, and smart scheduling. Developers can use it to automate repetitive coding tasks, manage projects, and ensure efficient use of their AI resources.

Solace Agent Mesh is an open-source, event-driven framework designed to build and orchestrate multi-agent AI systems. It allows developers to create teams of specialized AI agents, each with distinct skills and access to specific tools, such as database agents or multimodal agents. The framework handles communication between agents automatically, leveraging the Solace Platform for true scalability and reliability. Built on the Solace AI Connector (SAC) and Google's Agent Development Kit (ADK), it provides a fully asynchronous, event-driven, and decoupled AI agent architecture ready for production deployment. Key features include multi-agent event-driven architecture, agent orchestration, flexible interfaces, and dynamic embeds for context-dependent information resolution.

chart-gpt is an open-source AI tool designed to build charts quickly and efficiently from text input. Users can clone the repository, set up their PaLM API key, and start generating visualizations. The project supports full functionality with additional setup for a credit system, requiring integration with Supabase, Stripe, and NextAuth with Google. This makes it a flexible solution for developers and data enthusiasts looking to integrate AI-powered chart generation into their workflows or projects. The tool is built with TypeScript, CSS, and JavaScript, indicating a modern web-based application.

Serena is an advanced toolkit designed to function as an IDE for AI coding agents, offering semantic retrieval, editing, refactoring, and debugging capabilities. It integrates with any client/LLM via the Model Context Protocol (MCP), enabling agents to operate faster and more reliably, especially in large and complex codebases. Serena supports over 40 programming languages through its language server backend and leverages JetBrains IDEs' powerful code analysis via a paid plugin. Its agent-first tool design uses robust high-level abstractions, distinguishing it from approaches relying on low-level concepts. Serena also includes basic utilities like file search, shell command execution, and a memory management system for long-lived agent workflows.

Service Streamer is a middleware designed to optimize web services for deep learning applications, particularly by improving GPU utilization. It addresses the challenge of discrete user requests in web services versus the mini-batch processing typical of deep learning models, collecting requests into mini-batches to leverage parallel computing capabilities. This approach significantly enhances overall system performance and reduces latency for online inference. The tool is easy to use, requiring minor code changes to achieve substantial speed improvements, and offers good expandability for multi-GPU scenarios. It is compatible with various web and deep learning frameworks, making it a versatile solution for deploying and accelerating machine learning models in production environments. Service Streamer supports distributed GPU workers and web servers, and can be integrated with Redis for distributed setups.

Didero is a leading agentic system designed to automate procurement processes, helping businesses save time and money while allowing teams to focus on strategic tasks. It automates routine workflows such as sourcing, quoting, onboarding, contracting, PO lifecycle management, and AP MDM/ERP integration. Didero integrates with existing systems with low-touch, 2-week integration, requiring no internal IT build. The platform is recognized for its ability to handle imperfect data and provides enterprise-grade security with SOC 2 Type II compliance. It offers continuous improvement as agents learn and adapt over time, with human oversight ensuring control and strategic decision-making.

rust-bert is a Rust-native library offering ready-to-use Natural Language Processing (NLP) pipelines and transformer-based models. It serves as a port of Hugging Face's Transformers library, leveraging `tch-rs` for Libtorch bindings or `onnxruntime` for ONNX support, and `rust-tokenizers` for preprocessing. The library supports a wide array of NLP tasks including question answering, named entity recognition, translation, summarization, text generation, conversational agents, and more. It features multi-threaded tokenization and GPU inference for efficient processing. Users can get started with tasks like question answering with just a few lines of code, making it a powerful tool for integrating advanced NLP capabilities into Rust applications.

Show Me ChatGPT Plugin is a powerful tool designed to integrate diagram creation and editing seamlessly into the ChatGPT interface. Users can generate various diagrams, such as flowcharts, system architectures, and process maps, simply by providing text descriptions. This eliminates the need to switch between applications, streamlining workflows for visualizing complex information. The plugin supports real-time editing, allowing for quick modifications and refinements without leaving the chat environment. While the public version is no longer actively updated, the project demonstrates a significant capability for enhancing communication and understanding through visual aids within conversational AI platforms.

Owlu is a free AI email agent designed for solo professionals, freelancers, and one-person founders to streamline email management. It features chat-driven workflows, allowing users to automate tasks like summarizing reports, cleaning newsletters, or saving attachments. The tool prioritizes a 'human-in-the-loop' approach, ensuring users can review and approve actions before they are sent. Owlu integrates directly with Gmail, sending emails from the user's real account. Its Smart Inbox feature provides plain-language summaries and suggested next actions for each email, enabling quick triage and response. Users can also create personalized email campaigns and manage client communications at scale.

DeepVA is a composite AI platform designed for media companies to extract various types of information from images, videos, and live streams. It automates complex AI processes such as tagging, indexing, and searching, significantly enhancing content management, accessibility, and workflow efficiency. The platform supports both cloud and on-premises deployments, ensuring data sovereignty and compliance with regulations like GDPR and the AI Act. DeepVA allows users to train and utilize AI datasets with existing staff, offering a user-centric approach to custom model creation. It integrates seamlessly with existing workflows and third-party applications via an API-centric design, providing a future-proof solution with cutting-edge technology and a shorter time to market.

Drover AI pioneers the use of computer vision and AI on micromobility vehicles to address the limitations of existing IoT solutions. It aims to deliver a safer experience for all stakeholders, ensuring compliance with regulations and enabling cities to embrace micromobility as part of a sustainable urban transportation ecosystem. The platform offers PathPilot, an advanced module for real-time vehicle control and granular trip insights, and Drover Corral, a data dashboard for fleet behavior analysis. Drover AI helps operators win permits, mitigate operational inefficiencies, reduce insurance costs, and avoid fines by improving parking outcomes and detecting sidewalk/bike lane usage.

Clera acts as an AI-powered talent agent, specifically designed to connect top talent with elite jobs at high-growth startups. It streamlines the job search process by learning a candidate's preferences, experience, and dealbreakers through short conversations, then matching them with relevant companies. Instead of applying, candidates get direct introductions to founders and hiring managers, complete with context on why they are a good fit. Clera also assists with interview preparation and salary negotiation. It is entirely free for job seekers, with companies paying a success fee only upon a successful hire, making it a risk-free option for those looking to advance their careers in the startup ecosystem.

SpeechGPT is an open-source and privacy-focused web application designed for interactive conversations with ChatGPT. It allows users to improve their language speaking skills or simply engage in fun chats. The tool supports over 100 languages and integrates both built-in speech recognition and synthesis, along with optional support for Azure Speech Services and Amazon Polly. All user data is stored locally, ensuring privacy. It is mobile-friendly and can be deployed via Vercel or Docker, making it accessible and flexible for various users.

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime and SDK specifically designed for production AI agents. It offers OS-level abstractions for various AI resources such as LLMs, vector databases, storage, and caching, all accessible through a unified API. This allows developers to write agent logic once and scale it across local, cloud, and edge environments without changing their business logic. SRE emphasizes built-in security, observability, and includes over 40 production-ready components. It provides a robust and scalable foundation for agent orchestration and lifecycle management, making it easier to ship production-ready AI agents.

SynapseML (previously known as MMLSpark) is an open-source library designed to simplify the creation of massively scalable machine learning (ML) pipelines. It offers simple, composable, and distributed APIs for a wide variety of ML tasks, including text analytics, computer vision, anomaly detection, and deep learning. Built on the Apache Spark distributed computing framework, SynapseML shares the same API as the SparkML/MLLib library, allowing seamless integration into existing Apache Spark workflows. It supports training and evaluating models on single-node, multi-node, and elastically resizable clusters, and is usable across Python, R, Scala, Java, and .NET. Its API abstracts over various databases, file systems, and cloud data stores, simplifying experiments regardless of data location.

Magictool AI Chrome Extension is an all-in-one AI productivity copilot, integrating ChatGPT and 20 AI features for enhanced efficiency. It provides an AI Writing Copilot for crafting engaging content, grammar checks, text improvement, and summarization. Users can also summarize YouTube videos, chat with and summarize PDFs, and generate AI images using Stable Diffusion. The extension includes data scraping, a Magic Editor for AI-powered text editing, and a Reader Mode for clutter-free web page viewing. Additional features like Dark Mode, data analytics for CSV/Excel, custom AI commands, and note-taking further boost productivity.

Deep Vision AI, acquired by DFW Capital and now operating under EPIC iO, provides advanced AIoT solutions tailored for critical infrastructure. The platform, including DeepVision™ as a centralized VMS & Unified Command Center, offers real-time analytics, robust wireless connectivity, and AI-driven insights to significantly enhance safety, operational efficiency, and decision-making. It supports diverse applications such as physical site security with features like perimeter security and license plate recognition, and site safety with PPE validation and fire monitoring. The system also includes environmental and equipment monitoring, leveraging AI-powered sensor intelligence. EPIC iO's solutions are designed for rapid deployment and offer secure, fast, and unbreakable 4G/5G wireless connectivity, making them ideal for distributed, remote, and high-risk environments across numerous industries.

Grayscale AI specializes in advanced AI solutions for fully autonomous drones and robots, leveraging neuromorphic computing and AI. The company's technology is designed to mimic human neural networks, offering significant advantages in efficiency, safety, and speed. By circumventing traditional computing architecture, Grayscale AI's systems can achieve up to 500x less energy consumption, enabling complex AI operations without requiring a cloud connection. Their VUES methodology allows for strategy-focused optimization and human-like precision in responding to unforeseen events, analyzing edge cases in less than 100 ms. This approach results in safer, greener, and faster AI solutions for mobility and transport/logistics.

iWeaver is an AI-powered knowledge assistant designed to streamline workflow automation and knowledge management. It allows users to upload various content formats, including PDFs, documents, research papers, web pages, and YouTube videos, to analyze, summarize, and organize information in one place. The platform features a multi-agent processing system that automates over 70% of tasks, coordinating specialized AI agents for specific functions like summarizing, mind mapping, and content creation. iWeaver aims to provide structured knowledge by identifying key concepts and connecting ideas across documents, making it ideal for tasks such as financial analysis, legal research, academic studies, and content production. It offers a natural dialogue experience, adapting to user needs and providing actionable insights based on a continuously evolving knowledge base.