AI Agents & Automation

Iris.c is an inference pipeline designed for generating images from text prompts using open weights diffusion transformer models. It is implemented entirely in C, requiring zero external dependencies beyond the C standard library. The tool supports various model families, including FLUX.2 Klein (4B and 9B versions) and Z-Image-Turbo (6B), offering both distilled and base models for different quality and speed requirements. Key features include optional MPS and BLAS acceleration for significant speedups, memory-mapped weights for efficient memory usage, and integrated text encoders. It supports text-to-image, image-to-image transformations, multi-reference generation, and an interactive CLI mode, making it a versatile tool for developers and researchers working with image synthesis.

Ask Maya is an AI-powered English language tutor designed to help users practice speaking English through natural, real-time voice conversations. The tool eliminates the need for typing or strict grammar rules, allowing users to speak freely and receive instant feedback to sound more natural. It's accessible 24/7, enabling practice anywhere, anytime, whether on the bus, at home, or during a coffee break. Ask Maya aims to boost confidence and fluency quickly, offering a fun and pressure-free environment for language learners. It provides various plans, including a free trial, and supports payments via PIX and credit card.

AcceptMyApp is an AI-powered assistant designed for iOS developers to streamline the app submission process. It meticulously analyzes your app's metadata against Apple's stringent Review Guidelines, proactively identifying potential rejection risks before you submit your build. This pre-check functionality helps developers avoid costly delays and rework. In cases where an app is rejected, AcceptMyApp provides clear insights into why Apple flagged the build and assists in generating reviewer-safe appeal replies, offering a clear path to fix, appeal, or submit with confidence. The tool leverages AI to provide comprehensive analysis and support throughout the app review lifecycle.

Unmanned Defense Systems specializes in advanced loitering munitions and autonomous swarm systems, designed for fast-paced operations and rapid battlefield readiness. Their offerings include high-performance ISTAR UAV platforms like FORECASTER and HAULER for detection and surveillance, alongside long-range loitering munition UAV platforms such as AVENGER 5 for precise strikes. The core of their system is SwarmC2 software, which enables coordinated UAV operations, integrating reconnaissance, data analysis, battlefield management, and precise loitering munition deployment. This software provides full kill chain control, advanced data analytics, and decision-making capabilities, ensuring seamless integration and enhanced operational control. The modular components of their products ensure rapid deployment and easy battlefield readiness, optimized for reliability in contested environments.

Summie is a mobile meeting assistant designed to streamline meeting documentation and enhance productivity. Users can record any meeting with their phone, and Summie automatically generates accurate summaries, key takeaways, and actionable insights. It supports over 90 languages for audio recording and provides smart transcriptions with speaker detection and replay functionality. A unique feature is the ability to "Ask Summie anything" about your recorded meetings, allowing for deep-dive questions and analysis. The tool prioritizes data security and GDPR compliance, with data retention in Germany and personal data minimization. Summie is ideal for professionals seeking comprehensive meeting insights and automated documentation.

SpeakType is a macOS application offering privacy-first, offline voice dictation. Leveraging WhisperKit AI, all processing occurs entirely on your Mac, ensuring that audio and transcripts remain local without any cloud uploads. This design prioritizes user privacy and data security. The tool is optimized for Apple Silicon, providing efficient and real-time speech-to-text transcription. It integrates seamlessly across various applications via a customizable keyboard shortcut, making it suitable for dictating emails, documents, code, and web forms. SpeakType aims to provide a reliable and secure dictation solution for Mac users.

LowTech AI offers a suite of easy-to-use AI-powered tools designed to boost productivity, creativity, and overall happiness for a wide range of users. The platform provides AI tools backed by thoughtful prompts, making advanced AI accessible to writers, managers, teachers, and many others. Users can quickly summarize text, generate professional emails, code R functions, or find synonyms, all through simple fill-in-the-blank inputs. LowTech AI emphasizes effortless intelligence, allowing users to leverage superhuman abilities without needing extensive technical knowledge. The platform also supports flexible tool creation and seamless sharing, enabling users to create custom AI tools or easily improve existing ones, and share them without requiring recipients to sign up.

Deeptone- AI Duet Songs is an iOS mobile application designed to transform your music listening and creation experience. It empowers users to generate unique song covers by seamlessly replacing original vocals with AI-generated voices. Users have the flexibility to choose from a variety of AI voices, including their own or those of famous singers, to create personalized duets. The app provides free downloads, unlimited streaming, and offline playback capabilities, ensuring a continuous and data-free music experience. This tool is ideal for anyone looking to experiment with vocal transformations and create custom versions of their favorite tracks with ease.

Chainlit is an open-source Python framework designed to accelerate the development of production-ready conversational AI applications. It allows developers to build interactive chat user interfaces in minutes, not weeks, by providing a streamlined environment for integrating AI agents and automated workflows. The framework supports popular AI tools and services such as OpenAI, Anthropic, LangChain, LlamaIndex, ChromaDB, and Pinecone, making it versatile for various AI projects. Chainlit emphasizes ease of use for Python developers, enabling them to quickly prototype and deploy AI applications. While the original team has stepped back from active development, it is now community-maintained, ensuring ongoing support and evolution.

LLamaTuner is an open-source, efficient, flexible, and full-featured toolkit designed for fine-tuning large language models (LLMs). It supports a wide range of models including Llama, Llama2, Llama3, Qwen, Baichuan, GLM, Falcon, and even visual language models (VLMs) like LLaVA. The toolkit is optimized for efficiency, capable of fine-tuning 7B LLMs on a single 8GB GPU and supporting multi-node fine-tuning for models exceeding 70B. It automatically dispatches high-performance operators like FlashAttention and Triton kernels to boost training throughput and is compatible with DeepSpeed for ZeRO optimization techniques. LLamaTuner offers various training algorithms such as QLoRA, LoRA, and full-parameter fine-tuning, alongside support for continuous pre-training, instruction fine-tuning, and agent fine-tuning. It also includes features for chatting with large models using pre-defined templates.

DINO-X-API provides examples for using DINO-X, a unified vision model hosted on DeepDataSpace, designed for open-world object detection and understanding. It offers state-of-the-art performance in open-set detection, including significant improvements in recognizing long-tailed objects. The model accepts text, visual, and customized prompts, generating representations like bounding boxes, segmentation masks, pose keypoints, and object captions. DINO-X supports practical tasks such as Open-Set Object Detection and Segmentation, Phrase Grounding, Visual-Prompt Counting, Pose Estimation, and Region Captioning. It also features a universal object prompt for Prompt-Free Anything Detection and Recognition, and seamless integration with AI tools like Cursor and Claude via DINO-X MCP Server.

UP Bridge the Gap provides a robust platform for AI on the Edge computing, featuring a diverse range of devices such as boards, modules, and complete systems. These devices are designed for industrial use, facilitating advanced industrial automation and AI solutions. The platform supports various applications, including smart city infrastructure, transportation, and industrial inspection, leveraging integrated AI accelerators like Hailo-8™. UP Bridge the Gap also offers development kits, camera support, and a vibrant community forum for technical discussions and support, making it a comprehensive ecosystem for edge AI deployment.

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.

api-for-open-llm is an open-source project that offers a unified backend interface for a wide range of open large language models, designed to mimic the OpenAI ChatGPT API. This allows developers to seamlessly integrate and utilize models such as LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, and ChatGLM into their applications. Key features include support for streaming responses, enabling printer-like effects, and the implementation of text embedding models crucial for document knowledge Q&A. It also integrates with LangChain for advanced LLM development and supports loading fine-tuned LoRA models. The project simplifies the process of using open models as ChatGPT alternatives by requiring only simple environment variable modifications, and it offers vLLM for inference acceleration and concurrent request handling.

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.

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.

Windmill is the leading AI-powered performance review platform designed to provide a comprehensive context graph of your employees. It streamlines performance management by grounding reviews in actual work, leveraging AI to draft performance reviews from real evidence. The platform supports various aspects of people management, including performance reviews, 1:1s with auto-generated agendas, continuous feedback, calibrations, and pulse surveys. Windmill integrates with popular tools like Slack, Jira, and Google Workspace to gather data and facilitate communication, ensuring that feedback is timely and relevant. It aims to make performance reviews faster and more accurate, helping managers and employees focus on meaningful development.

Irene-Voice-Assistant is a Russian offline voice assistant designed to operate without an internet connection, making it ideal for local control and automation. It supports an extensible plugin system, allowing users to add new skills and functionalities. The assistant requires Python 3.5+ for operation and offers various installation methods, including a quick installer for Windows and detailed instructions for Linux and Mac. A key feature is its integration with LLMs like ChatGPT and GPT-4 via the VseGPT.ru service, enabling advanced AI-powered interactions and information retrieval from the internet. It also boasts a high-performance VOSK streaming STT model, offering Whisper-level recognition accuracy locally. A web-based settings manager simplifies configuration and plugin management.

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.

Verve AI is a comprehensive AI interview assistant designed to help job seekers excel in live online interviews. It provides real-time AI guidance, discreet assistance, and a suite of tools including resume builders and mock interviews. The platform learns from your background and goals to offer tailored responses, automatically detecting questions and suggesting the best answers. Verve AI supports various interview types, including behavioral, technical, coding, online assessments, and HireVue, and works across all major meeting platforms like Zoom, Google Meet, and Microsoft Teams. Its unique 'Stealth Mode' ensures the AI is visible only to the user, even during screen sharing, providing confidence and support without detection. It also offers specialized copilots for coding interviews and supports over 55 languages.