AI Agents & Automation

KAN-TTS is a comprehensive speech-synthesis training framework designed to empower users to develop and customize their own text-to-speech (TTS) models from the ground up. The framework currently supports popular models such as sam-bert and hifi-GAN, with plans to integrate more in the future. It offers extensive language support, including Mandarin, English, British English, Shanghainese, Sichuanese, Cantonese, Italian, Spanish, Russian, and Korean, making it versatile for a global audience. KAN-TTS provides a training tutorial through its wiki page and offers a demo on ModelScope for users to experience its capabilities. The project is open-source, hosted on GitHub, and encourages community contributions.

Kernel Labs is a startup studio located in Seattle, Washington, with a strong focus on machine learning, computer vision, and security. The company's mission is to build innovative ventures that aim to create and disrupt significant markets. They actively partner with CEOs, providing deep expertise and support to nurture new ideas from concept to fruition. Their team comprises industry veterans with a proven track record in technology and business development, including a CEO passionate about disruptive innovation and a VP of Engineering with a Ph.D. in Computer Science. Kernel Labs is dedicated to developing technology strategies and ensuring excellence in product development for their portfolio companies.

KouriChat is an open-source, LLM-based emotional companionship program designed to create more realistic emotional companionship experiences. It allows users to interact with virtual characters, offering features like multi-user support, immersive role-playing, and intelligent dialogue segmentation with emotional emojis. The platform also integrates image generation and recognition capabilities through Kimi, supports voice messages, and provides persistent memory storage. KouriChat includes an automatic update function and a visual WebUI for ease of use. It is primarily deployed on Windows Server and offers a semi-automatic deployment process, making it accessible for users with varying technical skill levels.

KVCache-Factory is a unified framework designed for KV Cache compression methods specifically for auto-regressive models. It offers support for multi-GPU inference, making it suitable for large language models such as Llama-3-70B-Instruct. The framework integrates various compression techniques including PyramidKV, SnapKV, H2O, and StreamingLLM, and is compatible with Flash Attention v2 and Sdpa Attention. It provides tools for performance visualization and supports inference on benchmarks like LongBench and Needle in a Haystack. KVCache-Factory is an open-source project, making it accessible for developers and researchers working on optimizing LLM inference.

LLM-Dojo is a lightweight, open-source framework designed for post-training large language models (LLMs). It offers comprehensive support for various training methodologies, including Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback with Value Regularization (RLVR), On-Policy Knowledge Distillation (On-Policy KD), and Guide Knowledge Distillation (Guide KD). The platform also facilitates mixed training approaches, enabling single-round or multi-round Guide distillation, multi-teacher distillation, and reward mixed training. A key feature is its automated data shunting capabilities. Built on a refactored OpenRLHF core, LLM-Dojo streamlines the framework by retaining only the essential RLVR components and integrating advanced KD and Guide-KD techniques, making it suitable for rapid fine-tuning experiments with features like Deepspeed support, LoRA/QLoRA, and automatic chat template adaptation.

free-gpt3.5-2api is an open-source project designed to offer free API access to GPT-3.5, enabling developers to integrate powerful language models into their applications. It supports various authentication methods, including免登录chat2api,账号chat2api, and ACCESS_TOKEN, providing flexibility for different use cases. The tool can be easily deployed using Docker, Docker Compose, Vercel, or Koyeb, making it accessible for a wide range of development environments. It also includes features to prevent API abuse, ensuring secure and controlled access. The project offers model mapping for various GPT-3.5 turbo versions to a common render-sha model, and also supports gpt-4o.

Hugging Multi-Agent is a comprehensive tutorial designed for developers interested in understanding and implementing multi-agent systems, particularly those based on the MetaGPT framework. It offers a practical learning path, guiding users from foundational agent concepts to the development of complex multi-agent applications. The tutorial is ideal for engineers aiming for career advancement in large language model and agent development, focusing on hands-on coding and personalized agent capabilities. It requires Python programming skills, including some asynchronous programming knowledge, and the ability to read and understand project source code. The resource covers agent structure, multi-agent frameworks, and practical development steps, including creating simple and multi-functional agents, as well as managing agents.

GPT-vup is an open-source project designed to create AI virtual hosts (VUPs) for live streaming on platforms such as BiliBili and Douyin. Built on a producer-consumer model and utilizing OpenAI embeddings and the GPT-3.5 API, it allows VUPs to answer audience comments and Super Chats, welcome new viewers, and thank gift-givers. The tool offers various plugins for enhanced functionality, including speech interaction for voice-to-text communication, action matching for VUPs to react to audience behavior, and scheduled events for storytelling or rap performances. It also supports context plugins for enriching conversations and integrates with Vtube Studio for avatar animation.

Gradio Hackathon Registration Winter 25 is a Hugging Face Space designed to facilitate registration for the Gradio Agents & MCP Hackathon Winter 2025. This application allows participants to sign up by submitting their name, email address, Hugging Face username, details about their usage, and their proposed project idea. The information provided by registrants is securely stored in a shared dataset, ensuring proper management of participant data for the hackathon. While the tool's primary function is registration, its underlying technology and hosting on Hugging Face Spaces highlight its connection to the AI and machine learning community.

EIDON AI offers a comprehensive data infrastructure layer for robotics, focusing on collecting and processing human demonstration data for AI robot manipulation. The platform includes the Eidon Tracker, a 7-IMU wearable for full upper-body arm kinematics, and the Eidon Glove, which provides 16-DOF finger tracking. Data collection is facilitated by the Eidon App, available on iOS and Android, which syncs natively with the hardware to capture synchronized egocentric video and sensor data. This app also supports video-only collection and handles operator payments. Collected data flows into Eidon Sym, a simulation environment and data pipeline that uses VLM-powered quality control to filter, auto-tag objects, and output simulation-compatible formats for model training.

oai-skills is an open-source GitHub repository that archives the contents of the `/home/oai/skills` directory found within ChatGPT's code interpreter environment. This project, initiated by Elias Judin, provides a snapshot of the skills and functionalities available to the AI. It serves as a valuable resource for developers, researchers, and anyone interested in understanding the underlying capabilities and tools utilized by ChatGPT's code interpreter. The repository is read-only, indicating its purpose as a historical archive rather than an active development project. Users can explore the various files and folders to gain insights into how the code interpreter operates and what kind of tasks it is equipped to handle, making it useful for educational and investigative purposes.

PyOD is a comprehensive Python library for anomaly detection, established in 2017 and widely used in both academic research and commercial products. It supports over 60 detectors across tabular, time series, graph, text, and image data, all accessible through a unified API. Version 3 introduces ADEngine for intelligent orchestration and an agentic workflow via the 'od-expert' skill for AI agents, allowing natural language interaction for anomaly detection investigations. The library maintains backward compatibility with its classic fit/predict API and is built on SUOD for fast parallel training and Numba JIT for per-model speedups. It is recognized for its impact in space and science, enterprise deployments, and educational courses.

pytorch-seq2seq offers comprehensive tutorials for understanding and implementing sequence-to-sequence (seq2seq) models using the PyTorch deep learning framework and TorchText library. The repository focuses on practical application, guiding users through the process of training models for neural machine translation, specifically from German to English. It covers foundational seq2seq concepts, including encoder-decoder models with LSTMs and GRUs, and delves into advanced topics like attention mechanisms to alleviate information compression problems. The tutorials are structured to build knowledge progressively, starting with basic workflows and moving to more sophisticated architectures. It also provides necessary setup instructions, including dependency installation and spaCy model downloads, making it a valuable resource for those looking to implement and experiment with seq2seq models.

PrivateBlok is an AI platform specifically designed for private markets, offering a comprehensive suite of tools that integrate data, intelligence, and customizable workflows. The platform leverages a sophisticated Multi-Agent System to efficiently manage various financial workflows. It incorporates both public and proprietary data sources to provide robust insights. A key feature is its AI Co-pilot, which assists users with critical functions such as investment intelligence, investor reporting, and portfolio tracking, making it a valuable asset for professionals in the private market sector.

The website for Hydralogic AI currently displays a 'Parked Domain name on Hostinger DNS system' message. The content on the page promotes Hostinger's services, such as web hosting, AI-powered website builders, and VPS hosting. It mentions using AI tools to launch websites, including features like CRM and booking forms through 'Horizons'. The site also offers options for finding similar domains and creating professional email addresses. There is no specific information about Hydralogic AI as an AI consulting company, suggesting the domain may have been acquired or is no longer active under its original purpose.

ForU AI is a platform dedicated to building a proof-based reputation system for both human contributors and AI agents within the AI economy. Its core mission is to establish a trust layer, enabling the verification of contributors and securing communities. The platform analyzes patterns and traits to generate user profiles, aiming to provide a reliable and verifiable identity for participants in AI-driven ecosystems. This system is designed to foster trust and accountability, which are crucial for the widespread adoption and integration of AI technologies across various sectors.

Seeing AI is a free application specifically designed for individuals who are blind or have low vision. This ongoing research project leverages the power of AI to provide a visual assistant that narrates the surrounding world. The app helps with various daily tasks, including reading text, describing photos, and identifying products. It continuously evolves based on feedback from its community and advancements in AI research, aiming to open up the visual world for its users and enhance their independence and comfort.

Simple_Reinforcement_Learning is an open-source toolkit designed for the development and testing of reinforcement learning algorithms. It provides a structured environment for implementing various RL techniques, including stateless problems, Markov Decision Processes, dynamic programming, temporal difference algorithms, DynaQ, DQN, policy gradient, Actor-Critic, PPO, DDPG, SAC, imitation learning, offline learning, MPC, MBPO, goal-oriented reinforcement learning, and multi-agent systems. The toolkit is built to run on Python 3.9, PyTorch 1.12.1, and Gym 0.26.2, making it compatible with widely used machine learning libraries and environments. It serves as a valuable resource for researchers and engineers looking to explore and experiment with different reinforcement learning paradigms.

SUSI.AI server backend is an open-source Artificial Intelligence server designed to power personal assistants. It facilitates both chat and voice interactions, allowing users to perform a wide range of actions such as music playback, managing to-do lists, setting alarms, streaming podcasts, and accessing real-time information like weather and traffic. The server's core intelligence and personality drive the SUSI.AI platform, with additional functionalities extensible via external APIs. It is highly customizable, allowing users to deploy it on various platforms like Heroku, Google Cloud, AWS, Azure, and Digital Ocean, and even develop custom skills for tailored AI experiences. The project emphasizes community contributions for bug fixes and feature enhancements.

Honda Research Institute Europe (HRI-EU) is a leading research institution dedicated to innovation through science, particularly in the fields of Artificial Intelligence and intelligent systems. Their core focus is on Cooperative Intelligence, aiming to develop systems that work effectively among, for, and with humans. Research areas include cooperative behavior, data analytics, learning, ethics in AI, perception, knowledge representation, personalization, human-machine interaction, prediction, risk assessment, and system optimization. HRI-EU also explores applications in intelligent adaptive cruise control, ergonomics for robots, and energy management. The institute collaborates with academic and industrial partners, fostering a vibrant research environment for PhD and Master students.

Squbix Digital is a global software company dedicated to providing advanced technology solutions, with a strong focus on the healthcare and fintech sectors. Their expertise spans blockchain and AI lab research and development, enabling them to deliver innovative and tailored solutions. They serve both private and public sectors, leveraging cutting-edge technologies to address complex challenges. With offices strategically located in Singapore, Sydney, New York, Dubai, and Bhubaneswar, Squbix Digital demonstrates a global reach and commitment to supporting diverse client needs across various regions. Their offerings aim to enhance operational efficiency and drive technological advancement within their target industries.

General Reasoning is an AI R&D company dedicated to building infrastructure for long horizon AI capabilities. The company focuses on developing advanced AI models that can manage complex, long-term tasks across various domains. Their work involves creating robust systems that can adapt and learn over extended periods, aiming to enhance operational efficiencies and support sustainable growth through autonomous technology deployment. Key initiatives include the release of Firehorse and research into KellyBench, demonstrating their commitment to pushing the boundaries of reinforcement learning and AI agent development. They also offer Harbor Environments on OpenReward, providing tools for practical application and research.

Romantic AI is a platform designed for users to create and interact with personalized AI companions, including girlfriends, boyfriends, and anime characters. Users can customize their AI's appearance, choosing between aesthetics, modern realism, or anime brightness, and define their personality traits such as caring, playful, or empathic. The tool aims to provide emotionally engaging interactions, whether for emotional support, flirtation, or simply a chat partner. Romantic AI emphasizes a realistic, interactive, and intimate virtual companionship experience, allowing users to craft a companion that feels closely united to their preferences without relying on pre-prepared templates.

Virtual-Human-for-Chatting is an open-source project that enables the creation of Live2D virtual humans for interactive chatting applications, built on the Unity engine. It leverages OpenCVPlusUnity for image processing and real-time face detection, allowing for dynamic virtual avatar responses. The project requires users to obtain their own API keys for services like Azure, OpenAI, and APISpace to power its conversational capabilities. This flexibility allows for customization of the AI backend. The project is designed for developers and creators interested in building virtual human interfaces, offering a foundation for integrating Live2D models with AI-driven chat functionalities within a Unity environment.