#python
ROMA is an open-source framework that helps you build smart multi-agent AI systems by breaking big, complex tasks into smaller parts that agents can work on at the same time. It uses a clear, step-by-step process where tasks are split, solved, and combined, making it easy to understand and fix problems. You can connect any AI model or tool, and it supports secure code execution and fast data access. This means you can create powerful, flexible AI agents for research, analysis, or other tasks, with full control and transparency over how they work, saving you time and effort in solving complex problems.
https://github.com/sentient-agi/ROMA
#python
BlenderMCP connects Blender with Claude AI, letting you control 3D modeling and scene creation using simple text commands. You can create, modify, and delete objects, apply materials, adjust lighting, and even run Python scripts inside Blender through AI. It also supports downloading assets from Poly Haven and generating models with Hyper3D Rodin. This makes 3D design faster, easier, and more interactive, especially if you want to break down complex tasks or work step-by-step. It works on multiple platforms and integrates with tools like Visual Studio Code and Cursor for smooth workflows. Just install the Blender addon and set up the MCP server to start using AI-assisted 3D modeling.
https://github.com/ahujasid/blender-mcp
#python
XLeRobot is a low-cost, easy-to-assemble household robot platform starting at about $660, designed for general manipulation tasks with dual arms and mobile capability. It supports various camera options and can be controlled via keyboard, Xbox controller, or VR devices without Wi-Fi, offering zero latency. The project provides detailed guides for buying parts, 3D printing, assembly, and software setup, making it accessible for robotics enthusiasts and learners. This robot helps you explore embodied AI affordably, enabling hands-on experience with autonomous household tasks and robotics research, all backed by active development and community support.
https://github.com/Vector-Wangel/XLeRobot
#python
Elysia is an open-source Python framework that uses decision trees to help AI agents choose the best tools and actions based on context, making AI smarter and more efficient. It connects easily to Weaviate databases to search and display your data in clear, useful formats like product cards or tables. You can install it quickly with Python, customize it with your own data and models, and even run a demo online. This means you get an AI system that not only finds information but also reasons about it and shows it in ways that make sense, saving you time and improving your data interactions.
https://github.com/weaviate/elysia
#python
You can improve your Wazuh security system by using advanced detection rules from SOCFortress, which are more accurate and detailed than the default ones. These rules cover many integrations like Sysmon, Office365, Microsoft Defender, and more, helping you detect threats better and faster. You can easily install them with a script on your Wazuh Manager. This strengthens your network security by catching more threats early and adapting to new attacks, making your cybersecurity more effective and easier to manage. Plus, it’s open source and free to use, so you can customize and expand it as needed.
https://github.com/socfortress/Wazuh-Rules
#python
Chatterbox TTS is a powerful, open-source text-to-speech model that can clone voices with just a few seconds of audio and lets you control emotional intensity to make speech sound natural or dramatic. It works fast enough for real-time use, like virtual assistants or games, and produces very clear, stable speech. It also includes a hidden watermark in every audio file to help track and ensure responsible use. You can easily install and use it in Python, and it supports voice conversion to change one voice into another. This helps you create expressive, personalized speech for videos, games, or AI projects without needing expensive software.
https://github.com/resemble-ai/chatterbox
#python
Fooocus is a free, offline, and open-source AI image generator that creates high-quality images from simple text prompts without needing complex settings. It uses the powerful Stable Diffusion XL model and offers easy installation with minimal clicks. Fooocus includes advanced features like inpainting, outpainting, face swapping, and prompt expansion to improve image quality and creativity. It supports multiple presets (general, anime, realistic) and works on Windows, Linux, and Mac with moderate hardware requirements (4GB GPU VRAM minimum). This makes it accessible for users who want professional-level AI image generation without technical hassle or online dependency.
https://github.com/lllyasviel/Fooocus
#python
WhisperLiveKit lets you convert speech to text in real-time directly in your browser, with speaker identification, using advanced AI models designed for low delay and high accuracy. It processes audio intelligently to avoid cutting off words, supports multiple users, and reduces processing when no voice is detected. You can easily install it, run a server, and start transcribing live speech instantly. It also offers options for speaker diarization, multiple languages, and secure HTTPS setup. This helps you capture meetings, assist hearing-impaired users, transcribe podcasts, or analyze calls quickly and locally without sending data to the cloud.
https://github.com/QuentinFuxa/WhisperLiveKit
#python
Verifiers is a tool that helps create environments for training large language models (LLMs) using reinforcement learning (RL). It includes features like async GRPO training and integration with other frameworks. This tool is useful for building and evaluating LLMs in various tasks, such as creating synthetic data or using tools within models. It supports both single-turn and multi-turn interactions, making it versatile for different applications. By using Verifiers, users can efficiently train and evaluate LLMs, which can improve their performance and accuracy in tasks like answering questions or generating text.
https://github.com/willccbb/verifiers
#python
Related Website Sets (RWS) let companies declare which of their websites are related, so browsers like Chrome can allow limited sharing of cookies across these sites. This helps keep features like staying signed in or remembering your shopping cart working smoothly when you move between related sites, even as browsers block most third-party cookies to protect your privacy. By submitting their sites as a set, companies ensure a better, more seamless experience for you without losing privacy protections. This system balances user convenience with privacy by controlling when cross-site data is shared.
https://github.com/GoogleChrome/related-website-sets
#python
Nemo RL is a powerful and scalable library that helps you efficiently train and fine-tune large AI models, from small ones on a single GPU to huge models with over 100 billion parameters using thousands of GPUs. It integrates easily with Hugging Face models and uses NVIDIA’s Megatron Core for fast, optimized training with advanced parallelism, making it ideal for very large models and long sequences. It supports various reinforcement learning algorithms and fine-tuning methods, offers flexible resource management with Ray, and provides detailed, user-friendly documentation and examples. This means you can train state-of-the-art AI models faster and more reliably, even at massive scale, with less hassle.
https://github.com/NVIDIA-NeMo/RL
#python
Terminal-Bench is a tool that tests how well AI agents perform real tasks in a terminal, like compiling code or setting up servers, all on their own. It includes a set of tasks with instructions and tests, plus a system that connects AI models to a safe terminal environment. You can install it easily with pip and run tests to see how good your AI is at practical, real-world jobs. This helps you build, compare, and improve AI agents for coding and system tasks, making your AI development more reliable and measurable. You can also contribute new tasks or join a leaderboard to track progress.
https://github.com/laude-institute/terminal-bench