AI Agents & Automation

Sagittarius is an innovative open-source tool designed for exploring the voice and video capabilities of GPT-4 and Gemini models. It provides an online platform where users can interact with these advanced AI models using both voice and video inputs, offering a real-time exploration of multimodal AI. The tool is accessible directly through a web browser, eliminating the need for any installation. Users simply require an API key from either OpenAI (with access to the gpt-4-vision-preview model) or Gemini to get started. Sagittarius is noted for its speed and support for multiple voices, making it a versatile option for developers and enthusiasts interested in cutting-edge AI interactions.

IndoNLU is a comprehensive collection of Natural Language Understanding (NLU) resources specifically designed for Bahasa Indonesia. It features 12 distinct downstream tasks, offering a robust benchmark for evaluating Indonesian language processing models. The project provides code to reproduce results and includes large pre-trained IndoBERT and IndoBERT-lite models, which were trained on an extensive 4-billion-word corpus (Indo4B) comprising over 20 GB of text data. Developed through a collaboration between universities and industry partners, IndoNLU also offers access to the Indo4B dataset and various FastText models. It serves as a vital resource for researchers and developers working on Indonesian NLP.

InternAgent 1.5 is a sophisticated autonomous system designed for end-to-end scientific discovery, encompassing both Algorithm Discovery and Empirical Discovery. Building upon InternAgent 1.0, it structures scientific inquiry into three interconnected subsystems: Generation (hypothesis construction via deep research), Verification (methodological evaluation through solution refinement), and Evolution (evidence-driven refinement using long-horizon memory). This framework achieves leading performance on scientific reasoning benchmarks like GAIA, HLE, GPQA, and FrontierScience, demonstrating sustained autonomous optimization over extended discovery cycles. It supports diverse workflows, from agent memory and reinforcement learning to dry-lab simulations and wet-lab experimentation, across Physical, Biological, Earth, and Life Sciences.

SOMAS implements a Multi-Agent System (MAS) framework specifically designed for human-machine collaborative crisis response. It leverages vision-language models (VL) and reinforcement learning (RL) to significantly enhance safety and reliability in critical situations. The framework features real-time task execution with modular task chains, built-in safety rules, and human oversight. It also includes a simulation training system with an experience replay library for risk prediction and optimization, alongside a dynamic trust mechanism that balances task utility and safety constraints through RL. SOMAS offers a dual-mode architecture for online execution and offline simulation, and has developed the first fine-tuned safe LLM and training dataset for emergency scenarios, demonstrating improved helpfulness and reduced risk response rates.

Stephanie is an open-source platform designed for building voice-controlled applications and automating daily tasks, mimicking the functionality of a virtual assistant. It provides a flexible framework for developers to create and customize their own voice-controlled systems. The platform emphasizes its open-source nature, allowing for community contributions and extensive modification. Key features include voice control, task automation, and an intent prediction algorithm called Sounder. It supports Python and offers detailed documentation for installation, configuration, and usage, making it suitable for technical users looking to implement custom voice solutions.

SQLite-Vector is a cross-platform, ultra-efficient SQLite extension designed to integrate vector search directly into embedded databases. It operates seamlessly across iOS, Android, Windows, Linux, and macOS, utilizing minimal memory (defaulting to just 30MB). This tool eliminates the need for complex preindexing, allowing for immediate vector search on existing data stored as BLOBs in ordinary SQLite tables. It supports various vector types including Float32, Float16, BFloat16, Int8, UInt8, and 1Bit, alongside highly optimized distance functions like L2, Cosine, and Dot Product. SQLite-Vector is ideal for Edge AI applications, enabling offline, privacy-preserving AI workloads with real-time performance directly on devices.

Hellbender Inc. specializes in crafting cutting-edge Computer Vision solutions, offering advanced AI vision systems and industrial AI cameras. They provide mission-critical hardware and software infrastructure for AI-driven perception systems, engineered for the edge in autonomy, robotics, and industrial applications. Their services include design, development, and turn-key manufacturing, with a focus on producing high-quality hardware in America. Hellbender also offers Computer Vision as a Service (CVaaS) for bespoke systems, addressing complex problems. They are a Raspberry Pi Design Partner and emphasize their commitment to employees, community, and the environment.

Shaan.ai is a premium, human-sounding domain name available for purchase, specifically designed for AI assistants, conversational agents, and consumer-facing intelligent products. The name evokes a friendly, confident, and approachable feel, ideal for brands aiming to build trust and long-term user relationships. Its simplicity and phonetic clarity provide strong global appeal across various applications including consumer, education, and support. Originating from South Asian languages, "Shaan" means pride, dignity, or grace. Paired with the .ai extension, it clearly signals an artificial intelligence persona, positioning a brand as capable, personable, and culturally resonant. The purchase process is secure, with Atom holding payments until the domain transfer is complete, and offers flexible payment plans including installments.

LibKGE is a PyTorch-based library designed for the efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). Its primary goal is to foster reproducible research and facilitate meaningful comparisons between KGE models and training methods. The library is highly configurable, easy to use, and extensible, providing clean implementations of various training strategies, hyperparameter optimization techniques, and evaluation metrics. It supports common KGE models like RESCAL, TransE, DistMult, ComplEx, and ConvE, with explicit exposure of all parameters via well-documented configuration files. LibKGE also includes GraSH for efficient multi-fidelity hyperparameter optimization on large-scale KGE models.

Keepsake is a Python library designed for version control in machine learning, enabling developers to track and manage their experiments efficiently. It automatically uploads files and metadata, including hyperparameters, training data, weights, metrics, and Python dependencies, to Amazon S3 or Google Cloud Storage. Users can retrieve this data via a command-line interface or within a notebook environment, facilitating experiment analysis and replication. Keepsake supports various ML frameworks like Tensorflow, PyTorch, and scikit-learn, storing data as plain files for easy integration into production systems. It also offers features for comparing experiments, committing code to Git after the fact, and loading models for production use.

TaskSync is a Copilot chat sessions orchestrator designed to streamline AI-assisted development workflows. It offers three primary options for integrating feedback loops: a VS Code Extension with a smart prompt queue, a terminal-based task agent protocol, and an MCP server for real-time feedback. The VS Code extension features smart queue mode, autopilot for autonomous agent work, agent orchestration, and remote access. It supports file, folder, tool, and context references, along with image paste support. TaskSync aims to reduce premium AI requests by enabling efficient task management and human-in-the-loop feedback, ensuring responsible AI usage and compliance with GitHub's terms of service.

Grizzly AI leverages AI agents to significantly reduce the time and effort required to respond to Requests for Proposals (RFPs), bids, and tenders. The platform helps teams quickly understand the scope, scoring criteria, and requirements of a tender by mapping the tender pack. It then drafts responses by matching existing content (past bids, case studies) to the new questions, ensuring relevance and consistency. Before submission, Grizzly AI scores answers against evaluation criteria, flags missing evidence, and identifies areas for improvement. Post-submission, it integrates feedback to continuously refine the content library, making each subsequent bid more efficient and effective. This ensures senior staff can focus on won projects, allows for bidding on more opportunities, and ultimately increases win rates by aligning responses with evaluator expectations.

Dalitics specializes in AI and predictive analytics, transforming real-world data into actionable insights to drive business growth and maximize ROI. The company offers comprehensive support to businesses of all sizes, providing expertise in predictive analytics, customer insights, and tailored intricate analyses using both financial and non-financial data. Their approach is personalized, involving issue identification, objective definition, data gathering and privacy, AI model construction and training, and continuous feedback loops for improvement. Key solutions include AI models for churn prediction, cross-selling and upselling, credit scoring systems for Romanian companies, and the Elcano Financial Health Check for in-depth financial analysis.

JourneoAI is an AI-powered travel planning platform designed to create personalized itineraries quickly and efficiently. Users can input their budget, desired vibe (e.g., romantic, adventure, foodie), and destination to receive a full trip plan in seconds. The tool provides daily lineups of restaurants, bars, hidden spots, and activities, all balanced for time and budget. JourneoAI also offers real-time flight and hotel suggestions from trusted partners like Expedia and Travelpayouts, allowing users to book directly. It supports quick regeneration of itineraries if plans change and can adapt to dietary needs, allergies, or mobility requirements. The platform works directly in the browser, eliminating the need for app downloads, and caters to solo, couples, or family travel styles.

lexvec is an open-source implementation of the LexVec word embedding model, designed to achieve state-of-the-art results in various Natural Language Processing (NLP) tasks. It functions similarly to other popular word embedding models like word2vec and GloVe. The tool offers pre-trained vectors derived from Common Crawl data, available in both subword and standard LexVec formats, with options for cased and lowercased words. Users can compute vectors for out-of-vocabulary (OOV) words using a binary model. LexVec supports both in-memory and external memory training, making it adaptable for large corpora. It also incorporates subword information through character n-grams, enhancing its performance. The project includes evaluation metrics against other models like fastText, word2vec Skip-gram, and GloVe, demonstrating its competitive accuracy.

GROWL is the first physical AI coach designed to bring a full-size, human-form AI entity into the home. It moves, reacts, and speaks to users in real time, offering a supportive and fully embodied coaching experience that trains with you, not at you. This innovative system combines advanced hardware, software, and content to create an interactive, personalized boxing and fitness experience. Key features include immersive projection of a virtual coach, interactive sensing for precise punch tracking, AI-powered 3D motion tracking for form correction, and advanced gaming power using Unreal Engine 5 for gamified workouts. The revolutionary multi-layer composite boxing bag provides optimal resistance for all skill levels, while dynamic lighting and sound enhance the immersive atmosphere.

Tldr AI Summarizer is an intelligent reading companion designed to instantly summarize any article found on the web. This tool helps users save valuable time by providing concise summaries, allowing them to stay informed without sifting through lengthy content. It's particularly useful for cutting through clickbait and quickly grasping the main points of an article. Currently, Tldr AI is available as a web extension, with beta waitlists open for Chrome, Android, and macOS Safari versions, indicating future platform expansion.

Bielik-7B-Instruct-v0.1 is an instruct fine-tuned version of the Bielik-7B-v0.1 model, designed specifically for Polish language interactions. This application allows users to provide text messages and receive generated text responses. It offers flexibility by enabling users to adjust key parameters such as temperature and maximum response length, which helps in controlling the creativity and verbosity of the AI's output. The tool is suitable for various applications including content generation, educational assistance, and chatbot development, making it a versatile option for those working with Polish language AI.

Vorto offers transformational supply chain automation, leveraging AI to integrate procurement, operations, and logistics. The platform aims to eliminate non-productive time (NPT) and significantly cut delivered costs. It predicts demand, procures products from supplier networks, and automatically schedules logistics and carriers. Vorto reacts in microseconds to parameter changes, re-routing drivers and re-scheduling deliveries to recalibrate supply chain imbalances at the lowest cost. The Autopilot feature allows businesses to set and forget, configuring for any payload and business, with carriers auto-tendered and dispatched. This system helps improve driver utilization, reduce truck usage, and decrease CO2 emissions, ultimately creating stability and efficiency across the entire supply chain.

Deep Java Library (DJL) is an open-source, high-level, and engine-agnostic Java framework for deep learning. It empowers Java developers and data scientists to easily build, train, and deploy deep learning models without needing to be machine learning experts. DJL offers a native Java development experience, allowing users to leverage their existing Java expertise and preferred IDEs. A key differentiator is its engine-agnostic nature, providing flexibility to switch between deep learning engines like MXNet, TensorFlow, and PyTorch. DJL also includes automatic CPU/GPU choice for optimal performance and an ergonomic API designed to guide users through deep learning tasks, making it simple to integrate models into Java applications.

llm_benchmarks is an open-source repository offering a comprehensive collection of benchmarks and datasets specifically designed for evaluating Large Language Models (LLMs). It covers a wide array of assessment areas, including knowledge and language understanding with benchmarks like MMLU, GLUE, and Natural Questions. The repository also includes resources for evaluating reasoning capabilities through datasets such as GSM8K, DROP, and AGIEval. Furthermore, it addresses grounding, abstractive summarization, and content moderation with benchmarks like ACI-BENCH, MS-MARCO, and ToxiGen. This tool is invaluable for researchers and developers looking to rigorously test and compare the performance of different LLMs across diverse linguistic and cognitive tasks.

Eagle X5 13B Chat is a vision-centric, high-resolution multimodal Large Language Model designed to provide detailed responses by integrating both text and image inputs. This advanced model enhances multimodal perception through the strategic use of various vision encoders and diverse input resolutions. It further improves performance by employing channel concatenation, allowing for a more robust understanding and generation of content. The tool is available for use under the CC-BY-NC-SA-4.0 license, making it accessible for non-commercial applications. Its ability to process and combine visual and textual information makes it suitable for tasks requiring a comprehensive understanding of complex data.

ML.NET is an open-source and cross-platform machine learning (ML) framework specifically designed for .NET developers. It empowers users to easily build, train, deploy, and consume custom ML models directly within their .NET applications, eliminating the need for prior machine learning expertise or proficiency in other languages like Python or R. The framework supports data loading from various sources, offers extensive data transformation capabilities, and includes a wide array of ML algorithms. Developers can train models for diverse scenarios such as classification, forecasting, and anomaly detection. ML.NET also provides extensibility by allowing the consumption of both TensorFlow and ONNX models, broadening its application scope.

MADDPG offers a PyTorch implementation of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, specifically tailored for multi-agent reinforcement learning in environments with both cooperative and competitive elements. This tool corresponds to the research paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments." It includes a quick start guide for running simulations, such as testing the algorithm on a 'simple_tag' scenario with pretrained models. The implementation allows for training agents, like predators catching prey, within the Multi-Agent Particle Environment (MPE). Users can also modify environment settings, such as switching between sparse and dense reward structures, to suit their experimental needs.