Coding & Development

Stable-Baselines3 (SB3) is a robust open-source library offering reliable implementations of reinforcement learning (RL) algorithms built on PyTorch. It serves as the next major version of Stable Baselines, aiming to facilitate the replication, refinement, and identification of new ideas within the RL community and industry. SB3 provides a common interface, supports custom environments and policies, and includes features like Tensorboard integration, custom callbacks, and high code coverage. While designed for ease of use, it assumes some prior knowledge of RL concepts. The library is actively maintained for bug fixes and documentation updates, with newer algorithms and faster variants developed in associated repositories like SB3 Contrib and SBX (SB3 + Jax).

matsim-libs is an open-source library designed for multi-agent transport simulations, offering a comprehensive toolbox for various aspects of transportation planning and analysis. It includes modules for demand-modeling, agent-based mobility simulation (traffic flow), and re-planning. The platform also features a controller for iteratively running simulations and methods for analyzing generated output. Developers and researchers can combine or use these modules stand-alone, or replace them with custom implementations to test specific aspects of their work. The project provides resources like an issue tracker, build instructions, and example projects to facilitate development and integration.

SPTAG (Space Partition Tree And Graph) is an open-source library developed by Microsoft Research and Microsoft Bing, designed for large-scale vector approximate nearest neighbor search. It represents samples as vectors and compares them using L2 or cosine distances. SPTAG offers two primary methods: kd-tree (SPTAG-KDT) for efficient index building and balanced k-means tree (SPTAG-BKT) for superior search accuracy in high-dimensional data. Key features include fresh updates for online vector deletion and insertion, and distributed serving across multiple machines. The library is inspired by the NGS approach and uses k-nearest neighborhood graphs for enhanced connectivity, with balanced k-means trees replacing kd-trees for improved accuracy with high-dimensional vectors. It provides an iterative search process combining tree and graph searches.

Trace is a mobile application designed to simplify staying current with daily tech news. It aggregates stories, conversations, and product launches from over 50 sources, grouping them into scannable daily pulses. The app uses AI to summarize trending topics, extract key points, and create timelines, allowing users to catch up faster without sifting through numerous feeds. Users can personalize their feed by choosing topics they care about, which Trace then uses to prioritize and summarize relevant stories. This approach aims to provide a streamlined and noise-free reading experience, ensuring efficient understanding of the full story.

samples-for-ai is a comprehensive collection of deep learning samples and projects designed to help beginners get started with deep learning. It encompasses a wide range of classic deep learning algorithms and applications, supporting multiple frameworks including TensorFlow, CNTK (BrainScript and Python), PyTorch, Caffe2, Keras, MXNet, Chainer, and Theano. The project offers samples in Visual Studio solution format, making it accessible for users leveraging Microsoft Visual Studio Tools for AI or Open Platform for AI. Users can run samples locally or submit jobs to OpenPAI, providing flexibility in deployment. This open-source initiative encourages contributions and adheres to the Microsoft Open Source Code of Conduct, fostering a collaborative environment for deep learning development.

SoftSpell, formerly CodeSpell, is an AI-powered SDLC platform designed to accelerate software development and modernize legacy systems. It provides a suite of tools including ReqSpell for requirement extraction and breakdown, CodeSpell for AI-assisted code generation and documentation, and TestSpell for AI-driven test automation. The platform helps engineering teams streamline their entire SDLC, from requirements to deployment, by mapping dependencies, identifying repeated refactors, and generating reusable refactoring patterns. SoftSpell aims to improve code consistency, reduce time-to-market, and minimize risks during modernization, integrating seamlessly with existing IDEs, languages, and deployment pipelines.

simpleai is an open-source Python library designed to implement various artificial intelligence algorithms, drawing inspiration from the book "Artificial Intelligence, a Modern Approach" by Stuart Russel and Peter Norvig. It offers a more "pythonic" and maintainable approach compared to other implementations. The library includes traditional and local search algorithms, Constraint Satisfaction Problems (CSPs), and statistical classification. It also provides interactive execution viewers for search algorithms, available via web or terminal. simpleai emphasizes readability, stability, and adherence to PEP8 guidelines, making it suitable for both educational purposes and developing AI applications. Installation is straightforward via pip.

PMC-LLaMA offers the official code for developing open-source language models specifically tailored for the medical domain. The project emphasizes a two-phase training approach: initial pretraining with a vast medical corpus (like PubMedCentral papers and medical books) followed by instruction tuning using a specialized dataset. This methodology has been shown to improve the model's ability to follow user instructions compared to other medical LLMs. The repository provides various versions of PMC-LLaMA, including 7B and 13B parameter models, with links to their Hugging Face implementations. It also includes quick start guides, training scripts, and benchmark results against other prominent LLMs in medical QA tasks, demonstrating its competitive performance.

semisup-learn is a Python framework designed for semi-supervised learning, enabling the use of scikit-learn classifiers with datasets that are only partially labeled. It features implementations of Contrastive Pessimistic Likelihood Estimation (CPLE), a 'safe' framework applicable to classifiers that can yield prediction probabilities, ensuring model performance isn't worse than supervised-only training. The framework also includes Self Learning (self-training) and a wrapper for Semi-Supervised Support Vector Machine (S3VM) for comparison. CPLE is noted for its general applicability, low memory footprint, and reliance only on assumptions made by the chosen classifier, though it has high computational complexity. The project is an early-stage research endeavor.

cosine_metric_learning offers a repository with code for training a metric feature representation, specifically tailored for person re-identification tasks. This tool is intended to be used in conjunction with the deep_sort tracker, implementing the approach described in the 'Deep Cosine Metric Learning for Person Re-identification' paper. It includes functionalities to train models on datasets like Market1501 and MARS, with options for different loss modes such as cosine-softmax. Users can monitor training progress and evaluation metrics using TensorBoard, export features for testing, and freeze trained models for deployment with Deep SORT. The repository provides detailed instructions for setting up datasets, initiating training, and evaluating model performance.

Coroot is an open-source observability and APM tool designed to provide actionable insights into application performance. It leverages AI-powered Root Cause Analysis to help identify and resolve issues efficiently. The tool automatically gathers metrics, logs, traces, and profiles using eBPF, offering zero-instrumentation observability. It provides a complete Service Map, predefined inspections for auditing applications without configuration, and an Application Health Summary. Key features include SLO tracking, distributed tracing for outlier requests, log pattern analysis, seamless logs-to-traces correlation, and lightning-fast search. Coroot also offers continuous profiling to analyze CPU and memory usage spikes, deployment tracking for Kubernetes clusters, and integrated Cost Monitoring across AWS, GCP, and Azure without requiring cloud account access.

sklearn-bayes is a Python package designed for Bayesian Machine Learning, offering a scikit-learn compatible API. This allows developers and data scientists to seamlessly integrate Bayesian methods into their existing machine learning workflows. The package includes a wide array of algorithms such as ARD Models (Relevance Vector Regression/Classification, Type II Maximum Likelihood ARD Linear/Logistic Regression), Decomposition Models (Restricted Boltzmann Machines, Latent Dirichlet Allocation), Linear Models (Empirical Bayes Linear/Logistic Regression, Variational Bayes Linear/Logistic Regression), Mixture Models (Variational Bayes Gaussian/Bernoulli/Dirichlet Process/Poisson Mixture Models), and Hidden Markov Models (Variational Bayes Poisson/Bernoulli/Gaussian Hidden Markov Models). It provides probabilistic alternatives to traditional scikit-learn models, making it suitable for tasks requiring uncertainty quantification and robust model selection.

Inner Warden is an open-source, self-defending security agent for Linux and macOS servers, built in Rust. It offers autonomous threat detection and response by monitoring 40 eBPF kernel hooks, identifying attack patterns, and blocking malicious activity before it can cause damage. The tool features AI-scored confidence levels for threats, dry-run mode by default, and a hash-chained audit trail for transparency. It can block SSH brute-force attacks, credential stuffing, and web scanners, deploying honeypots to capture attacker data. Inner Warden also supports collaborative defense through a mesh network, allowing nodes to share threat intelligence and automatically block known attackers. It integrates with Telegram for real-time alerts and action approvals, and reports blocked IPs to AbuseIPDB and Cloudflare WAF.

GameSmith AI is an AI-powered tool designed for generating and animating 2D sprites, making it a valuable asset for game developers and hobbyists. Users can create custom sprites by providing text descriptions and optional reference images, offering flexibility in design. The tool also enables animation of these sprites with various motions, streamlining the asset creation process. Once generated and animated, users can download sprite sheets for direct integration into their games. Hosted on Hugging Face, GameSmith AI leverages AI, specifically Gemini, to facilitate the creation of game-ready 2D assets.

Safe-Reinforcement-Learning-Baselines is a GitHub repository dedicated to advancing safe reinforcement learning (RL) research. It serves as a central hub for exploring and comparing different safe RL baselines and benchmarks, encompassing both single-agent and multi-agent reinforcement learning scenarios. The repository is actively maintained and welcomes contributions from the community, encouraging users to add new papers or suggest improvements. It organizes its content into supported environments, safe RL baselines, surveys, theses, books, and tutorials, making it a valuable resource for researchers and practitioners in the field.

The Frontier AI Cybersecurity Observatory is a platform designed to collect and evaluate AI capabilities within the cybersecurity domain. It offers a comprehensive leaderboard that allows users to explore cybersecurity data by filtering through various benchmarks and models. This tool is crucial for understanding emerging impacts and risks associated with AI in cybersecurity. Built with Gradio, it provides an interactive interface for selecting specific aspects of cybersecurity work and inputting model or agent data for evaluation.

Am I in The Stack? is a Hugging Face Space by BigCode designed to help developers determine if their GitHub repositories are included in The Stack dataset. Users can enter their GitHub username and select a specific dataset version to perform the check. This tool is particularly useful for developers and researchers interested in understanding the provenance of code within large language model training datasets. If a user's code is found, the tool provides further information, enabling them to take appropriate action or gain insights into their code's inclusion.

Rogue is an AI Agent Evaluator & Red Team Platform designed to stress-test AI agents for both compliance and security vulnerabilities. It offers automatic evaluation against business policies and expected behaviors, allowing users to define scenarios, verify compliance, and monitor live conversations. Additionally, Rogue provides robust red teaming capabilities, simulating over 75 vulnerabilities across 12 security categories and 20 attack techniques, with CVSS-based risk scoring. It supports 8 compliance frameworks, including OWASP, MITRE, and NIST. The platform operates on a client-server architecture with TUI and CLI interfaces, supporting various protocols and offering reproducible scans for regression testing and security fixes.

LoreKeeper is a comprehensive TTRPG game prep toolkit designed for Game Masters. It allows users to upload existing lore, notes, voice memos, and videos, which the AI then learns to power various generation features. Key capabilities include generating NPCs, monsters, maps, and names, as well as creating character portraits, location maps, and scene art from your lore. The tool also offers cinematic video scene generation and the ability to produce full campaign sourcebooks in PDF format. LoreKeeper aims to transform hours of game preparation into minutes of work, supporting D&D, Pathfinder, and any other tabletop RPG system.

Niyoto Technologies Pvt. Ltd. is a deep tech startup specializing in hardware and software solutions for the defense sector. They leverage a proprietary, state-of-the-art AI platform and custom-built hardware to address diverse problems. A winner of the iDEX Defence India Startup Challenge, Niyoto supports the “Make in India” initiative. Their key products include AI software for tunnel detection, landmine and IED detection with pinpoint accuracy, and buried object/crevasse detection in challenging environments like Himalayan glaciers. The platform features powerful AI, remote operation for operator safety, rapid data acquisition, intuitive UI, autonomous flying capabilities, non-destructive data acquisition, end-to-end encryption, and near real-time analytics. Niyoto also aims to develop dual-use technologies for applications beyond defense, such as utility mapping, underground pipe leakage detection, archaeological site mapping, and disaster relief operations.

rnnlib is an open-source recurrent neural network library designed for sequence learning problems, building upon Alex Graves's foundational work. It provides implementations for tasks like online handwriting prediction and synthesis, demonstrating the capabilities of recurrent neural networks, particularly LSTM networks, in learning from sequential input. The library requires a C++11 compiler, Fortran, cmake, libcurl, automake, libtool, and texinfo for building. Auxiliary scripts in the 'utils' directory require Python packages such as SciPy, PyLab, and PIL, while experiments in 'examples' need ScientificPython for NetCDF data manipulation. It offers features like optimized LSTM layers, RMSprop optimizer, and configurable output layers with Gaussian mixtures, making it a robust tool for researchers and developers working with sequence data.

Robe is a comprehensive code assistance tool specifically designed for Ruby development within Emacs. It leverages a Ruby REPL subprocess, loading your application or gem code to provide detailed insights into loaded classes, modules, and method definitions. Key functionalities include jumping to method definitions, superclass methods, or constant definitions, displaying method documentation, and offering method and constant name completion. It also supports completion for instance and local variable names within the current file. Robe integrates with `inf-ruby` for managing the Ruby console and offers features like reloading the current file or the entire Rails environment. It's compatible with `company-mode` for enhanced completion and supports built-in Emacs completion. The tool is tested with various Ruby versions and Emacs 27.1+, primarily on GNU/Linux, with some functionality on JRuby and MS Windows.

SOVITS Voice Conversion | Overwatch 2 is an AI-powered tool designed for voice conversion, specifically allowing users to transform their voice to mimic characters from the popular game Overwatch 2. Hosted on Hugging Face, this application provides a unique way for gamers and content creators to experiment with character voices. While the live website currently indicates a build error, the tool's intent is to offer an accessible platform for voice modulation, likely leveraging advanced AI models for realistic sound transformation. It aims to cater to individuals interested in creative audio projects or enhancing their gaming experience through personalized voice effects.

DigestDiff is an AI-driven tool designed to help developers understand and communicate their codebase's evolution through its commit history. It offers three core functionalities: generating detailed codebase overviews, summarizing recent work for standups and reports, and creating streamlined release notes. The tool emphasizes privacy, requesting only read-only access to GitHub repositories and never storing generated content or accessing actual code. Users can also manually input commit history, ensuring flexibility and security. DigestDiff aims to accelerate developer onboarding, improve team communication, and automate documentation processes.