Projects

### Overview: This repository contains a curated list of awesome research papers, datasets, and software projects focused on machine learning applied to source code (MLonCode). The repository aims to provide insights into the latest advancements and applications of machine learning in software development. ### Key Features: - **Digests**: Summaries of recent research papers. - **Conferences**: Listings of relevant conferences and workshops. - **Papers**: A collection of papers on various topics related to ML on source code. - **Program Synthesis and Induction** - **Source Code Analysis and Language modeling** - **Neural Network Architectures and Algorithms** - **Embeddings in Software Engineering** - **Program Translation** - **Code Suggestion and Completion** - **Program Repair and Bug Detection** - **APIs and Code Mining** - **Code Optimization** - **Topic Modeling** - **Sentiment Analysis** - **Code Summarization** - **Clone Detection** - **Differentiable Interpreters** - **Related research** - **Posts**: Articles and blog posts related to ML on source code. - **Talks**: Talks and presentations on ML on source code. - **Software**: Tools and utilities for implementing ML on source code. - **Datasets**: Datasets used in ML on source code research. - **Credits**: Acknowledgments and contributions. - **Contributions**: Suggestions for improving the repository. - **License**: The repository is licensed under the MIT License. ### Tech Stack: The repository is written in

### Overview: Firefly 是一个开源的大模型训练工具，支持对主流大模型进行预训练、指令微调和DPO。项目旨在提供一个一站式解决方案，帮助开发者快速训练和微调各种大模型，包括但不限于 Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Llama、InternLM、Baichuan、ChatGLM、Yi、Deepseek、Qwen、Orion、Ziya、Xverse、Mistral、Mixtral-8x7B、Zephyr、Vicuna、Bloom 等。 ### Key features: - 支持预训练、指令微调、DPO，支持全量参数训练、LoRA、QLoRA 高效训练。 - 使用[Unsloth](https://github.com/yangjianxin1/unsloth)加速训练，节省显存。 - 支持绝大部分主流开源大模型，包括 Llama3、Gemma、MiniCPM、Llama、InternLM、Baichuan、ChatGLM、Yi、Deepseek、Qwen、Orion、Ziya、Xverse、Mistral、Mixtral-8x7B、Zephyr、Vicuna、Bloom 等。 - 整理并开源指令微调数据集，如 firefly-train-1.1M、moss-003-sft-data、ultrachat、Wizard

Overview: ClawRouter is an open-source smart LLM router designed for autonomous agents, providing a wallet-independent, USDC-based local routing system that significantly reduces AI API costs by up to 84%. It routes requests to the cheapest model in under 1ms, making it the only LLM router an agent can pay for autonomously. Key features: - Agent-native - Local routing - USDC payments via x402 - Sign up at user.blockrun.ai - 15 dimensions analysis - 88% savings compared to baseline Tech stack: TypeScript Why it matters: ClawRouter simplifies agent operations by eliminating the need for traditional account signups and credit card payments, offering a wallet-independent, cost-effective solution for autonomous agents.

Overview: Mycroft Core is the core component of the Mycroft AI platform, serving as the foundation for all voice assistant functionalities. Key features: - Microphone and audio processing - Speech-to-Text (STT) and Text-to-Speech (TTS) capabilities - Skill management and execution - Configuration and management of Mycroft devices and accounts Tech stack: Python Why it matters: Mycroft Core is essential for the functionality and performance of Mycroft AI, providing the core processing and interaction capabilities that enable the voice assistant to understand and respond to user commands.

### Overview: Scikit-image is a powerful Python library for image processing, providing a comprehensive suite of tools for tasks such as filtering, segmentation, and feature extraction. It is widely used in scientific research, data analysis, and machine learning applications. ### Key Features: - **Image Processing Tools:** A wide range of image processing techniques including filtering, segmentation, and feature extraction. - **Integration with Scientific Python:** Built on top of the Scientific Python ecosystem, making it easy to integrate with other scientific libraries. - **Community and Documentation:** Active community support and detailed documentation, including forums and a user forum. ### Tech Stack: Python ### Why it Matters: Scikit-image is essential for researchers and developers working in fields such as computer vision, medical imaging, and data science. Its comprehensive set of tools and community support make it a go-to library for image processing tasks across various applications.

### Overview: Osmedeus is a modern security orchestration engine designed to simplify complex workflow automation. It provides declarative YAML workflows, distributed execution, and a rich function library for both beginners and experts. With features like event-driven scheduling, agentic LLM steps, and cloud infrastructure, Osmedeus ensures powerful, composable automation without compromising security. ### Key Features: - **Declarative YAML Workflows**: Define pipelines with hooks, decision routing, module exclusion, and conditional branching. - **Distributed Execution**: Redis-based master-worker pattern with queue system, webhook triggers, and file sync across workers. - **Rich Function Library**: 80+ utility functions including nmap integration, tmux sessions, SSH execution, TypeScript/Python scripting, SARIF parsing, and CDN/WAF classification. - **Event-Driven Scheduling**: Cron, file-watch, and event triggers with filtering, deduplication, and delayed task queues. - **Agentic LLM Steps**: Tool-calling agent loops with sub-agent orchestration, memory management, and structured output; plus ACP subprocess agents (Claude Code, Codex, OpenCode, Gemini). - **Cloud Infrastructure**: Provision and run scans across DigitalOcean, AWS, GCP, Linode, and Azure with cost controls and automatic cleanup. - **Rich CLI Interface**: Interactive database queries, bulk function evaluation, workflow linting, progress bars, and comprehensive usage examples. - **REST API & Web UI**: Full API server with webhook triggers, database queries, and embedded dashboard for visualization. ### Tech Stack: Go

### Overview: This repository is a curated collection of GPT agents designed for cybersecurity, focusing on both offensive and defensive strategies. It aims to provide a comprehensive set of tools and knowledge for security professionals. ### Key Features: - **MagicUnprotect**: Interacts with the Unprotect DB to retrieve malware evasion techniques. - **GP(en)T(ester)**: Offers guidance for pentesting. - **Threat Intel Bot**: Provides the latest APT threat intelligence. - **Vulnerability Bot**: Analyzes and provides insights into vulnerabilities and secure coding practices. - **SourceCodeAnalysis**: Analyzes and answers questions about project source code. - **Web Hacking Wizard**: Clarifies web security topics with interactive questions. - **ChadGPT**: Provides executables like gdb, curl, and strace. - **CyberGPT**: Offers the latest CVE details. - **Cyber Mentor**: A cybersecurity mentor for beginners. - **Cyber Security Career Mentor**: Practical advice for cybersecurity careers. - **CyberGuard**: A cybersecurity advisor for home and small businesses. - **CatEye**: AI cybersecurity best practices advisor for C-level executives. - **SOC Copilot**: Cybersecurity expert with keyword-based guidance. - **HackTricksGPT**: A knowledgeable cybersecurity professional. - **MITREGPT**: Provides quality cybersecurity advice and tips. ### Tech Stack: The repository is primarily written in Python, utilizing libraries such as OpenAI's GPT models and the necessary dependencies for interacting with the knowledge sources. ### Why It Matters: This repository serves as a valuable resource

### Overview: Practical RL is an open course on reinforcement learning in the wild, taught on-campus at HSE and YSDA, and maintained for online students. The course covers essential concepts and practical applications of reinforcement learning, focusing on real-world problems and providing ample opportunities for deeper exploration. ### Key Features: - **Lectures and Seminars:** Comprehensive lectures and seminars on reinforcement learning, including practical applications and advanced techniques. - **Hands-On Labs:** Interactive labs that allow students to "feel" reinforcement learning concepts through practical problem-solving. - **Practical Problems:** Real-world problems from openAI gym and other environments, ensuring relevance and applicability. - **Git Contributions:** Encourages contributions to improve the course, making it a friendly environment for both on-campus and online students. ### Tech Stack: - **Primary Language:** Jupyter Notebook ### Why It Matters: - **Real-World Applications:** The course focuses on practical reinforcement learning problems, ensuring that students can apply their knowledge to real-world scenarios. - **Hands-On Experience:** Interactive labs and practical problem-solving help students "feel" the concepts, making the learning experience more engaging and effective. - **Community Engagement:** Encourages contributions to improve the course, fostering a supportive and collaborative learning environment. ### Repository: - **GitHub Stars:** 6596 - **Description:** A course in reinforcement learning in the wild - **Primary Language:** Jupyter Notebook ### Additional Materials: - **RL Reading Group:** A community for discussing and learning about reinforcement learning. - **FAQ:** Resources for course

### Overview: Skills Manager is a lightweight desktop application designed to manage and synchronize AI agent skills across a wide range of coding tools, including Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more. It simplifies the process of installing, deploying, and managing skills across multiple environments, ensuring a unified and efficient workflow. ### Key Features: - **Unified Skill Library**: Skills can be installed from Git repositories, local folders, `.zip` archives, or the skills.sh marketplace, all stored in a central repository located at `~/.skills-manager`. - **Marketplace**: Browse and discover popular skills using keyword search. - **Agent Workspace**: Agents can manage skills directly, avoiding the need to write to agent-specific folders, preserving sources, presets, and update tracking. - **Presets**: Skills can be grouped into presets, which can be activated or deactivated in any workspace. - **Global Workspace**: Each agent has a dedicated workspace listing all skills installed globally, ensuring a consistent view across all agents. - **Project Workspaces**: Project-specific workspaces allow managing skills for individual projects, keeping the view up-to-date with the agent's current setup. ### Tech Stack: Rust ### Why It Matters: Skills Manager streamlines the management of AI agent skills across multiple coding tools, making it easier to maintain and update skills without disrupting the workflow. By centralizing skills and providing a unified view, it simplifies the process of installing, deploying, and managing skills across different environments, ensuring a more efficient and consistent workflow.

### Overview: ml5.js is a friendly machine learning library designed for artists, creative coders, and students. It provides access to machine learning algorithms and models in the browser, built on top of TensorFlow.js, making it approachable for a broad audience. ### Key Features: - **ML5.js** is designed to be user-friendly and accessible, making it ideal for artists, creative coders, and students. - **Supports TensorFlow.js**: Built on top of TensorFlow.js, it provides a seamless integration for machine learning tasks. - **Code Examples and Tutorials**: Offers detailed examples and tutorials to help users understand and implement machine learning concepts. - **Ethical Computing**: Emphasizes ethical considerations such as bias in data, stereotypical harms, and responsible crowdsourcing. - **Inspired by Processing and p5.js**: Built on the principles of these libraries, making it easy to learn and use. - **Code of Conduct**: Establishes a welcoming and friendly environment for all contributors and users. ### Tech Stack: JavaScript ### Why it Matters: ml5.js aims to make machine learning accessible and ethical, making it a valuable tool for artists, creative coders, and students. Its friendly approach and support for ethical computing make it a valuable addition to the machine learning community.

Overview: This repository is a comprehensive list of AI/ML & Data Science jobs for college students, updated daily. It includes positions for internships and new graduates in the USA and internationally, focusing on FAANG+ companies, Quantitative roles, and other relevant fields. Key features: - Comprehensive job listings for AI/ML & Data Science positions - Updated daily, prioritizing recent postings - Focus on FAANG+ companies, Quantitative roles, and other relevant fields Tech stack: GitHub Why it matters: This repository provides valuable resources for college students looking to secure internships and new graduate positions in the rapidly growing field of AI/ML and Data Science. Repository: speedyapply/2027-AI-College-Jobs GitHub stars: 6582

### Overview: Argos Translate is an open-source offline translation library written in Python, providing a robust solution for translating between various languages. ### Key Features: - Supports multiple languages including Arabic, Azerbaijani, Basque, Catalan, Chinese, Czech, Danish, Dutch, English, Esperanto, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Kyrgyz, Korean, Malay, Persian, Polish, Portuguese, Portuguese (Brazil), Russian, Slovak, Spanish, Swahili, Swedish, Turkish, Ukrainian, Urdu, and more. - Manages pivoting through intermediate languages to translate between languages that don't have direct translations installed. - Compatible with Python libraries, command-line, and GUI applications. - Supports installing language model packages, which are zip archives with a ".argosmodel" extension containing the data needed for translation. ### Tech Stack: Python ### Why It Matters: Argos Translate is a powerful tool for developers looking to integrate translation capabilities into their projects without relying on cloud-based services. Its ability to handle language pivoting and its support for pre-trained models make it a versatile solution for both offline and online applications.

### Overview: NLP.js is an open-source library designed for building natural language processing (NLP) applications in Node.js. It offers a wide range of functionalities including language detection, sentiment analysis, entity recognition, and more, with support for multiple languages and plugins for enhanced functionality. ### Key Features: - **Language Detection**: Determines the language of a given phrase. - **Levenshtein Distance**: Calculates the minimum number of single-character edits required to change one phrase into another. - **Substring Matching**: Finds the best substring of a string with the lowest Levenshtein distance to a given pattern. - **Stemmers and Tokenizers**: Provides stemmers and tokenizers for various languages. - **Sentiment Analysis**: Analyzes phrases for sentiment, including negation support. - **Named Entity Recognition**: Recognizes named entities in text, supporting multi-language and similar string handling. - **Classifier**: Classifies utterances into predefined intents. - **Natural Language Generation**: Manages answers for a given utterance, including entity extraction, intent classification, and sentiment analysis. - **Support for 40 Native and 104 BERT-supported Languages**: Includes support for various languages, including fantasy languages. - **Plugin System**: Allows customization and extension of the library with plugins. - **Container System**: Manages plugins, settings, and pipelines for a more organized and modular approach. - **Connector System**: Provides connectors for integrating with other platforms like Microsoft Bot Framework and Direct Line. ### Tech Stack: Node.js ### Why It Matters: NLP.js simplifies the

Overview: Julep is a framework for building durable, composable AI agents using Python. It allows agents to crash and resume, retry safely, and explain every step through derived projections. Key features: - Composable, durable dataflows - Flows that can crash and resume, retry safely, and explain every step - Built on the `@flow` surface for defining Python functions as graph steps - Supports `@tool`, `@pure`, `@think`, `@tool`, `@flow`, `@each`, `@reschedule`, and `@retry` decorators - Provides a `deploy` function to freeze the tool and reasoner surface - Includes a `dry_run` function to execute locally with deterministic fake reasoners Tech stack: Python Why it matters: Julep simplifies the creation of AI agents by providing a robust, composable framework that ensures dataflows are reliable and explainable, making it easier to develop and maintain complex AI systems. Repository: julep-ai/julep GitHub stars: 6576

Overview: OpenMVG is an open-source library for Multiple View Geometry, providing tools for 3D computer vision and Structure from Motion. It is designed to be easy to read, learn, modify, and use, with a strong focus on simplicity and maintainability. Key features: - Multiple View Geometry (MVG) library - Image manipulation and feature processing - Feature tracking and camera models - Multiple-view geometry algorithms - Structure-from-Motion (SfM) algorithms - Robust estimation techniques - State-of-the-art and classic algorithms Tech stack: C++ Why it matters: OpenMVG simplifies reproducible research in 3D reconstruction from images/photogrammetry, making it easier to build and trust larger systems. The library is designed for ease of use, with a strict test-driven development and samples that allow for accurate implementation of state-of-the-art and classic algorithms.

### Overview: AdversarialNetsPapers is a comprehensive collection of papers and resources related to Generative Adversarial Networks (GANs), focusing on image translation, synthesis, and other applications. This project serves as an invaluable resource for developers and researchers interested in the latest advancements in GANs. ### Key Features: - **Image Translation**: Techniques for generating images from one domain to another. - **Facial Attribute Manipulation**: Altering facial attributes in images. - **Face Swap and Reenactment**: Creating realistic face swaps and reenactments. - **Gaze Correction and Redirection**: Correcting gaze direction in images. - **Person Image Synthesis**: Generating new images of people. - **Image Inpainting**: Reconstructing missing parts of images. - **Scene Generation**: Creating realistic scenes from images. - **Image Blending**: Combining multiple images into a single image. - **Re-identification**: Enhancing image recognition. - **Super-Resolution**: Enhancing image resolution. - **De-Occlusion**: Removing occlusions from images. - **Semantic-Segmentation**: Segregating images into semantic classes. - **Object-Detection**: Detecting objects in images. - **Landmark-Detection**: Locating key points in images. - **Video-Prediction-and-Generation**: Generating videos based on image sequences. - **Shadow Detection and Removal**: Removing shadows from images. - **Makeup**: Enhancing makeup in images. - **3D**: Applications in 3D image processing. - **Improving Classification

Overview: The Agent Starter Pack is a Python package designed to quickly deploy AI agents on Google Cloud. It includes production-ready templates, CI/CD, observability, and security features. Key features: - Production-ready AI agent templates - Vertex AI evaluation and interactive playground - Cloud Run or Agent Engine deployment - CI/CD integration - Built-in monitoring and observability Tech stack: Python Why it matters: It streamlines the process of deploying AI agents on Google Cloud, making it easier and faster for developers to get started with AI on the platform. Repository: GoogleCloudPlatform/agent-starter-pack GitHub stars: 6567

### Overview: Anti Slop is a rulebook designed to filter out generic AI-generated UI designs, text, and code, ensuring that an AI coding agent adheres to specific guidelines. It serves as a tool for developers to maintain quality and uniqueness in their projects. ### Key Features: - **Anti-Slop Rules**: A set of rules that prevent AI-generated content from being generic and generic. - **Filter vs. Style Guide**: Unlike a style guide, Anti Slop focuses on removing slop and filler content rather than prescribing design elements. - **User-Friendly**: The rules are designed to be simple and easy to follow, without imposing strict design constraints. ### Tech Stack: JavaScript ### Why It Matters: Anti Slop ensures that AI-generated content is tailored and professional, providing a clean and directed output that aligns with human standards. This approach helps developers maintain a high level of quality and originality in their projects, making them more appealing and effective in their intended use cases. Repository: miqdadbadjuber/anti-slop Primary Language: JavaScript GitHub Stars: 6568

### Overview: Airweave is an open-source context retrieval layer designed for AI agents and RAG systems. It seamlessly integrates with various applications, tools, and databases, ensuring continuous data synchronization and unified access through a context-aware interface. ### Key Features: - **Context Retrieval Layer**: Connects to your applications, tools, and databases, providing up-to-date and relevant context. - **Unified Search Interface**: Enables AI agents to retrieve context from multiple sources in a single request. - **Open-Source and Cloud-Ready**: Built on Python and compatible with Docker, making it easy to deploy and scale. ### Tech Stack: Python ### Why It Matters: Airweave simplifies the process of integrating AI with existing systems, making it easier to access and utilize context-rich data for informed decision-making.

Overview: ANUS is a free coding agent that runs on the smartest free models available today, providing a terminal-based experience similar to paid services. It continuously refreshes its list of available models and models that have answered recently. Key features: - Runs on the smartest free models available - Continuously updates its list of available models and models that have answered recently - Supports multiple free models for fallbacks Tech stack: JavaScript Why it matters: ANUS offers a free alternative to paid coding agents, providing a terminal-based experience with the intelligence of the latest free models, making it accessible and useful for developers without the financial burden of a paid subscription.