Directory
Published directory entries matching your search.
The kaggle-bestbuy big repository, hosted on GitHub under the user zygmuntz, contains code for the Best Buy competition hosted on the Kaggle data science platform. It is an open-source project that accepts contributions from GitHub users.
Lightwood is an AutoML framework that generates and customizes machine learning pipelines using a declarative JSON-AI syntax. It handles data types such as numbers, dates, categories, tags, text, arrays and multimedia formats, and includes a time-series mode. Users can override defaults or replace pipeline steps, and the framework generates Python code for the pipeline.
m2cgen is a tool that transforms trained machine learning models into native code across a wide range of programming languages including Java, C, Python, Go, JavaScript, C#, R, PHP, Dart, Haskell, Ruby, F#, and Rust, with zero dependencies. Its codebase is hosted in the BayesWitnesses GitHub repository, which includes navigation for installation, development guidance, supported languages, and supported model types.
An alternative to Supabase for AI Code editors and Vibe Coding tools.
Nanocoder is an open-source coding agent built for terminal use by a community collective rather than a corporate entity. It allows users to bring their own AI model, stores code locally on the user's machine, and does not require users to owe fees or obligations to a company. It is hosted as a public repository on GitHub.
An archived, read-only GitHub repository holding an open solution to the Home Credit Default Risk challenge. It provides code, configs and notebooks plus documented solutions using LightGBM, sklearn and XGBoost with engineered features; the README lists cross-validation and leaderboard scores for each. References to Neptune are optional and the solution can run as a plain Python script.
OpenRabbit is a free, open-source, self-hosted GitHub pull request reviewer. It analyzes PR diffs, consults a pluggable LLM provider such as Groq or OpenRouter, and posts a summary with inline comments. It runs entirely in GitHub Actions, so no server or hosting subscription is required, and code stays in the user's runner.
Kilo - Open-source AI coding assistant for VS Code, JetBrains, and the CLI.
Poirot is a native macOS companion app for Claude Code. Built with SwiftUI, it lets users browse sessions, explore diffs, and re-run commands. It also provides session analytics, usage limit gauges, conversation views, and search across sessions. The app requires no login and no analytics and works offline.
An AI-powered autonomous coding agent integrated directly into VS Code. opensource.
Zero-configuration MCP server that unifies multiple AI coding assistants (Claude Code, Cursor, Codex) through intelligent auto-discovery.
Tura is an open-source agent runtime harness that turns a task into a runtime-managed command graph, avoiding repeated model round trips in a ReAct session. The documentation describes it as a terminal-native developer tool that turns intent into verified code changes, emphasizing reading the repository first, keeping an audit trail, and proving results.
This is a curated gallery of interesting Jupyter Notebooks, organized by topic categories including introductory tutorials, programming and computer science, statistics and machine learning, data science, mathematics, physics, chemistry, biology, earth science, geo-spatial data, linguistics, and text mining.
AI Context Linter is a GitHub Action that checks AI coding context files such as CLAUDE.md, .cursorrules and AGENTS.md for security issues, structural problems and AI anti-patterns. It auto-detects context files and runs 12 rules, including detection of hardcoded API keys and leaked home directory paths. Rules cover structure, vague or conflicting instructions and file-type specifics, with configurable token limits and disabled rules.
Alpaca is a project that provides code and documentation to train Stanford's Alpaca instruction-following LLaMA models and generate associated training data. It includes details on the data release, data generation process, and fine-tuning procedures.
Awesome ADE is a curated GitHub list of open-source Agentic Development Environments, covering orchestrators, TUIs, tmux harnesses, sandboxes and the agents they run. It is maintained by KyroLabs and organized by packaging and stack layer.
A hand-picked collection of tools and resources for Vibe Coding.
Backprop is a Python library, installable via PyPi, that enables use, finetuning and deployment of machine learning models. It provides task interfaces for conversational question answering, text classification in over 100 languages, image classification, summarisation, emotion detection and text generation, and models can be finetuned with a single line of code.
DAIN (Depth-Aware Video Frame Interpolation) is a CVPR 2019 research project that explicitly detects occlusion by exploring depth cues. It develops a depth-aware flow projection layer to synthesize intermediate flows that sample closer objects than farther ones. The repository provides code, pre-trained models, testing and training instructions, and a Google Colab demo.
A supplement to Copilot and Cursor - utilizes AI for batch processing of project codes.
A DeepSeek-native terminal coding agent in Rust with OS-level sandboxing, persistent goal mode, background tasks, and verification gates.
Brood Box is a command-line tool for running coding agents inside hardware-isolated microVMs. It boots a microVM via libkrun and KVM, mounts a copy-on-write snapshot of the workspace, and allows review of each file change before it is accepted. The project is described as experimental, with APIs and behavior subject to change between releases.
Claude Engineer is an interactive command-line interface that uses Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. The framework lets Claude generate and manage its own tools, expanding its capabilities through conversation. It is available both as a CLI and a modern web interface.
Code2prompt is a command line tool that converts a codebase into a single LLM prompt. It includes source tree representation, prompt templating functionality, and token counting capabilities. Installation options include Cargo, Homebrew, and a pip SDK.
