Directory
Published directory entries matching your search.
h5i is a workspace for securing web applications through two approaches: finding vulnerabilities with AI agents and proving correctness with formal verification. It provides AI agents a toolkit for browser automation, HTTP traffic manipulation and reconnaissance, and includes h5i-app, an Axum-based Rust framework for verification with Lean 4.
Hands-On Large Language Models is an illustrated guide to large language models. It includes over 275 custom figures, working code examples, timelines, and references to key research papers. The book has received positive reviews from Andrew Ng, Nils Reimers, Josh Starmer, Luis Serrano, Leland McInnes, and Prof. DDr. Roman Egger.
HandyAI is a collection of free browser-based tools for AI and Claude developers, including token counters, prompt analyzers, JSON to tool-use converters and cost calculators. It requires no sign-up and lists the LLM Token Counter and AI Cost Calculator as live tools, with others announced for later release.
hcom is a tool that enables AI agents to message, monitor, and spawn one another across terminal environments. It is compatible with a range of common AI agent CLIs including Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, and Kimi. It is available as a public GitHub repository.
Hermes Agent is a GitHub repository or organization with source code, releases, documentation, or project resources.
A freeCodeCamp handbook for developers on organizing AI agents for real business cases. It covers prerequisites, large language models, definitions of AI agents, and a decision algorithm for creating optimal agents, including checking budget, starting with one agent, and measuring performance. It uses a Google Research, Google DeepMind, and MIT paper as its primary source and code examples in a Google Colab notebook.
HTML widgets are R packages that produce interactive web visualizations, working like R plots. A line or two of R code produces a D3 graphic or Leaflet map. Widgets run at the R console and can be embedded in R Markdown reports and Shiny web applications. The page lists widget examples including Leaflet, dygraphs, Plotly and Highcharter, and describes composing dashboards with flexdashboard and linking widgets with crosstalk. New widgets can be developed by bridging R and JavaScript.
Hyperbrowser offers cloud browsers, isolated sandboxes and web data APIs for AI agents. It provides Chrome sessions and microVMs that can be launched in one call and connected to Playwright, Puppeteer or an agent. The documentation describes automating websites, running code in isolated environments and scraping web data.
hyperopt (hyperopt-sklearn) is an open-source project that provides hyper-parameter optimization functionality for the scikit-learn (sklearn) machine learning library. It is hosted as a public repository on GitHub for collaborative development.
This repository provides a hyperparameter optimization implementation for machine learning algorithms, accompanying a paper on hyperparameter optimization theory and practice. It includes sample code for regression and classification problems using the Boston-Housing and MNIST datasets, covering algorithms such as random forest, SVM, KNN and artificial neural networks.
ChainForge is an open-source visual programming environment for battle-testing prompts to large language models. It supports querying multiple models at once, comparing response quality across prompts, models and model settings, and setting evaluation metrics to visualize results. Built on ReactFlow and Flask, it can be installed locally with pip or tried on the web, where features are limited.
A delightful machine learning tool that allows you to train/fit, test and use models without writing code.
Ignite is a high-level library for training and evaluating neural networks in PyTorch. It provides a simple engine and event system, out-of-the-box metrics to evaluate models, and built-in handlers for composing training pipelines and saving artifacts. The library aims to require less code than pure PyTorch while keeping maximum control, with an extensible API for metrics and experiment managers.
Pix2pix implementation in keras. The repository provides code to download the facades dataset, install requirements, and start training, and it references the original Image-to-Image Translation with Conditional Adversarial Networks paper.
Impala is a distributed C++ query engine for SQL queries over petabytes of data stored in Apache Hadoop clusters. It supports data in HDFS, Apache HBase and Amazon S3, window functions and subqueries, and uses LLVM for on-the-fly code generation. It is Apache-licensed and open source, and the repository is a mirror of Apache Impala.
Inline Help is a no-code AI-powered user assistance tool that turns a knowledge base into in-app support. It offers Explain This, Tooltips, Chatbot, Widget, Knowledge Base, and Ticket Form features, with support in seven languages. A 14-day free trial is offered with no credit card needed.
Interview Solver is a technical interview preparation platform and AI copilot for software engineering candidates. Its native desktop application for macOS and Windows provides real-time, screen-sharing-invisible assistance during live coding interviews, including LeetCode-style problem solutions, system design diagrams, voice transcription, and answers tailored to a user's resume or job description.
The ipython-notebooks repository, hosted on GitHub under the user ogrisel, contains sample IPython notebooks for use with the scikit-learn machine learning library. It is an open-source project that accepts contributions from GitHub users.
An archived educational course repository for learning about LLMs, LLMOps and vector databases by designing, training and deploying a real-time financial advisor LLM system. It includes source code, video and reading materials, and covers a training pipeline using QLoRA and a streaming pipeline ingesting financial news. The repository was archived by its owner and is read-only.
IWE is a Markdown knowledge graph tool offering an LSP for editors, a CLI and MCP memory for AI agents. It stores notes as connected Markdown documents in a project folder, usable from Neovim, Helix, VS Code, Zed, the CLI or Claude/Codex. Neither the CLI nor the Mac app includes an AI model.
jcode is an open-source terminal coding agent written in Rust. It supports agent swarms, background tasks, and a small RAM footprint, and is installed with one command on macOS, Linux, or Windows. Login flows connect subscription and API model providers, and the agent itself is free while hosted inference plans are available.
Jinming Yang's GitHub profile describes him as a frontend engineer and AI-first builder based in Shenzhen, China. It links to current projects including ai-workflow, Vsync, UnMarket and aide, and lists legacy projects such as dom-to-code, gpt-runner and ios-scriptable-tsx.
Code for interactive simulacra of human behavior [[arxiv]](https://arxiv.org/abs/2304.03442).
Jupyter Notebook is a web-based interactive computing platform combining live code, equations, narrative text, visualizations, and dashboards. It supports over 40 programming languages, including Python, R, Julia, and Scala, and notebooks can be shared via email, Dropbox, GitHub, and the Jupyter Notebook Viewer.
