Directory
Published directory entries matching your search.
Skills is a directory for discovering and installing skills for AI agents. Skills are reusable capabilities that provide procedural knowledge helping agents accomplish specific tasks more effectively. Installation uses a skills CLI command, and the leaderboard ranks skills based on anonymous telemetry data collected from that CLI.
Supports software work with AI-assisted coding, testing or application development.
Open-source Python library designed to make it extremely easy to build and run agents using just a few lines of code.
A model-driven approach to building AI agents in just a few lines of code.
Superagent is a security product that connects software, security workers, and development workflows. Its workers cover pull request review, dependency updates, red team assessments, and agent guardrails, and the Security-One decision model supports triage across applications, agents, code, and infrastructure. Findings are routed into development workflows, with human approval for consequential changes.
Apache Superset is an open-source data exploration and visualization platform. It offers a no-code visualization builder and a SQL IDE, connects to SQL-based databases, and ships with more than 40 pre-installed visualization types. It includes dashboards, a chart builder, SQL Lab and datasets, with a plug-in architecture for custom visualizations.
SwarmVault is a local-first tool that turns documents, code, transcripts, notes and URLs into a markdown wiki and a local knowledge graph for AI agents. It follows a three-layer architecture based on a pattern described by Andrej Karpathy. A first run requires no API keys, using a built-in heuristic provider that runs locally and offline.
SWE-bench is a benchmark for evaluating large language models on real-world software issues collected from GitHub. Given a codebase and an issue, a language model generates a patch that resolves the described problem.
The fastest AI copilot for JetBrains. Write code 10x faster with intelligent autocomplete and an AI agent.
A neuro-symbolic framework for building applications with LLMs at the core.
Tabby is a self-hosted AI coding assistant presented as an open-source, on-premises alternative to GitHub Copilot. The project describes itself as self-contained, requiring no DBMS or cloud service, with an OpenAPI interface for integration with existing infrastructure such as cloud IDEs, and support for consumer-grade GPUs.
Ted Spare is a GitHub user with the handle tedspare, who builds projects under the RubricLab organization. The profile hosts 30 public repositories with accessible code contributions on the GitHub platform.
Tensor Trust is the source code for a web game and data cleaning pipeline described as a prompt injection attack game that collects data for adversarial ML research. The repository covers the game and pipeline and links to a paper and the game itself.
TensorForce is an open-source library built on TensorFlow for applied reinforcement learning. Hosted on GitHub, the project provides installation guidance, quickstart example code, and command line usage documentation for users.
TestDriver is an AI code reviewer that runs every pull request in a real desktop sandbox, finds bugs, and builds end-to-end UI tests. It adds tests back as a new pull request and runs unattended in CI. Pricing starts at $20 per seat per month on the ProCloud plan with 120 testing minutes included, plus $0.14 per testing minute.
The Hundred-Page Language Models Book by Andriy Burkov is a concise hands-on guide covering machine learning basics through advanced transformer architectures and large language models. It explains AI fundamentals, text representation, count-based models, recurrent neural networks, and transformers, with mathematical foundations and Python code examples. The book targets ML practitioners and engineers building text-based applications.
The Bot is a public JavaScript repository that provides an example of a neural network learning to predict the angle between two points. It is built using the synaptic.js library and demonstrates this machine learning functionality in code.
The FLUX.1 family of models on Replicate is a collection of Black Forest Labs' FLUX AI models for image generation and editing. Users can run the models with one line of code, fine-tune them with custom data, and edit images using Flux Fill, Depth, and Canny tools. The collection includes multiple FLUX model variants suited for different use cases.
An illustrated explainer article on VQGAN, describing how the model generates images from text at a conceptual level and how VQGAN and CLIP work in tandem. It covers a theory of perception, using transformers to model interactions, expressing images through a codebook, and training the GAN and transformer.
Supports software work with AI-assisted coding, testing or application development.
Tiledesk is an open-source, no-code platform for building AI chatbots and connecting live agents. Conversations can be designed visually, connected to knowledge sources and deployed on web, WhatsApp and voice channels. The platform offers a 14-day free trial.
TinkerIQ is a Hugging Face Space application that allows users to upload circuit images to analyze components and generate code templates for platforms including Arduino, ESP32, and Raspberry Pi, while providing detailed component lists. The Space is currently sleeping due to inactivity.
torchvision is a package of popular datasets, model architectures and common image transformations for computer vision. The repository holds documentation, benchmarks, examples, packaging, references and tests alongside the torchvision code. Installation instructions point to official guidance for stable torch and torchvision versions; building from source is covered on the contributing page.
A web app to generate template code for machine learning.
