Directory
Published directory entries matching your search.
A research repository examining how agentic AI coding assistants work, covering reconstructed prompt patterns, agent coordination and security classification. It documents design patterns such as system prompts, sub-agent coordination and permission mechanisms, described as approximations based on observation rather than verbatim copies. It aims to help AI engineers and researchers learn from these architectural patterns.
Repository containing references and code for the book Distributed Machine Learning Patterns from Manning Publications by Yuan Tang. The book covers applying patterns to build scalable and reliable machine learning systems, constructing pipelines with data ingestion, distributed training and model serving, and automating tasks with Kubernetes, TensorFlow, Kubeflow and Argo Workflows.
A free curriculum of six courses on agentic AI design patterns for developers and product managers. It covers code, architecture, decisions and hands-on games, with 21 patterns for developers and 15 modules for product managers. No account is needed to read the material.
A write-up on practical patterns for integrating large language models into systems and products, drawing on academic research, industry resources and practitioner know-how. It covers seven key patterns, including evals, RAG, fine-tuning, caching, guardrails, defensive UX and collecting user feedback.
Colibri Core is an NLP tool and a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams, i.e. patterns with one or more gaps of fixed or dynamic size. It counts and extracts patterns from large corpus data. The central tool, colibri-patternmodeller, builds, views, manipulates and queries pattern models.
Magic Patterns is an AI design tool for product teams that turns prompts into production-ready UI. It can use existing components and design rules to generate prototypes, and offers an infinite canvas with collaboration. A changelog describes PDF uploads and export options.
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.
Building Effective Agents is an Anthropic engineering publication that details the company's approach to developing reliable large language model (LLM) agents. It covers research on agent capabilities, safety considerations, technical frameworks, and practical guidance for developers, noting that simple, composable patterns are more effective than complex frameworks for successful agent implementations. It also references Anthropic's Claude Managed Agents.
BurnRate is an AI usage analytics tool that tracks costs, tokens and usage patterns across AI coding providers. It connects OpenAI and Anthropic reporting accounts for provider-reported spend and offers a local CLI for session-level detail. Cloud workspaces come in Free, Pro at $12/month and Team at $29/seat/month plans.
Desbordante is a high-performance open-source data profiler. It uses a variety of algorithms to discover different patterns in data and supports running data cleaning scenarios using these algorithms. The tool is available as a console version and an easy-to-use web application.
Collection of patterns for experimenting with agents, llm pipelines, and ChainOfThoughtStrategy.
GPTZero is an AI content detection tool that accepts pasted text and returns an overall AI score with sentence-by-sentence detection. Its Authorship feature offers writing replay in Google Docs, replaying edits, flagging copy and pastes and grading typing patterns. A team plan includes shared credits, unified billing and seat management at 500,000 words per member per month, with card payment only.
LochBot is a free prompt injection vulnerability checker. It analyzes a pasted system prompt against 31 documented injection attack patterns in 7 categories and returns a security score with fix suggestions. The analysis runs client-side in the browser. Results can be exported as JSON.
Lux is a Python library for automated data exploration. When a pandas dataframe is printed in a Jupyter notebook, Lux recommends a set of visualizations highlighting trends and patterns, shown in an interactive widget for browsing and exploring the dataset.
Magic Eraser is a web tool from Magic Studio that removes objects, people, text, blemishes and patterns from photos. Users upload an image, select the area with a brush, erase with AI and download the result. The source states unlimited free use with no signup, and lists uses such as real estate, photography, fashion, e-commerce and social media.
Rasa is an AI agent platform built for product teams developing customer-facing AI agents. The platform extends large language models with structured flows, deterministic logic, and built-in recovery patterns. Its capabilities include real-time enterprise retrieval-augmented generation, voice support, agentic AI functionality, multilingual support, and conversation orchestration, with use cases across customer support, sales enablement, and operational efficiency for industries including finance, retail, and healthcare.
RegexAI is a free online tool for testing regular expressions with live matching. It also builds new patterns from plain-English descriptions of what the user wants to match, according to the site. No signup is required.
Wordware is an AI context lab based in San Francisco, founded in 2023. Its core product is Sauna, an AI workspace that learns user preferences, identifies patterns in user work, reduces administrative busywork, and proactively supports user tasks.
