Tools & resources

Mixture of Experts is a weekly news podcast produced by IBM and hosted on the IBM Think podcast pages that recaps trends and innovations in the artificial intelligence industry. It publishes audio episodes that discuss recent AI research and developments at the frontiers of the field.

An independent platform for evaluating and comparing generative AI models. It publishes third-party assessments and comparative data on model capabilities and performance.

System Prompts Leaks is an open reference archive of extracted AI system prompts, stored as Markdown files and organized by vendor. It collects prompts captured from chat assistants and coding agents—including Anthropic Claude, OpenAI ChatGPT and Codex, Google Gemini, xAI Grok, Cursor, Copilot, VS Code, and Perplexity—as well as officially published prompts for comparison. The repository is updated regularly and is intended for developers and researchers studying the hidden instructions and rules supplied to AI systems before user messages.

A paid membership community and training program offered by Playmakers AI that teaches professionals how to become AI consultants or start AI implementation agencies. The program provides 3–5 weekly expert calls, instructional content and go-to-market guidance aimed at finding business customers and delivering $500–5K/month implementation services; it is distributed via a subscription on playmakersai.com.

awesome-gpt-image-2 is a curated collection of structured GPT Image 2 prompts, reverse-engineered image-generation cases, reusable templates, and agent tooling. It organizes examples into categories such as interfaces, infographics, posters, products, branding, photography, illustration, characters, storytelling, and documents, and uses an atomic schema that separates subjects, lighting, materials, layout, and visual details into composable prompt components. The repository also includes the GPT-Image-2 Style Library agent skill, whose generated reference data is shared with the visual gallery. The skill helps agents select styles, templates, categories, and scene tags, and can be installed for tools including Claude Code, Codex, and Cursor through the skills CLI, npm, GitHub Packages, or the Claude Code plugin marketplace. A companion website provides searchable gallery browsing, prompt copying, filtering, and signed-in image generation. The repository is released under the MIT License and states that its third-party prompt cases and images are organized for learning, research, and automated testing, with ownership and commercial-use rights remaining subject to their original sources.

The a16z Show is a podcast produced by Andreessen Horowitz (a16z). It covers technology and culture trends, technology news, and the future of software through discussions with industry experts, business leaders, and other guests. The show is published multiple times per week and is available through Apple Podcasts.

Product Hunt is a community-driven website that surfaces, reviews, and ranks newly launched tech products, apps, and hardware. It was founded by Ryan Hoover in 2013 and was acquired by AngelList in 2016; the site hosts daily product listings, discussions, and maker-focused events.

SAM.gov (System for Award Management) is the U.S. federal government's official website for registering entities to do business with the federal government and for searching federal procurement and assistance opportunities. It is operated by the General Services Administration (GSA) and consolidates multiple legacy systems into a single portal.

Can I Vibecode It? is an open-source catalog that evaluates whether AI coding agents such as Claude Code, Codex, or Cursor can build a usable personal replacement for a paid SaaS application. Each app entry provides a YES, KINDA, or NOT REALLY verdict, the exact prompt for attempting the replacement, and the tradeoffs of leaving the original service, including lost network effects, data, or infrastructure. App entries are contributed as one JSON file per app, with the schema and verdict criteria documented in the repository. The site uses Astro server output with a Node adapter to render fully server-rendered HTML, SQLite via better-sqlite3 for vote counters and waitlist data, and vanilla JavaScript and CSS for interactions. Satori and resvg generate Open Graph images at build time. It runs locally with npm install, npm run dev, npm run build, and npm start, requires no environment variables for local development, and supports optional analytics, sign-in, payments, email, and media-storage configuration. It can be deployed on a VPS behind a reverse proxy, with DATA_DIR used to keep user data outside the repository. The project is released under the MIT License, and its prompts are intended to remain free.

Public APIs is a community-maintained, open-source directory of free public APIs for software projects. The repository organizes APIs by domains such as finance, weather, development, games, and transportation, and records integration details including authentication requirements, HTTPS support, and CORS availability. It also provides contribution guidance and an API for the project.

A book by Mark Richards and Neal Ford covering software architecture fundamentals, including architectural characteristics, comparative ratings of common architectural styles, and techniques such as risk storming for assessing architectural risk.

AI Engineering from Scratch is a free, open-source curriculum developed by rohitg00 for learning to build and ship AI systems end to end. Its 20-phase sequence covers development tooling, mathematical and machine-learning foundations, deep learning, NLP, computer vision, generative AI, LLM applications, agent engineering, Model Context Protocol (MCP), agent skills, reinforcement learning, and related topics, with implementations in Python, TypeScript, Rust, and Julia. The repository describes 511 lessons and approximately 329 hours of material; each lesson produces a reusable artifact such as a prompt, skill, agent, or MCP server. Learners are instructed to read the lesson documentation, type and run the code from the repository root, record command evidence and outputs, and make a small change before continuing. It provides routes for complete foundations, mathematics and machine learning, production LLM applications, agent engineering, MCP, agent skills, and Claude certification preparation. The repository is distributed under the MIT license and is accompanied by a website containing the same lesson content.

CryptosRUs is a crypto media brand and channel associated with George, covering market commentary, livestreams, and crypto news. Its site provides daily market briefings, a live BTC/ETH/SOL ticker, chart and market-context research, and links to its YouTube community and trader Discord. The coverage includes market drivers, ETF flows, chart levels, liquidity, macro developments, and questions for traders to investigate. CryptosRUs also publishes a twice-weekly newsletter and promotes related learning and market tools, including MarketPulse and AskClash.

The Python Package Index (PyPI) is the official repository of software for the Python programming language, hosting packages that developers can publish and install via Python package managers. It serves as the central distribution point for Python libraries and tools, providing package metadata, releases, and download endpoints.

G2 is a business software and services review platform that aggregates user reviews, ratings, and comparisons to help buyers evaluate and choose software. The site, founded as G2 Crowd, is operated by G2, Inc. and is used by vendors for listings and buyers for research.

Trustpilot is a consumer review website founded in Denmark in 2007 by Peter Holten Mühlmann. It hosts reviews and ratings of businesses worldwide, enables consumers to post feedback and companies to respond, and is operated by the Trustpilot Group (listed on the London Stock Exchange since 2021).

Udemy is a global online learning marketplace operated by Udemy, Inc., offering on-demand video courses created and published by independent instructors across topics such as technology, business, and personal development. The platform, founded in 2010, lets instructors sell courses and learners purchase access to individual courses or bundles.

Skillshare is an online learning community operated by Skillshare, Inc., offering subscription-based access to video classes primarily in creative and entrepreneurial subjects such as design, illustration, photography, and marketing. Courses are created and taught by independent practitioners and creators and the platform includes community features like projects and peer feedback. The company was founded in 2010 and is headquartered in New York City.

Our World in Data is a nonprofit research and data website that presents evidence about global issues through charts, data explorers, topic pages, and articles. It covers subjects including population, emissions, pollution, poverty, education, artificial intelligence, democracy, and global health, and is used to examine demographic and other long-term trends. Its published material is openly accessible and openly licensed.

AskNature is an online knowledge base and design resource maintained by the Biomimicry Institute that catalogs biological strategies, functions, and references to inspire biomimicry-driven innovation. It offers searchable examples and summaries of natural solutions for use by designers, engineers, and researchers.

Real Producers is a U.S.-based media brand and publisher focused on the residential real estate industry. It publishes a magazine and online content and runs awards and events recognizing top real estate agents and teams.

An online directory of AI tools intended to help users research which products address particular client pain points. The site is described as indexing tools by use case and surfacing entries for comparison and discovery.

USAspending.gov is the U.S. government's official open-data website for federal spending, operated by the U.S. Department of the Treasury. It publishes searchable data and visualizations on federal awards (contracts, grants, loans and other financial assistance) and recipients to provide transparency and meet reporting requirements.

Growjo is a data and media company that publishes rankings and lists of high-growth companies, provides company growth metrics and profiles, and offers hiring and market-insight information for recruiters, investors, and jobseekers.

EstateSales.NET is an online directory that lists local estate sales, tag sales, and auctions. The site provides sale descriptions, photographs, dates, and directions and includes search tools to find nearby sales and estate sale companies.

Copilot Workshops is an open-source collection of guided, hands-on lessons for exploring GitHub Copilot's agentic capabilities across the software development lifecycle. Its content covers the Copilot CLI, VS Code agent mode, the GitHub Copilot app, and the Copilot cloud agent, with Markdown lessons, images, and an Astro + Starlight site that publishes the material; the workshop's Tailspin Toys demo application is maintained in a separate repository. The repository is MIT-licensed.

Build Your Own X is a curated GitHub repository of step-by-step guides for recreating familiar technologies from scratch as programming exercises. Its index organizes tutorials covering databases, operating systems, programming languages, Git, web servers, neural networks, command-line tools, games, browsers, distributed systems, and other software categories, with implementations and guides in languages including Python, JavaScript, Go, C++, Java, and others.

Open Source Society University is a free, self-directed computer science curriculum assembled from online courses and, where necessary, supplementary books. It is organized around undergraduate computer science requirements into Intro CS, Core CS, Advanced CS, and a final project, with materials selected for open enrollment, recurring or self-paced availability, teaching quality, and alignment with the CS2013 curriculum guidelines. Learners may follow it independently or in groups, in or out of order, and most course material is free, although some providers may charge for graded assignments, tests, or projects.

A community-maintained directory of projects made by independent developers in China, presented as a plain Markdown repository. It organizes entries into a main list of ready-to-use websites and apps, a programmer-focused section for projects requiring command-line use or coding, and a games section; entries can be marked as in development, launched, or closed or unmaintained. Contributors can add projects through pull requests or issues.

Awesome LLM Apps is an open-source GitHub collection of Python templates for AI agents, agent skills, and retrieval-augmented generation (RAG) applications. Its examples include starter and advanced agents, multi-agent teams, voice and multimodal agents, MCP-based agents, memory-enabled agents, data analysis, web scraping, and other application patterns. The repository provides runnable source projects and step-by-step tutorials. Individual agents can be cloned and run with an API key, while agent skills can be installed with a command such as `npx skills add` and used with coding agents including Claude Code, Codex, and Cursor. The projects support models from providers and ecosystems including Claude, Gemini, GPT, DeepSeek, Llama, and Qwen. The repository describes the collection as free and open source under the Apache-2.0 license.

A DataExpert-io GitHub repository that curates learning resources for data engineering. It organizes a 2024 career roadmap, free beginner and intermediate boot-camp materials, required software, hands-on projects, interview guidance, books, communities, newsletters, company and tool directories, engineering blogs, whitepapers, and data-engineering creator accounts. Its categorized references cover areas including orchestration, data lakes and clouds, warehouses, data quality, analytics, data integration, semantic layers, modern OLAP, LLM application libraries, real-time data, and data lineage.

PerceptionBench is a benchmark for evaluating atomic visual perception in multimodal large language models (MLLMs). It isolates perception from reasoning and domain knowledge by defining ten atomic perceptual capabilities, including counting, depth, localization, OCR, and perception-related hallucination, based on an error taxonomy derived from failures across existing benchmarks. The released dataset contains 3,000 verified open-ended questions with short, uniquely determined answers; 1,800 are decomposed from failures in source benchmarks and 1,200 are newly authored using supplementary images. The repository provides the benchmark's code and links to its paper and dataset.

An OpenAI repository containing Lean 4 formalizations of ten results presented in its paper on advances in mathematics and theoretical computer science. The formalizations cover high-dimensional sphere packing; binary and spherical codes; non-sofic groups; Connes’s rigidity conjecture; arithmetic circuit complexity; quantum parallel repetition; the closest vector problem; Ehrhart’s volume conjecture; multicolor Ramsey numbers; and compactness and degeneracy conjectures in extremal graph theory. Each result is implemented as a separate Lean module, including `SpherePacking.lean`, `MetricCodes.lean`, `NonSoficGroup.lean`, `ConnesRigidity.lean`, `Permanent.lean`, `QuantumParallelRepetition.lean`, `GapCVP.lean`, `EhrhartVolumeInequality.lean`, `MulticolorTriangleRamsey.lean`, and `CompactnessAndDegeneracy.lean`. The project uses Lean 4.32.0, mathlib, and Lake. With the mathlib cache installed, all formalizations can be built with `lake build All`, or individual modules can be built by name; the repository also provides reasoning walkthroughs and documents independent checking with Comparator.

Prehistoric Animal Museum is a free browser-based 3D museum for children and families, developed by Leon Made This. It presents 18 prehistoric-animal exhibits across land, sea, and sky, with interactive models that visitors can rotate and zoom. Each exhibit provides optional short narration in English or Simplified Chinese, without autoplay, and a parent guide with information about the animal's period, fossil discoveries, size, diet, classification, and sources. The responsive site supports phones, tablets, and desktops, keyboard navigation, reduced-motion settings, remembered language selection, and shareable language-specific links. The museum is designed mainly for children aged 2–6 with an accompanying adult. It requires no account, contains no advertising or analytics scripts, and uses prepared static models, images, and narration rather than runtime calls to AI, advertising, or analytics services. The repository describes some reconstructions as evidence-informed artistic interpretations because fossils do not preserve every detail.

Ember is a collection of redshift-aware color palettes for terminals, interfaces, charts, and heat maps. It models warm-screen filters at 3400 K, 2000 K, and 1200 K, where each RGB channel is multiplied by a different gain, and supplies palettes designed to preserve text readability, categorical color separation, contrast, perceptual separation, and ordered lightness after the modeled transform. It includes neutral or warm-neutral text and surface colors, terminal accents, categorical palettes, and 256-sample sequential maps; deeper filters intentionally provide fewer distinct semantic colors and may assign unsupported ANSI names as aliases. The palettes are distributed in terminal, CSS, JSON, Python, and Matplotlib formats. The repository documents deterministic filtered-output simulations based on published gains rather than photographs, calibrated physical color temperatures, or predictions of every display pipeline.

An open, machine-readable taxonomy of learning across the primary and elementary years, produced by Marble. It represents fine-grained micro-topics as nodes in a prerequisite graph, with each topic containing a plain-language description, subject and domain, conceptual or procedural type, approximate age range, mastery evidence, assessment prompt, and links to source curriculum standards such as NGSS, Common Core, and the UK National Curriculum. Dependency edges identify hard or soft prerequisites and include reasons; the dataset also provides parent-friendly domain summaries. The JSON files include topics, dependencies, curriculum standards, domain clusters, and a manifest with counts and checksums. The repository describes it as pure data with no runtime or dependencies, and provides an interactive curriculum explorer at withmarble.com/curriculum.

Harness Engineering is Ryan Lopopolo’s anthology, field guide, and agent-context repository for improving coding-agent output without changing the underlying model or coding agent. It shapes the surrounding environment through context and tools so an agent can recover intent, operate the real system, respect authority, prove its outcome, and incorporate lessons from accepted work, corrections, failures, and user responses. The repository uses AGENTS.md to route agents to relevant arguments, cases, and proof, and provides a thesis index, playbooks, source material, and executable constraints for encoding organizational requirements and decisions. Repository-authored material is licensed under CC BY 4.0.

An open GitHub guide and configuration project by jamesob for running state-of-the-art large language models locally. It documents a multi-GPU system using PCIe switches so GPUs can communicate peer-to-peer, including hardware selection, BIOS bifurcation, link-speed and ASPM settings, kernel and GRUB parameters, ACS configuration, and GPU power limiting. The repository also provides Docker-based serving configurations, a local speech-to-text configuration, and a GPU peer-to-peer bandwidth and latency benchmark.

CommerceAgentBench is a benchmark developed and maintained by the Accio team at Alibaba International for evaluating whether AI agents can complete long-horizon business workflows in high-fidelity, stateful, reproducible replicas of online services. Its tasks cover browser operations, native-style command-line tools, file and spreadsheet production, API and MCP workflows, public-web research, supplier analysis, product publishing, logistics, storefront configuration, and other commerce operations. Each task runs in a fresh container and is graded by a deterministic or LLM-assisted verifier. The benchmark uses local mock services representing commerce, SaaS, messaging, document, and operational systems; runs preserve the resolved configuration, agent trajectory, verifier result, artifacts, logs, and container metadata for auditing and reproducibility. The repository describes 107 tasks spanning CLI, browser, file, and API/MCP interfaces, with text-only, browser-text-capable, and vision-required capability slices. The project was previously called RealReplicaBench.

An open-source collection of common React job-interview questions with detailed answers and explanations in Spanish. The repository organizes material from beginner to intermediate topics, including JSX, components, props and state, hooks such as useState and useEffect, rendering, hydration, server-side rendering, controlled components, custom hooks, and React design patterns. Its companion site, reactjs.wiki, supports searching, saving, and sharing questions.

GQA is a dataset for visual question answering and visual reasoning that provides grounded, compositional questions and answers over real-world images, built from scene graph annotations (derived from Visual Genome). It is used to train and evaluate models on compositional, spatial and relational reasoning in images.

The Koerner Office is a business newsletter and podcast produced by Chris J. Koerner that shares tactics, ideas and discussions for starting and growing businesses and real-estate holdings. It is distributed as an email newsletter and as podcast episodes, and its issues/episodes focus on business strategy, deal flow, and real-estate approaches.

arXiv is an open-access repository of scholarly preprints (e-prints) operated by Cornell University Library. It hosts papers across physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and economics, assigns persistent arXiv identifiers, provides full-text (PDF/TeX) and metadata, and exposes content via its website, OAI-PMH and a public API; submissions are subject to basic moderation and some categories require endorsement. The service is free to read and is funded and governed through Cornell University Library together with a membership program and institutional/foundation supporters (including the Simons Foundation).

MobyGames is an online, community-maintained database of video game metadata and credits, established in 1999. It aggregates release dates, platforms, developer and publisher credits, cover art, screenshots, genre tags, system requirements, and user-contributed reviews and trivia, and provides a searchable web interface and browseable game pages.

An online course and community (branded Switch Dimension AI) created by Rob Shocks that teaches how to build and ship products with AI. The offering combines instructional content on building AI-powered applications with access to a learner community and is hosted at switchdimension.com.

A Notion template created by Jeff Su that collects 15 reusable AI prompts for writing, research, ideation, and analysis. Each entry includes the prompt text, usage instructions, and a video walkthrough with examples; the template notes compatibility with ChatGPT, Claude, and Gemini and is distributed via the Notion Marketplace.

L'Hebdo is the weekly news bulletin of Impact Centre Chrétien — Bruxelles. It is distributed as a downloadable PDF and contains church news, practical information and event schedules for the congregation.

A downloadable list of 30+ "unsexy" or blue-collar business ideas compiled and published by the My First Million podcast. The resource aggregates business concepts mentioned on MFM episodes and is distributed as a free lead magnet via the podcast's HubSpot offers landing page.

A marketed guide and sales landing page hosted at communityboardplaybook.com that offers instruction on earning money with direct-mail / community-card advertising; the landing page headline reads "Want an Easy Way To Make $1,000 With Direct Mail?". The site title uses "Community Card Playbook" while the domain name uses "communityboardplaybook.com" and the front page does not clearly identify an author or publisher.

Google for Developers is Google's developer-focused resource and media platform, providing documentation, guides, tools, and technical content for Google technologies and APIs. It also operates an official YouTube channel for developer announcements, tutorials, and event content.

Modern Software Engineering is an organization and content platform focused on practices for producing better software faster. Its LinkedIn page features work and talks from software engineering leaders including Dave Farley, Trisha Gee, Steve Smith, Emily Bache, Kevlin Henney, and Kent Beck.

Wikipedia is a free, multilingual online encyclopedia created and edited by volunteers and hosted by the Wikimedia Foundation. It provides general-reference articles and factual information across many subjects, including science, history, and zoology.

A two-day, hands-on AI workshop from Outskill covering AI tools, agent building, workflow automation, and image and video generation. The program is advertised as including more than 16 hours of instruction with expert mentors and access to more than 10 AI tools.

An RSS feed for Hostinger's tutorial articles, available at the Hostinger Tutorials feed URL and readable in RSS clients such as Newsboat.

A book by Simon Brown about lightweight software architecture, technical leadership, and balancing architectural practices with agile development. It describes risk storming as a technique for identifying risks in software architecture.

BiteBico is a technology interview-preparation platform and community offering courses and resources on system design, coding, behavioral interviews, machine learning, and object-oriented design.

Outskill is an AI education provider that runs two-day mastermind workshops covering hands-on use of AI tools, AI agent building, workflow automation, image and video generation, and AI-assisted coding.

QCon San Francisco is a software engineering conference for senior practitioners and engineers, featuring production lessons and discussions on AI, software architecture, leadership, and engineering culture. The 2026 edition is scheduled for November 16–20, 2026, in San Francisco.

InfoQ is a technology information and community platform that publishes articles, interviews, conference videos, transcripts, and presentation slides, primarily covering software development, architecture, cloud computing, and related engineering practices.

AI Engineering Lab is a free, self-paced 24-week AI engineering course developed by Zorost Intelligence AI Lab. It takes learners from Python and machine learning through deep learning, LLM internals, prompt and context engineering, retrieval-augmented generation with vector search, quantization, LoRA and DPO fine-tuning, evaluation harnesses, coding-agent harnesses, AI agents, MCP, and cloud and Databricks platforms including Azure AI Foundry, Google Vertex AI, AWS Bedrock, and Databricks. The curriculum uses one continuous fictional freight-company case study. Each week pairs a concept with a runnable Python, SQL, or PySpark artifact; from Week 3 onward, the work includes a metric and an error note. The repository contains 43 runnable notebooks, publishes the full curriculum online, requires no signup or paid API key, and states that the first eight weeks require no GPU. It is MIT licensed.