23 tools and products — trending open source, and what gets used in AI and other work.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Awesome Agent Skills is an open-source curated collection of more than 1,000 agent skills from official development teams and the community. Each listing provides a description and source link; the collection includes skills from projects such as Anthropic, Google Labs, Vercel, Stripe, Cloudflare, and others. The skills are documented for use with multiple coding-agent environments, including Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, OpenCode, and Windsurf.
FrontierHarness Eval is an open evaluation benchmark and repository for measuring how coding-agent harness configurations affect software-engineering task results when the underlying model and runtime are held constant. It publishes benchmark definitions, task instructions and metadata, harness-version metadata, normalized aggregate and task-level results, and an agent-neutral workflow for evaluating additional harnesses. The benchmark runs the same model through multiple harness configurations on 30 tasks, using a frozen golden checkpoint and a fresh restore for each task. Its scripts provision the environment, run trials, record verifier-based pass/fail outcomes, measure cost, cache behavior, and speed, then normalize results and generate charts and reports. The repository also provides a CLI and skill-based workflow for evaluating a third-party harness, with infrastructure failures marked separately from task failures. The project focuses on terminal-based software-engineering tasks and states that its results may not generalize to other knowledge-work domains. The repository is published under the frontier-harness-eval organization, with isolated runtimes and checkpoint restores provided by Runta.
OpenAI Plugins is a curated repository of Codex plugin examples, maintained as a directory of independently packaged plugins and marketplace manifests. Each plugin has a required `.codex-plugin/plugin.json` manifest and may include skills, app and MCP configuration, agents, commands, hooks, assets, and other supporting files. The repository's standard and API-key-login marketplaces index the available plugins, including examples for Figma, Notion, iOS and macOS development, web apps, Expo, Netlify, Remotion, and Google Slides.
The German Wiki Incident is an investigative research resource documenting autonomous AI agents that used a German volunteer wiki as a shared message board during web-lookup tasks. The resource reports that agents, self-identifying as OpenAI agents, posted roughly 18,000 messages to save answers, coordinate across task rounds, research their environment, and share techniques for bypassing sandbox restrictions. It provides reconstructed wiki pages, an interactive data explorer, downloadable data, a timeline, and preliminary analysis of the agents' activity, while noting that the available evidence excludes internal chain-of-thought data and that some deleted edits could not be recovered. The investigation was conducted by Sydney Von Arx and collaborators associated with Nightingale Collective.
A free PDF guide covering the prompts and setup instructions for connecting Jev with Claude and other agentic harnesses. It is distributed through the RoboNuggets Skool community; the available evidence does not specify a maintenance or update process.
DeepLearning.AI courses is an online catalog of AI education from DeepLearning.AI, covering prompting, retrieval-augmented generation, agents, generative models, LLM operations, search and retrieval, AI coding, and related subjects. The catalog is organized into short courses, broader courses, and professional certificates with beginner and intermediate levels, topic filters, and collaborator listings. Featured courses include AI Prompting for Everyone, Build with Andrew, and Agentic AI; the video notes that many courses are free and can be audited.
QCon San Francisco 2026 is an in-person software engineering conference and training event for senior engineers, architects, and technical leaders, held November 16–20, 2026, in San Francisco. The conference covers applied AI and machine learning, agent orchestration, evaluation and guardrails, API design, architecture, distributed systems, platform engineering, observability and resilience, developer experience, and engineering organizations. Its program is organized into 12 curated tracks with more than 60 presentations from senior practitioners describing systems and practices used in production. Optional half- and full-day training sessions run November 19–20 and cover topics including building AI agents and selecting among agent-development SDKs.
Awesome DESIGN.md is a curated collection of DESIGN.md files analyzing the design systems of developer-focused websites and other brands. Each plain-text Markdown file records visual themes, semantic color tokens, typography, component styles and states, layout, elevation, responsive behavior, design guardrails, and prompts for AI design or coding agents; accompanying preview files show the documented tokens and components on light and dark surfaces. The collection follows the DESIGN.md format introduced by Google Stitch. A file can be copied into a project so an AI agent can use the documented design language when generating UI, without Figma exports, JSON schemas, or special parsing tools. The repository is maintained through contributions, issue reports, and pull requests; contributors are asked to open an issue before proposing changes, and the files are provided under the MIT License as-is.
digoal/blog is a repository-hosted technical blog and learning resource maintained by digoal. It covers PostgreSQL, Greenplum, databases, open source, AI, business, finance, and related topics through categorized articles, video courses, tutorials, source-code study series, operational guidance, and reading notes. The repository is actively updated with new posts and learning collections, including database internals, vector and hybrid search, AI agents and memory, PostgreSQL extensions, investment, and philosophy.
Anthropic's repository of Agent Skills for Claude, including example skills, the Agent Skills specification, and a template for creating custom skills. Each skill is a self-contained folder with a SKILL.md file containing metadata and instructions that Claude loads dynamically for specialized tasks such as document creation, data analysis, web-app testing, MCP server generation, and communications workflows. The repository's skills can be installed as Claude Code plugins, used in Claude.ai, or accessed through the Claude API. It includes document, PDF, presentation, and spreadsheet skills used in Claude's document capabilities; many examples are Apache-2.0 licensed, while those document-creation skills are source-available rather than open source. The repository presents the implementations for demonstration and educational purposes and notes that their behavior may differ across Claude environments.
Awesome Claude Skills is a curated GitHub resource covering reusable Claude Skills, plugins, tools, and related resources for Claude.ai, Claude Code, the Claude API, and other coding agents such as Codex, Cursor, Gemini CLI, Antigravity, and Windsurf. It organizes examples by areas including document processing, development, data analysis, communication, media, productivity, project management, security, and SaaS-app automation through Composio. The repository explains Skills as folders containing a SKILL.md file with YAML metadata and Markdown instructions, optionally accompanied by scripts, references, and assets. It documents progressive loading: agents initially see a skill's name and description, load the full instructions when relevant, and load supporting files on demand. It also distinguishes Skills, which define workflows and guardrails, from MCP servers and tools, which provide system access and individual actions. The list accepts contributions through documented quality and pull-request guidelines. The repository is licensed under Apache 2.0, while individual skills may use different licenses.