Xonsh is a cross-platform, Python-powered interactive shell that combines Python syntax with shell subprocess commands. The codebase implements a full shell environment with a custom parser (PLY-based with version-specific extensions), an execution engine that compiles xonsh code to Python AST, a rich tab-completion system with multiple backends (bash, git, pip, python, custom completers), a pluggable history backend (JSON, SQLite), a prompt system with git status and virtualenv information, and a subprocess management layer with job control. It also includes CLI tools for formatting, linting, and interactive configuration (xonfig wizard and web UI). The architecture is monolithic with a clear module structure: parsers, executers, completers, prompts, history, procs, and shells. External dependencies include prompt_toolkit, pygments, and PLY (vendored). The repository is actively maintained with frequent releases, supports Python 3.10+, and has an extensive test suite. Some technical drift exists due to deprecated API shims, multiple parser versions, and LLM-generated tests, but the core is well-engineered.
This repository is a curated, multi-vendor collection of leaked system prompts from major AI chatbots (ChatGPT, Claude, Gemini, Grok, Perplexity, DeepSeek, etc.), captured verbatim from production systems. It serves as a reference corpus for studying AI behavior instructions, safety guardrails, tool definitions, and product positioning across model versions and vendors. The repository also includes Claude Code bundled skills (code review, design-sync, dataviz, deep research) and Claude Design starter components, which are supplementary tooling. While primarily a documentation archive, it contains some well-crafted reusable components such as color palette validation scripts, a design system build/diff pipeline, and a deep research workflow script. The prompts are organized by vendor with version tracking, and the repository is actively maintained with recent updates. However, the tooling scripts lack dependency pinning, and the prompts are time-sensitive snapshots that will drift as products evolve.
This repository is a comprehensive knowledge base and reference implementation for Claude Code best practices, curated by Shayan Rais. It is not a standalone application but rather a living documentation and configuration library that demonstrates how to effectively use Claude Code CLI through agents, skills, commands, hooks, and workflows. The core architecture follows a Command → Agent → Skill orchestration pattern, with working examples such as a weather reporter system and a structured RPI (Research-Plan-Implement) development workflow. The repository includes reusable configuration patterns (YAML frontmatter schemas for agents and skills), a cross-platform Python hook script for lifecycle events, detailed changelogs that track drift against official Claude Code documentation, and extensive reference guides covering settings, environment variables, MCP servers, and startup flags. While primarily a documentation and reference project, it contains runnable Claude Code configurations that can be directly adopted or adapted by other projects.
This repository repackages Anthropic's official Claude Desktop Linux .deb with a comprehensive set of Linux-native enhancements and community features. It applies 48 surgical JavaScript patches (compiled from Nim sources) to the minified Electron bundle, adding custom theme engine with 97 bundled dual light/dark palettes, multi-profile isolation, Quick Entry global hotkey, Computer Use desktop automation backends (X11, wlroots, GNOME, KWin portals), and an in-app Extra settings panel for themes, feature flags, and third-party inference configuration. The project produces packages for Arch (pacman), Debian/Ubuntu (APT), Fedora/RHEL (RPM), NixOS (flake), and AppImage, with automated CI that polls upstream every 2 hours, validates patch integrity, and publishes signed repositories. The architecture is a patch overlay on a third-party Electron desktop app. Patches are organized into three groups: linux (31 patches, always-on), core (7 patches, infrastructure), and community (10 patches, opt-in). A Nim-based build system compiles each patch into a native binary that performs regex-based transformations on the minified JS, with strict idempotency checks that fail the build if any pattern doesn't match. The patching system also handles upstream code-split chunks and concatenates/splits them as needed. The theme engine injects CSS custom properties via Electron's insertCSS, supports live reload via file watcher, and includes a full browser UI (theme picker SPA) with search, keyboard navigation, and wallpaper-driven generation via matugen. While the codebase demonstrates high engineering craftsmanship—consistent IPC validation, atomic config writes, robust fallback chains for Computer Use backends, and a reproducible build workflow with byte-identical artifact checks—it is tightly coupled to a single upstream app's minified bundle shape and DOM structure. The 48 patches are a significant maintenance burden that must be re-validated on every upstream release. However, the project is actively maintained, with automated CI catching most regressions, and several patterns (spinner injector, theme engine, config utilities) could be extracted for reuse in other Electron or web applications.
This repository is a hybrid: it is primarily a curated awesome list for Claude Code resources, but it is backed by a real automation layer that treats the README as a generated artifact. The single source of truth is a CSV resource table plus a config.yaml that defines category ordering; a Python script (generate_readme.py) renders the README, ticker SVGs, and recently-added carousels. The repo also includes GitHub Actions workflows that validate new resource submissions via issue forms, handle maintainer approval/rejection commands, and automatically open PRs to add approved resources. This makes it less of a static list and more of a self-maintaining content pipeline.
ReadAny is a full-featured, cross-platform e-book reader application with deep AI integration. It supports reading EPUB, PDF, MOBI, FB2, and other formats via the modified foliate-js engine, and provides text-to-speech, annotations, reading statistics, and cross-device sync (WebDAV, S3, LAN). The AI subsystem offers chat with RAG (semantic search over book content), context-aware tools, and execution of user-defined skills. The application follows a local-first architecture with robust offline capabilities and optional cloud sync. The codebase is structured as a pnpm monorepo with four main packages: 'core' (shared business logic, types, stores, AI, RAG, sync, stats, TTS), 'app' (Tauri desktop client with React+shadcn UI), 'app-expo' (Expo/React Native mobile client), and 'cli' (agent integration via MCP and managed shims). The application exhibits high craftsmanship in its platform abstraction layer, persistent store pattern, and hybrid search engine. However, there is significant platform-driven code duplication (desktop vs. mobile UI components) and a complex dependency graph with multiple patched packages, indicating some architectural debt.
Local Deep Research is a self-hosted, privacy-focused AI research assistant that performs deep, agentic research using multiple LLMs and web searches. It provides a full-stack web application (FastAPI + JavaScript), a programmatic API, and a Model Context Protocol (MCP) server. The system ingests user queries, decomposes them, executes parallel searches across web and academic sources (SearXNG, Google, arXiv, PubMed, Semantic Scholar, etc.), fetches and extracts content, evaluates evidence, and synthesizes reports with citations. It features per-user encrypted SQLCipher databases, a settings system with environment variable overrides, a RAG library with FAISS vector store, journal quality scoring, news subscriptions, and extensive security controls (egress policy, SSRF protection, credential scrubbing). The codebase is heavily tested with unit, integration, UI, accessibility, and security tests. It is a hybrid of a web application and a research data pipeline, but the dominant character is a production-grade application.
Witsy is a feature-rich desktop AI assistant built with Electron and Vue 3. It operates as a Bring-Your-Own-Keys (BYOK) client, aggregating dozens of LLM providers (OpenAI, Anthropic, Google, Ollama, etc.) into a unified chat, agent, and automation platform. The architecture follows a standard Electron main/renderer process split, communicating via IPC, with a Vue 3 frontend and a Node.js backend. Beyond basic chat, Witsy provides a sophisticated agent system supporting multi-step workflows, A2A communication, scheduling, and webhooks. It includes a full RAG pipeline (document ingestion, chunking, embedding, vector search), a plugin system for tools (MCP, code execution, web browsing, image generation), and extensive voice capabilities (STT/TTS with multiple providers). Data is persisted locally as JSON files within workspaces, with a vector database for semantic memory and document retrieval. A key differentiator is its automation layer, which can control the desktop (text selection, pasting, app detection) via platform-specific automators (macOS, Windows, nut-js). It exposes a local HTTP API and a CLI for external integration. The MCP (Model Context Protocol) client allows it to connect to a vast ecosystem of third-party tools. While primarily an application, it contains significant data engineering components (RAG pipeline, memory manager, deep research orchestrator) that are tightly integrated into the app's workflow. The codebase is well-structured with a strong emphasis on testing, though its massive feature surface and reliance on external APIs introduce inherent complexity and maintenance challenges.
This repository is a comprehensive educational cookbook for building with Anthropic's Claude API and Agent SDK. It contains over 60 Jupyter notebooks demonstrating capabilities such as classification, retrieval-augmented generation (RAG), summarization, text-to-SQL, knowledge graph construction, content moderation, tool use, multimodal processing, extended thinking, and agent orchestration. The repo also includes production-oriented hosting patterns (Docker, Kubernetes, Modal, Cloudflare Workers) for deploying agents, and extensive evaluation frameworks using promptfoo with custom Python evaluators (BLEU, ROUGE, LLM-as-judge). While primarily a tutorial collection, it exhibits hybrid characteristics with reusable infrastructure code for agent hosting, content moderation pipelines, and notebook validation. The codebase is actively maintained with CI/CD workflows, but relies on beta APIs and hardcoded model names that introduce technical drift. Data assets are synthetic but realistic, enabling reproducible demonstrations of Claude's capabilities.
This repository provides a stealth browser automation MCP (Model Context Protocol) server that offers undetectable control over real browser instances (Chrome, Chromium, Edge) via the Chrome DevTools Protocol (CDP) and the `nodriver` library. It exposes 97 tools across 11 sections including navigation, DOM interaction, element extraction (styles, structure, events, animations), network interception and modification (including dynamic Python-powered hooks), CDP command execution, cookie management, tab control, and proxy forwarding with authentication. The architecture is a FastMCP-based server with singleton managers for browser instances, network interception, element cloning, and process cleanup. It supports stdio and HTTP transports, Docker deployment, and optional bearer auth. The system is designed to bypass anti-bot detection (Cloudflare, CreepJS, login walls) and is used for scraping, testing, and AI agent automation. While the codebase is well-structured and the functionality is comprehensive, there is some code duplication across multiple element cloner implementations and technical drift risk due to tight coupling with CDP APIs and the `py2js` transpiler dependency.
This is a Claude Code plugin and resource library, not a deployable application or data pipeline: 27 slash commands, 9+ autonomous skills, 3 auditor subagents, and extensive prompt-engineering documentation that extend the Claude Code CLI. In production, the system functions as configuration-as-code content consumed by the Claude Code runtime — teaching the assistant how to create executable plans (PLAN.md is the prompt itself), chain meta-prompts, build MCP servers, manage subagent orchestration, run autonomous coding loops (the 'Ralph' technique), and apply iOS/macOS development expertise. The only real executable code is a handful of self-contained scripts: a TypeScript CLI for The Pirate Bay API, Python/TypeScript MCP server templates, project scaffolding shell scripts, and autonomous loop iteration scripts. The dominant architectural pattern is the 'router skill': a SKILL.md entry point with essential principles, an intake gate, a routing table, and progressive disclosure into workflows, references, templates, and scripts — implemented consistently across all skills with pure XML prompt structure and checkpoint-based plan execution. Despite being classified as an application (there is no data-research character — no notebooks, datasets, or pipelines), its substance is largely authored content rather than software. The craft is strong: consistent XML schemas across files, a genuine QA layer (skill-auditor agents), secret hygiene practices, and a well-developed checkpoint/auth-gate protocol for safe automation. However, the repo carries real drift risks: duplicated reference files (research-pitfalls.md, cli-observability.md are copied across skills), dangling references to not-yet-created files, tight coupling to Claude Code's evolving plugin API, version-specific Apple platform guidance that will age, and the included The Pirate Bay skill which depends on a fragile third-party API and presents a content-policy concern. An engineer seeking to reuse this should extract the self-contained templates and scripts (MCP server scaffolding, loop automation) and treat the reference material as opinionated prompt guidance rather than canonical documentation.
This is a self-contained tool for detecting third-party AI API model substitution by analyzing the statistical fingerprint of random number generation. The backend is a Python proxy server (http.server) that forwards requests to OpenAI/Anthropic endpoints, handles GitHub baseline retrieval with caching, and provides an auto-update mechanism. The frontend is a single HTML file with embedded JavaScript (no bundler) that handles all user interaction: calibration of official models, testing of unknown channels, quick one-click verification against pre-downloaded baselines, and multi-channel comparison. The tool uses cosine similarity and Jensen-Shannon divergence to compare distributions, with special handling for model-specific parameters (max_tokens vs max_completion_tokens). The code is functional and well-organized for a single-developer tool, but lacks modularity (everything in one HTML file, backend in one script) and has no test suite. The baseline data files are precomputed artifacts, not part of a live data pipeline.
This repository is an interactive educational resource (Jupyter notebooks) teaching prompt engineering for Anthropic's Claude LLM. It is not a software application or a data pipeline; it is a notebook collection, so it is classified as data_research by the notebook signal, but its 'data' is synthetic/demo content (animal names, user/product records, arithmetic operations, legal tax code excerpts) used to illustrate prompt patterns. The primary entry points are the notebooks themselves, with parallel implementations for the Anthropic direct API and AWS Bedrock (both boto3 and anthropic Bedrock clients). Lessons progress from basic prompt structure, clarity, system prompts, XML tags, few-shot examples, step-by-step thinking ('Precognition'), output formatting, avoiding hallucinations, to complex/industry use cases. The notebooks use get_completion wrappers around client.messages.create(...), %store magic to share variables, and a tool-use appendix that implements prompt-injected function calling via XML-like tags and regex parsing. Exercises include golden answers and rubric-based grading (e.g., summary quality scored 1-5). Reusable patterns include the tool-use prompt-injection function construct_successful_function_run_injection_prompt(invoke_results), system-prompt composition (general tool-use explanation + specific tool definitions), and a grader prompt pattern. However, the code is tightly coupled to notebook execution order, API details may drift, and duplicated content across anthropic/boto3 notebooks creates maintenance risk.
This repository is a Claude Code plugin and design system library for generating zero-dependency HTML presentations. It provides a structured workflow (SKILL.md) for an AI agent to create single-file slide decks with inline CSS/JS, featuring 34+ curated design templates (bold-template-pack) with detailed color palettes, typography scales, component definitions, and CJK internationalization guidance. The core runtime component is a reusable `<deck-stage>` web component that handles slide navigation, keyboard controls, auto-scaling, print support, and speaker notes. Supporting scripts enable Vercel deployment, PDF export via Playwright, and PowerPoint-to-JSON extraction. The repository is primarily a design specification library consumed by an AI coding agent, not a standalone application. It exhibits a hybrid nature: the templates are extensive design documentation (not executable code), while the plugin infrastructure and web component are functional code. The design philosophy emphasizes anti-generic aesthetics, fixed 16:9 stage scaling, and progressive disclosure of supporting files. Notable duplication exists between root and plugin paths, and all templates are marked alpha.
EvoNexus is an AI-powered business operating system with a dashboard for managing various applications and services. It has features for managing systems, knowledge base, and user authentication, and uses Docker for containerization.
KEA Research is a full-stack multi-provider AI research chat application. The backend is a FastAPI service backed by SQLite/SQLAlchemy, exposing chat, admin, health, user, and TTS endpoints. The frontend is an Astro + TypeScript single-page app that stores chat history and pipeline data in IndexedDB, with a Bootstrap-based UI. Deployment is containerized via Docker Compose with nginx handling TLS and SSE-friendly proxying. The core product logic is a four-step research pipeline: initial multi-provider responses, Mixture-of-Agents refinement, peer evaluation, and a final KEA synthesis with facts, consensus, flagged claims, rankings, and confidence scores. A web admin panel manages providers, models, provider sets, users, and app settings, while the frontend supports research layers, bookmarks, notes, drafts, export, attachment ingestion, and text-to-speech via a Kokoro ONNX model.
Vizra ADK is a retired Laravel package (final release v0.0.48) that provides a comprehensive framework for building AI agents with LLM orchestration, tool systems, memory, workflows, evaluations, tracing, and MCP integration. It is not a standalone application but a library designed to be installed into Laravel projects. The architecture follows Laravel package conventions: service providers, facades (Agent, Workflow), Eloquent models, Artisan commands, Livewire components, and database migrations. Key entry points include the Agent facade for running agents, the Workflow facade for orchestrating multi-agent workflows, and a set of CLI generators for scaffolding agents, tools, and evaluations. The system supports multiple LLM providers via Prism PHP, persistent memory (session, user, vector), tool chaining, sub-agent delegation, and an evaluation framework with LLM-as-a-Judge assertions. The codebase is well-structured with strong test coverage (Pest + Mockery), but the package is officially retired with no further development, leading to high technical drift as dependencies age out. Despite retirement, many components (e.g., ToolChain, VersionablePrompts, AgentVectorProxy, HasLogging) are self-contained and demonstrate reusable patterns suitable for extraction into new projects.
This repository serves as a comprehensive documentation project that provides deep-dive insights into the architecture, internals, and usage of various AI-powered CLI tools. It documents five specific tools: Claude Agent SDK, Gemini CLI, Codex CLI, OpenCode, and Pi Coding Agent, offering detailed explanations of their internal workings, features, and integration patterns. The content is derived from direct source code analysis and aims to fill the gaps in official documentation. The repository is structured with dedicated directories for each tool, following a standardized numbering convention for topics (e.g., 01-overview, 02-technical-stack). It also includes specialized extraction sections for the Claude Agent SDK, breaking down its subsystems into individually documented 'complete' files. This approach demonstrates a reproducible pattern for knowledge extraction from complex software systems. While the repository excels in organizing and presenting technical information, it relies on external source code for its content and does not include the analysis scripts or raw data used to generate the documentation. This makes reproducing the exact analysis challenging, though the documented versions of each tool are specified. The documentation faces a high risk of becoming outdated due to the rapid evolution of the underlying AI CLI tools.
This repository is primarily a large collection of GPT prompt templates (markdown files) designed for use with AI chat platforms like FlowGPT or gptcall.net. Each prompt file defines a specific role or task for the AI, such as a resume editor, coding tutor, fitness planner, or creative writing assistant. The repository also includes an Android application (OpenClaw and Codex) referenced in the README, along with Node.js scripts (update.mjs, db.mjs) for managing the prompt data. The prompts are structured with placeholders for user input and often request specific output formats, enabling users to import them into chat interfaces to obtain specialized AI behavior without crafting prompts from scratch. While the prompt library is extensive, it contains significant duplication, minimal-effort entries, and some policy-risking content (e.g., jailbreaks, NSFW role-play), which affects overall quality and reuse potential.
The ZeroClaw-Android repository is an archived Android application project that was intended as an experiment to create a home for AI agents on Android. The README explicitly states the project is archived due to scope concerns and safety issues with the largely AI-generated codebase. No actual source code is visible in the provided file tree beyond the README and a ZIP archive (ZeroClaw-Android-main.zip) whose contents cannot be inspected. The repository consists almost entirely of Git metadata, indicating the source code is not directly accessible for analysis. Without access to the application code, it is impossible to assess architecture, functionality, or code quality. The project is marked as abandoned with no maintenance activity.