thehardwarestore.ai

oh-my-openagent (omo) is a massive, actively-developed TypeScript monorepo that ships as a multi-harness AI-agent orchestration plugin. Its production function is to instrument coding-agent runtimes (OpenCode, OpenAI Codex CLI, and adapters for Claude Code and other harnesses) with a rich layer of lifecycle hooks, background agents, multi-model routing, LSP/AST tooling, team-mode parallelism, and a curated prompt system — all installable via a single `bunx oh-my-openagent install` or `npx lazycodex-ai install` command. The architecture is a workspace of 20+ pure-TypeScript core packages (model-core, rules-engine, skills-loader-core, team-core, tmux-core, delegate-core, hashline-core, lsp-core, mcp-client-core, etc.) that are consumed by two main adapter packages: `omo-opencode` (the full-featured OpenCode plugin with 11 agents, 54+ hooks, team mode, ultrawork/ULW loop, background agents, Codegraph MCP, etc.) and `omo-codex` (a lightweight Codex CLI plugin that vendories a subset of components — rules, comment-checker, LSP, git-bash, ultrawork, ulw-loop, telemetry — as isolated Codex components). A large shared-skills layer provides cross-harness SKILL.md files for programming languages, frontend design, ultimate browsing, debugging, and more. The codebase is notable for its aggressive package layering refactor (documented in ROADMAP.md), its strict no-excuse TypeScript policy, extensive automated QA evidence (.omo/evidence/), and its depth of agent-facing features like hash-anchored edits, prompt-async-gate, runtime fallback with model-suggestion retry, and the start-work/ULW-loop goal orchestration systems. With 64K stars, daily commits, 790 open issues, and a sprawling CI matrix, it is one of the most ambitious open-source agent-orchestration projects in maintenance today.

Understand Anything is a developer tool that analyzes codebases to create interactive knowledge graphs for code comprehension and onboarding. It combines deterministic static analysis (using tree-sitter) with LLM-powered semantic understanding to build explorable graphs of files, functions, classes, dependencies, and business domains. The system features a multi-agent pipeline for analysis, incremental updates via fingerprinting, and a React/Vite dashboard for visualization with guided tours, semantic search, and diff impact analysis. The architecture follows a monorepo structure with pnpm workspaces separating core analysis engine, dashboard UI, and plugin interface. Key capabilities include language-agnostic structural analysis across 30+ programming languages, business domain extraction, knowledge base analysis (Obsidian/Logseq-style wikis), and multi-platform support for AI coding assistants (Claude Code, Codex, Cursor, Copilot). The system operates offline for structural analysis while optionally leveraging LLMs for enrichment, with persistence to a .ua/ directory for team collaboration via version control.

planning-with-files is a persistent, file-based task-planning system for AI coding agents. It maintains task_plan.md, findings.md, and progress.md on disk and wires into agent lifecycle hooks (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, PreCompact, Stop) across Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, Pi, Hermes, and a dozen other assistants, re-injecting plan context into the model's context window on every turn. Plans survive context loss, /clear, compaction, and crashes; a session-catchup mechanism recovers prior transcripts. A v3 gated mode can block the agent from stopping until plan phases complete, backed by an append-only JSONL run ledger, stall detection, and SHA-256 plan attestation that makes hooks refuse to inject tampered content. Architecturally it is a distribution hub rather than a single application: a canonical skill under skills/planning-with-files is mirrored byte-identical into 15+ IDE-specific directories, with native TypeScript plugins (OpenCode, Pi, DSH), a Python plugin (Hermes), and shell/PowerShell hook dispatchers. Plan resolution is a fail-closed chain (PLAN_ID env → .active_plan pointer → newest plan dir → legacy root) guarded by slug validation, containment checks, symlink/junction rejection, and strict PWF_PLAN_ROOT pinning. The engineering is unusually rigorous for an agent-skill repo: 400+ pytest tests, byte-parity tests between shell/PowerShell/Python/TypeScript twins, a PATH-stub BSD userland simulation to catch GNU-only flags that silently fail on macOS, and heavy Windows PowerShell 5.1 / Git Bash portability hardening. Non-obvious patterns include KV-cache-stable injection output (no timestamps or free text in summaries, wall-clock normalization to T00:00:00Z) and an mtime-keyed attestation cache for performance. The repository is a developer tool, not a data/research project; although it ships benchmark and eval documentation (assertion pass rates, recovery-turn comparisons), those are verification evidence for the skill, not analysis artifacts. It is actively maintained at v3.24.0 with recent commits, 4 open issues, and 100+ releases; technical drift is low, with the main maintainability risk being deliberate duplication across 20+ canonical mirrors, mitigated by sync-ide-folders.py and parity tests but still a possible source of silent drift.

NanoClaw is a self-hosted, multi-agent AI orchestration platform that runs containerized agent sessions, integrates with a wide range of chat channels (Slack, Discord, Telegram, WhatsApp, iMessage, etc.), and provides a CLI-based admin interface. It is architected as a host service (Node.js/TypeScript, SQLite) that manages per-session agent containers (Bun runtime) isolated via Docker. The system features a typed guard/approval system for privileged actions, a plugin-based skill system for extensibility, and a structured migration framework for database schema evolution. Key operational flows include inbound message routing from channel adapters, session lifecycle management with two-DB mailbox split (inbound/outbound SQLite), container orchestration with credential injection via OneCLI vault, and host sweep for periodic maintenance. The CLI (`ncl`) provides resource CRUD with hooks, command guard integration, and a socket-based transport protocol. The project emphasizes a small, auditable codebase, skill-based feature installation over configuration, and deterministic setup/upgrade workflows with Claude Code fallback for error recovery.

drawio-skill is a comprehensive AI agent skill for generating, editing, synchronizing, inspecting, testing, and publishing editable draw.io diagrams from natural language, codebases, infrastructure-as-code, and data schemas. It provides a unified CLI (`diagramctl.py`) orchestrating a pipeline of 39+ specialized scripts covering importers (Python, JS/TS, Go, Rust, Terraform, K8s, Docker, SQL DDL, OpenAPI, CI pipelines), auto-layout (Graphviz, ELK, deterministic sequence/C4/tube-map), shape search (10k+ official icons), AI/LLM brand logos (321 brands), style presets, diagram diff, time-lapse, heat maps, and export (PNG, SVG, PPTX, Mermaid, HTML viewer). The architecture is centered on a versioned Diagram IR (JSON Schema) that separates meaning, provenance, and geometry, enabling incremental sync preserving manual layout, multi-view projection, architecture contract testing (Diagram-as-Test), what-if failure simulation, and accessible Story Mode. It integrates with agent platforms via a SKILL.md and an optional MCP server (`diagramctl_mcp.py`) exposing nine tools over stdio, and supports CI integration through GitHub Actions for PR diff and architecture test gates. The project is actively maintained with semantic versioning, 174 unit tests, and a changelog tracking releases through v3.2.0.

claude-mem is a persistent memory system for AI coding assistants, primarily targeting Claude Code but also supporting Codex, Cursor, Windsurf, OpenClaw, and other platforms. It captures observations, summaries, and user prompts from coding sessions via lifecycle hooks (SessionStart, PostToolUse, etc.), stores them in SQLite (local) or Postgres (server), and injects relevant context into future sessions to maintain continuity across agent interactions. The system operates as a background worker daemon (Bun) or a multi-user server (Express + BullMQ + Valkey) with API key authentication, team/project scoping, and rate limiting. Architecturally, claude-mem is a hybrid of a CLI plugin and a standalone server. The CLI component integrates into IDEs via hook scripts and MCP servers, while the server component provides REST APIs for memory management, search, and cloud sync. It features a dual-storage backend (SQLite for local, Postgres for server) with vector search via ChromaDB and full-text search via SQLite FTS5. The system includes a React-based viewer for browsing memory feeds, telemetry (opt-out PostHog), and a Cloudflare Workers-based sync hub for cross-device synchronization. The codebase demonstrates strong engineering practices with well-abstracted components (search strategies, provider abstraction, atomic file operations, telemetry scrubbing) but carries some technical debt from its dual-runtime evolution (legacy worker vs. server-beta) and extensive Windows-specific workarounds. It is actively maintained with frequent releases and comprehensive test coverage.

This repository is a curated resource hub (awesome list) for Claude Code skills, targeting Chinese-speaking developers. It contains 20 original SKILL.md files that can be directly installed into Claude Code, plus a curated directory of 441+ third-party skills organized by categories such as development efficiency, content creation, platform operations, and more. The repo includes a static website (docs/index.html) that mirrors the README, automated Python/Node.js scripts for synchronization, and rigorous CI/CD pipelines with pinned dependencies and comprehensive tests. It is not a running application but a content curation project with high-quality infrastructure for maintaining consistency between the README and the website, including atomic file writes and strict anchor validation. The original skills are well-structured and cover practical scenarios like code review, documentation generation, API testing, and refactoring, all in Chinese.

This is a VS Code extension that provides a unified interface for discovering, installing, and managing MCP (Model Context Protocol) servers and AI agent skills. It integrates with multiple sources: the Official MCP Registry, skills.sh, GitHub repositories, and CloudMCP (a hosted alternative). The extension offers a chat participant (`@mcp`) for natural-language search and install, and a sidebar webview with search and management tabs. It supports 30+ AI coding agents including GitHub Copilot, Claude Code, and Codex CLI. The architecture consists of a TypeScript extension backend (using esbuild for bundling) and a React 19 + Vite + Tailwind CSS + shadcn/ui frontend, communicating via typed RPC messages. Telemetry is collected anonymously with standardized error classification. The codebase is well-structured with clear separation of concerns, CI/CD pipelines, and unit tests.

Image-Blaster is a generative 3D asset pipeline and web viewer that transforms a single input image into a fully interactive 3D scene. The system uses Claude AI agents to orchestrate a multi-step workflow: image analysis and object extraction, background removal (plate generation), world generation via World Labs (gaussian splats, colliders, panoramas), 3D object generation via FAL (Hunyuan3D or Meshy), and sound effect generation via ElevenLabs. All generated assets are stored locally with a deterministic indexed naming convention and request metadata for resumability. The frontend is a React 19 + Three.js (R3F) application with physics (Rapier), post-processing (Bloom, DoF, motion blur), splat rendering (SparkJS), and a full scene editor with undo/redo, transform controls, and asset library. The architecture is a monorepo with a Vite dev server that serves assets and provides a CRUD API for scene projects. While the system is primarily an application, it also contains a data pipeline aspect in its asset generation scripts, which follow a consistent lifecycle of submission, polling, download, and metadata writing. The codebase demonstrates strong engineering practices with reusable patterns like the FAL queue wrapper, indexed file resolution, camera gesture hooks, and error boundaries. However, it is heavily dependent on external cloud APIs (FAL, World Labs, ElevenLabs) and Claude agent tooling, with no offline fallback or mock mode.

This repository is a curated collection of 177+ domain-specific scientific 'skills' for AI agents, following the Agent Skills standard. Each skill is a self-contained module providing a CLI tool, documentation, and tests for a specific scientific or technical task—ranging from single-cell RNA-seq analysis (scanpy) and molecular docking (diffdock) to clinical report validation and ISO standards readiness. The architecture is a monorepo of independent skills, each with its own scripts/, references/, assets/, and tests/. Skills are designed to be safe, bounded, and reproducible: they validate inputs before execution, enforce resource limits, avoid network access unless explicitly required, and produce structured JSON reports. The repository also includes a shared test infrastructure (skill_contract) and a meta-skill (autoskill) that can automatically propose new skills from screen activity. While primarily an application library for AI agents, it has strong data/research characteristics due to its heavy use of scientific data formats and validation of research artifacts.

This repository is a collection of Claude/Anthropic skills and platform documentation rather than a standalone application. It contains skill definitions (SKILL.md files), MCP server evaluation guidance, managed-agents documentation, and supporting tooling such as schema definitions and build scripts. The dominant character is developer-facing content and reusable patterns for building LLM agents, with some executable scripts for validation and report generation. It provides structured output schemas for evaluation pipelines (grading, benchmark, comparison, analysis), a validator hierarchy for XML/XSD-based skill files, and a security-conscious file I/O example in build-report-lite.mjs. It also documents managed agents, platform availability, and MCP best practices. The repository is not a data research project; there are no notebooks, data pipelines, or model training scripts. Maintenance is active, but technical drift is medium due to version-sensitive SDK references, manually maintained platform availability tables, and multiple language-specific examples that must be kept in sync. The code and schemas are generally well-structured and reusable, though some paths are hardcoded and some documentation is tightly coupled to generator scripts.

This repository implements a production-grade Google Maps business data extraction platform with multiple execution modes: CLI, web UI, REST API, AWS Lambda, and a self-hosted SaaS edition. The core scraping engine uses Playwright for browser automation and also supports a stealth HTTP fast mode. It extracts 36+ structured fields per business (name, address, phone, website, reviews, ratings, emails, coordinates, hours, etc.) and provides deduplication, grid-based area coverage, email extraction via website visits, and review parsing. The architecture is modular with packages for scraping jobs, runners (file, database, web, Lambda, SaaS worker), output writers (CSV, JSON, PostgreSQL, S3, custom plugins), job queuing via River, and a comprehensive admin dashboard with cloud provisioning on DigitalOcean and Hetzner. The system is designed for both single-user CLI use and multi-tenant SaaS deployments with authentication, 2FA, API key management, and scalable worker pools. The codebase demonstrates strong Go engineering practices with well-defined interfaces, dependency injection, and test coverage. Notable reusable components include cryptography utilities, HTTP server middleware, rate limiting, and a CLI prompt library. However, the repository has some maintenance concerns: two separate database migration sets for legacy and SaaS modes, in-memory deduplication that doesn't persist across restarts, committed test SSH keys in the `local/` directory, and a large dependency surface that could introduce version conflicts. The scraper logic is inherently brittle due to reliance on Google Maps internal data structures, which are subject to change without notice. For AI agent consumption: This is a powerful off-the-shelf scraping tool that can be deployed as a Docker container, AWS Lambda, or managed SaaS. It provides a complete API and web interface for managing scraping jobs, monitoring progress, and exporting data. The SaaS edition includes worker auto-provisioning, making it suitable for large-scale lead generation operations. The code is actively maintained with recent commits addressing performance and feature enhancements.

This repository is an 'awesome list' — a static Markdown index of externally hosted Claude Code skills, organized into 14 categories (documents, development, data, science, writing, learning, media, health, collaboration, security, utility, articles, and collections). It contains no source code, no executable skills, no CI/CD, and no tests. The production function is discovery: a human or AI agent reads the README to find third-party skill repositories, then clones or installs those skills separately. Architecture is a single README with external links plus a few embedded sponsor images. There are no data flows or APIs. The list is actively maintained with a recent commit and a large volume of open issues, indicating ongoing community input. The core value is the curation and categorization of 150+ external skills, not software engineering craftsmanship. Sponsored placements appear at the top, so it is not purely community-driven. Overall, a useful and well-organized directory, but with zero in-repo technical content.

This repository is a content-based Claude Code skill package rather than a conventional software service. It contains two agent skills — /tutor-setup and /tutor — that an LLM coding assistant executes using filesystem and WebFetch tools. tutor-setup scans a working directory, auto-detects whether it contains source code or documents, and generates an Obsidian StudyVault: concept notes, dashboards, exam-traps, and practice questions, with strict rules for source traceability, tag registries, wiki-linking, and folder conventions. tutor-setup operates through detailed phase models (D1-D9 for documents, C1-C9 for codebases), and codebase mode produces architecture maps, module notes, API surfaces, and onboarding exercises. tutor then reads that vault and runs interactive 4-question quiz rounds, updating concept-level progress files and a compact dashboard; it supports diagnostic, weak-area drill, section review, and hard-mode sessions, all governed by a zero-hint quiz design rule in references/quiz-rules.md. The implementation is almost entirely Markdown instructions plus two small Bash install/uninstall scripts; there is no compiled code, test suite, CI pipeline, or dependency manifest. The operational logic is prompt/instruction engineering that Claude Code interprets. External dependencies are Claude Code (or a compatible npx-skills-aware assistant), Obsidian for reviewing generated vaults, pdftotext/poppler for PDF extraction, and the assistant's built-in Read, Write, Edit, Glob, Grep, Bash, WebFetch, and AskUserQuestion tools. The data flow is unidirectional: source files in the CWD are scanned and extracted, transformed into StudyVault markdown, then quiz answers update concept files and dashboard aggregate stats. The skill enforces a CWD boundary to avoid accessing files outside the working directory. The strong point is unusually detailed and internally consistent procedural specification: mandatory source-content verification, per-topic coverage rules, tag registries, active-recall fold callouts, interlinking requirements, and self-review quality checklists. Weaknesses are the absence of automated tests/CI and versioned dependency pins, and behavior ultimately depends on the host LLM following prompt rules correctly. The README also references a different GitHub owner (RoundTable02) than the repository path (bevibing/tutor-skills), indicating a fork or repackage whose provenance should be verified before use. Overall, it fulfills its stated purpose well, and several Markdown modules are genuinely reusable as templates for other agent skills, study-vault generators, or adaptive quiz systems.

This repository is a curated collection of Claude skills—markdown instructions and supporting scripts that enable Claude (or any MCP-compatible agent) to perform a wide range of tasks, from document manipulation (DOCX, PPTX, PDF, XLSX) and GIF animation to web testing, MCP server building, and automation of hundreds of third-party SaaS services via Composio's Rube MCP. The repo is primarily a skill library with a standardized template for each skill, but it also contains several well-crafted Python libraries (e.g., easing functions, particle systems, OOXML validation frameworks) that are genuinely reusable. The architecture is modular: each skill lives in its own directory with a SKILL.md and optional scripts. The heavy reliance on external services (Composio, Rube MCP) and the massive duplication of templated skill documentation introduce maintenance risks, but the core utility scripts demonstrate solid engineering craftsmanship.

This repository is a curated suite of 152 Claude AI skills (76 builder + 76 paired checklist reviewer archives) for generating structured Excel workbooks across the automotive engineering lifecycle. Domains include ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, ASPICE, AUTOSAR, SysML/MBSE, diagnostics (UDS, DBC, ODX), calibration (A2L), quality tools (APQP, PPAP, FMEA), and program management. Each `.skill` file is a ZIP archive containing SKILL.md, Python generators/reviewers, references, and shared utilities. Builders produce multi-tab xlsx workbooks from JSON input; reviewers validate existing workbooks and emit compliance checklists with dashboards. The suite is maintained via an autonomous weekly cycle (plan, polish, docs, release), with status tracking, chain-contract audits, and known issue catalogs. While the concept is robust, many shipped skills suffer from documentation/code drift (advertised check counts mismatch actuals), silent failures (empty workbooks certified as compliant), and duplicated shared scripts across 152 archives.

This repository is a curated 'awesome list' of links to external Agent Skills repositories. It contains no application code, data pipelines, or executable software. Its sole function is to serve as a community-maintained index and directory. The README is meticulously organized by vendor and category, with contribution guidelines, quality standards, and a security notice. While it has no software components to extract, it is a highly effective and well-maintained directory for its domain. It is not a software application and has zero reusability as a codebase.