thehardwarestore.ai

Macro is a large open-source monorepo (AGPLv3) for an all-in-one collaborative productivity platform that unifies email, messaging, documents, tasks, CRM, AI agents, and more. The backend consists of 42+ Rust microservices following a consistent hexagonal architecture (domain/inbound/outbound), with PostgreSQL, OpenSearch, Redis, S3, Kafka/SQS/EventBridge for data storage and event-driven processing. The frontend is a SolidJS single-page application with a heavily customized Lexical editor, block-based content system, real-time collaboration via CRDT (Loro), and Tauri-based desktop/iOS apps. AI is a first-class feature with agent harnesses, MCP integration, and an AI editing worker. Infrastructure is managed via Pulumi and Docker Compose for local development. The codebase demonstrates high engineering craftsmanship with consistent patterns, extensive testing, and comprehensive observability, though the sheer scale and volume of generated code introduce some maintenance overhead.

This Rust codebase is an LLM inference proxy and tool-routing gateway. It exposes an OpenAI-compatible HTTP API (`/v1/chat/completions`, `/v1/models`) and forwards requests to multiple upstream LLM providers (OpenAI, Anthropic via direct/Bedrock, Vertex AI, vLLM DeepSeek, TokenHub) through a unified Provider trait. A QUIC server (s2n-quic, TLS 1.3) accepts connections from serverless tools written in Go or Node.js; the agent loop performs multi-round tool calling, invokes registered tools, and streams results back in SSE format. A separate model API proxy layer handles non-chat endpoint shapes (messages, responses, generateContent) with usage extraction and injection. Architecturally, the system is a Rust CLI binary (`yomo`) with three subcommands: `serve` starts the HTTP API and QUIC zipper, `init` scaffolds serverless tool projects, and `run` launches a tool subprocess and connects it to the zipper. Tool registration is done at runtime over QUIC and stored in-memory, so state is lost on restart. The HTTP layer is Axum, auth is bearer-token, and observability uses OpenTelemetry. The serverless execution model is subprocess-based: it creates temporary directories, runs `npm install`/`go mod tidy`, and exchanges metadata over stdout. Reusable engineering exists in the framing protocol (`io`), streaming SSE mappers, usage aggregation logic, TLS configuration, and provider error separation. However, the provider implementations are duplicated and brittle to upstream API drift; hard-coded model limits, ephemeral tool state, and near-empty serverless stubs reduce long-term maintainability. No integration tests against real upstream APIs were found in the reviewed surface.

ClawScan is a Go-based CLI tool for composable security scanning of AI agent skills and plugins. It orchestrates multiple external scanners (e.g., Snyk, VirusTotal, Socket, AIG, Cisco, SkillSpector) against skill directories, collects raw evidence, and optionally feeds results to an LLM judge for evaluation. The tool supports profile-based configuration (built-in profiles like `clawhub` and `openclaw-install-policy`), Docker sandboxing, declarative gate rules for automated policy enforcement, and benchmark execution against datasets like SkillTrustBench and clawhub-security-signals. It is distributed via npm (`@openclaw/clawscan`) and GitHub Releases, with a rich CI/CD pipeline including automated runtime image builds, dependency updates, and a Hugging Face leaderboard for security signals research. While primarily an application, it has strong data/research elements through its benchmark infrastructure and leaderboard submission validation.

CCPM is a structured project management skill for AI agents (Claude Code, Codex, etc.) that enforces a spec-driven development workflow: PRD → Epic → GitHub Issues → Parallel Agents → Shipped Code. The codebase consists of markdown reference documents (plan.md, structure.md, sync.md, execute.md, track.md, conventions.md) and a set of deterministic bash scripts that read project state from .claude/ directory (PRDs, epics, tasks with frontmatter). The system does not contain any runtime code—it is purely a collection of instructions and helper scripts that an AI agent reads and executes. Its architecture is a flat skill structure following the agentskills.io standard, with no external dependencies beyond git, gh CLI, and a GitHub repository. The primary data flows are local file operations (creating/reading/updating markdown files) and GitHub API calls via gh CLI for issue creation, syncing, and closing. The skill is harness-agnostic and works with any compatible agent framework.

This repository is a curated, interactive learning roadmap for building AI agents. It is not a software library or framework, but a single-page web application (index.html) that renders a comprehensive todo list, project ladder, and curated resource collection. The application allows users to track progress via checkboxes stored in localStorage, take Markdown notes per stage, search content, toggle dark mode, and navigate via a sidebar. The underlying data is a static JSON structure embedded in the JavaScript. The repo's primary value is its meticulously organized learning path covering agent loops, tool use, RAG, multi-agent coordination, skills/protocols, browser agents, evaluation, and production deployment. It references dozens of high-quality external resources (official docs, papers, open-source projects) and provides clear learning principles. While the repo contains no runnable agent code, the interactive frontend is a well-crafted tool for self-paced learning. The codebase is a hybrid: it is an application (web UI) but its content is a curated research/learning resource.

This repository is a full-stack web application for AI-driven 3D modeling. Users describe a design in natural language, and an AI agent generates parametric OpenSCAD code or creates a 3D mesh. The system is production-grade: it uses React 19 + TypeScript with TanStack Router and Vite on the frontend, Supabase for authentication, storage, and database, and multiple AI providers (Anthropic, Google, OpenAI, fal.ai) for model generation. It supports parametric CAD (OpenSCAD compiled via WebAssembly in a Web Worker) and creative mesh generation (text/image to 3D via external APIs). The application includes billing via an external service, token-based usage tracking, conversation history with branching, public sharing links, and 3D model export (STL, OBJ, GLB, etc.). While primarily an application, the repository also contains a benchmarks directory (13 documented OpenSCAD models) that demonstrate the AI-to-CAD capability and serve as output artifacts rather than research pipelines.

Opensquad is a multi-agent orchestration framework that enables users to create, manage, and run teams of AI agents (squads) for automated content workflows. The system is primarily a CLI tool (`npx opensquad init`) that bootstraps projects with agent definitions, pipeline configurations, and IDE integrations. It includes a Phaser-based 2D dashboard that visualizes agents working in a virtual office, updated in real-time via WebSocket. The architecture is file-based: squads are defined as YAML/Markdown files in `squads/`, pipelines as step sequences with bash validation gates, and skills as self-contained directories with `SKILL.md` manifests. The framework supports multiple content formats (Instagram carousels, blog posts, email newsletters) through a best-practices catalog and platform-specific Sherlock investigators that extract real engagement data from social media profiles. Key entry points include `bin/opensquad.js` (CLI dispatcher), `src/init.js` (project initialization), `src/update.js` (core file updates), `src/skills.js` (skill registry management), and `src/agents.js` (agent management). The dashboard is a React + Vite app with a Phaser scene (`OfficeScene.ts`) that renders pixel-art sprites and desks. External dependencies include Node.js 20+, Playwright (for browser automation and image rendering), and various MCP services (Apify, Canva, Blotato, Resend). The system is designed for non-technical users and emphasizes zero-config setup, progressive disclosure of complexity, and token-efficient phased execution (discovery → investigation → design → build).

OysterWorkflow is an open-core desktop application (Electron + React) that records a user's computer activity via Screenpipe (screen, audio, UI events), then uses multi-stage LLM calls to extract reusable, structured 'skills' (workflow graphs) that AI agents (Codex, Claude, Hermes) can execute. The system provides a full lifecycle: capture → ingest → normalize → segment → LLM-based workflow discovery → skill extraction → workflow graph generation → quality evaluation → installation into agent skill directories → execution via MCP or Hermes CLI. It also includes a cloud sync layer (Supabase), a marketplace (ClawHub), and a local runtime HTTP server for the UI. Architecturally, it is a hybrid monolith with clear module boundaries: a desktop shell (Electron main process), a local runtime server (Express), a CLI (commander), a React UI (Vite + React Flow), and a product state layer (SQLite-backed with cloud sync). The codebase is TypeScript-first, ESM-only, and heavily tested (200+ test files). It demonstrates strong engineering practices: atomic file I/O, bounded child process management, immutable revision control for workflow graphs, and a sophisticated prompt registry with versioned inheritance. While primarily an application, it contains a significant data pipeline component (ingest → normalize → segment → LLM extraction) that could be considered a research-grade feature engineering system. The repo is actively maintained with frequent commits, CI, and issue triage. Notable risks include heavy sidecar bundling (Screenpipe, Hermes, ffmpeg), rapid prompt set version churn, and a mixed licensing model (Apache 2.0 open core + PolyForm Noncommercial for product code).

This repository is a community-curated awesome list for the Model Context Protocol (MCP) ecosystem, cataloguing hundreds of MCP server implementations, clients, frameworks, utilities, and tutorials. It is primarily a structured markdown documentation site with a consistent badge taxonomy (language, scope, OS), a deep category hierarchy, and multi-language translations. The repo contains no application source code or data pipeline; the only executable logic is a GitHub Actions workflow that validates pull requests adding new entries. The validation enforces formatting standards, allowed emoji tags, Glama badge requirements, duplicate link checks, and non-GitHub URL rejection, which keeps the list high-quality at scale despite its size. The repository serves as a discovery hub for engineers building with LLMs and agentic systems, making it a valuable reference asset rather than a runnable service. It is actively maintained, with recent commits, broad community participation, and a strong automation framework, though its value derives from curation quality rather than software craftsmanship.

This repository is a curated directory/registry of 5,300+ community-built skills for OpenClaw, an AI agent platform. It is not a software application — it contains no runtime code, no API, and no executable logic. Instead, it is a structured catalog of markdown files organized into 30+ categories (DevOps, Search & Research, Coding Agents, etc.), where each entry links to a skill hosted on ClawHub (OpenClaw's public skills registry). The repo functions as a discovery and navigation layer: users browse categories to find skills, and contributors submit new skills via pull requests validated by a CI workflow. The repository also documents filtering criteria (excluding spam, duplicates, low-quality, crypto, and malicious entries), security considerations (VirusTotal scanning partnership), and contribution guidelines. While it shares some characteristics with a data_research repo (structured metadata, no application code), it is best classified as a curated content registry — the 'application' label applies only in the sense that it is not a data pipeline or research project. Key patterns include a consistent category taxonomy, a PR validation workflow, and documented quality gates. The main risks are link rot (5,300+ external links with no automated checking), quality variance across entries, and the manual effort required to maintain a list at this scale.

CloakBrowser is a commercial stealth browser automation library that wraps Playwright (Python, JavaScript, .NET) with a custom patched Chromium binary. Its core purpose is to evade bot detection by spoofing browser fingerprints, providing human-like interaction (Bezier mouse moves, realistic typing with typos, smooth scrolling), and managing licensed binary downloads with cryptographic verification. The architecture is a multi-language SDK sharing identical logic across Python, TypeScript, and C#, with a common human interaction engine, proxy/GeoIP integration, and license enforcement via denial files and server validation. Key entry points are the `launch()` and `humanize()` APIs, CLI diagnostics (`info`, `login`, `install`), and the `cloakserve` CDP multiplexer. External dependencies include Playwright/Puppeteer, MaxMind GeoLite2 database, Ed25519 signature verification (BouncyCastle), and a license validation server. The codebase demonstrates high engineering discipline with extensive cross-language parity tests and security-conscious binary distribution, but carries drift risks from triple-language duplication and reliance on Playwright internal APIs.

Supermemory is a commercial-grade AI memory and context engine that provides persistent long-term memory for AI agents. The repository implements the client-side integration SDKs, an MCP (Model Context Protocol) server, a memory graph visualization component, and supporting infrastructure. In production, it connects to an external cloud API (api.supermemory.ai) that handles document ingestion, semantic search, user profiles, and knowledge graph construction. The codebase is organized as a monorepo with distinct packages for TypeScript/Python SDKs covering multiple AI frameworks (Vercel AI SDK, OpenAI, Mastra, Claude, etc.), a Cloudflare Workers-based MCP server with OAuth and widget UI, a ship-grade memory-graph React component with force-directed canvas rendering, and a comprehensive validation schema package. The architecture demonstrates strong engineering practices: strict Zod validation, middleware injection patterns, caching and deduplication logic, and thorough testing across languages. Notable skill is evident in the memory-graph canvas engine (viewport, simulation, spatial indexing, version chain visualization) and the shared memory-context injection utilities. The main downside is significant logic duplication across four Python SDK packages and their TypeScript counterparts, which increases maintenance risk. The repo is actively developed with CI/CD pipelines publishing to npm and PyPI.

PraisonAI is a production-oriented, multi-language AI agent orchestration framework shipped as a monorepo of cooperating Python, TypeScript, and Rust packages. The core SDK (`praisonaiagents`) implements `Agent`, `Task`, `AgentTeam`, and `AgentFlow`/`Workflow` abstractions with MCP support (stdio/HTTP/WebSocket/SSE), integration with 20+ LLM providers via LiteLLM-style configuration, memory backends (SQLite, file, mem0, MongoDB), RAG/knowledge bases over vector stores, guardrails, approval flows, policy engines, context compaction, telemetry, background jobs, and durable run ledgers. A user-facing `praisonai` wrapper provides a Typer CLI (`run`, `chat`, `code`, `serve mcp`, agent-as-API), bot adapters for Telegram/Discord/Slack via a WebSocket gateway, sandboxed compute (Docker, E2B, Modal, Daytona), deployment registries, cloud managed agents, and a fine-tuning package (`praisonai-train`). The repository is decisively an application/framework, though it carries data-research features as part of the product surface (RAG pipelines, evaluation loops, synthetic-data generation, LoRA fine-tuning), making it a hybrid in feature terms only.

CyberStrikeAI is a full-stack, AI-native cybersecurity operations platform designed for autonomous penetration testing and red teaming. It orchestrates multiple AI agents using the CloudWeGo Eino ADK framework to plan and execute complex security assessments. The platform manages its own C2 (Command & Control) infrastructure with encrypted beacons and listeners, integrates with over 100 security tools via the Model Context Protocol (MCP), and maintains a persistent knowledge base and project fact graph. It features a comprehensive governance layer including Role-Based Access Control (RBAC), Human-in-the-Loop (HITL) approval workflows, tool execution guards, and detailed audit logging. The architecture is a monolithic Go-like backend serving a web SPA, with plugins for Burp Suite and Chrome. It supports multi-agent orchestration modes (single, deep, plan-execute, supervisor), a graph-based workflow engine, and integrations with various chat platforms (WeChat, Discord, Telegram). The codebase demonstrates high craftsmanship in its execution governance, process isolation, atomic update mechanism, and database schema reconciliation. A significant technical concern is the use of a non-standard Go dialect (featuring `func`, `type`, and `map` literals) tied to the Eino framework. This creates a hard dependency on a specific toolchain and represents a major drift risk from the standard Go ecosystem, limiting portability and the ability to use standard tooling. Despite this, the project is actively maintained with extensive test coverage and a clear focus on production-grade security automation.

This repository is a curated 'awesome list' and comprehensive documentation hub for the Agent Skills ecosystem. It does not contain any executable application code, data pipelines, or machine learning models. Instead, it serves as a static directory of links to official projects (Anthropic, OpenAI, Google, Vercel, etc.), community-contributed skills, tutorials, and best-practice guides. The core value lies in its translated and aggregated documentation, including detailed guides on Skill design patterns, practical experience from Anthropic, and a complete build guide. It is a reference resource, not a software tool. Engineers and AI agents should use this repo to discover the Agent Skills specification, find relevant skills to install, and learn how to create their own. It is not a library or framework to be imported.

Claude Delegator is a Claude Code plugin that provides GPT (via Codex CLI) and Gemini (via Gemini CLI) as specialized expert subagents. It offers five domain experts (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst) that can advise or implement based on task requirements. The plugin uses MCP (Model Context Protocol) to connect to external CLIs, featuring sophisticated delegation logic with proactive triggers, session management (single-shot and multi-turn), and response synthesis. A key innovation is the zero-dependency Gemini MCP bridge that wraps the Gemini CLI in a standard MCP interface.

Debug-gym is a framework for developing and evaluating AI agents that perform interactive debugging of software. It provides a Gymnasium-inspired environment where agents can use tools like a debugger (pdb), file viewer, editor, and shell to inspect and modify code in order to fix bugs. The framework supports multiple execution backends (local, Docker, Kubernetes) to ensure isolation and reproducibility, and integrates with various LLM providers through a unified interface. The system is designed around a loop of observation, action, and feedback: the agent observes the current state (e.g., code, test output), selects a tool to apply (e.g., set a breakpoint, edit a file), and receives the outcome from the environment. This enables the creation of agents that can learn to debug or be evaluated on debugging benchmarks such as SWE-Bench and Mini-Nightmare. The framework also includes analysis tools for visualizing agent trajectories and logging experiment results, supporting both development and research use cases. Key architectural features include a plugin-based tool system, abstract terminal and LLM interfaces, and a secure workspace for code manipulation. These components are designed to be modular and extensible, allowing researchers and developers to plug in new tools, environments, or language models with minimal changes to the core loop.

The Eleven is a full-stack prediction market platform for live football events, deployed on X Layer (chain 196) using Uniswap v4 hooks. The system is powered by 11 autonomous AI agent personas (e.g., IlRegista, IlBomber) that monitor live match data from API-Football or Football-Data.org, evaluate binary propositions (e.g., clean sheet, corners over, next goal), and create markets via a commit-reveal mechanism. Markets are implemented as PropMarketHook contracts deployed through a factory using CREATE2. Users can stake on outcomes gaslessly via EIP-3009 signatures relayed by the x402-facilitator service, and markets are resolved deterministically after match events. The monorepo (pnpm workspaces) contains five packages: `contracts` (Foundry-based Solidity), `agent` (TypeScript runtime with Prisma persistence), `web` (Next.js 15 dApp with RainbowKit, Three.js 3D pitch, and Farcaster Frame v2 integration), `x402-facilitator` (standalone npm package for gasless USDT0 transfers), and `mcp-server` (MCP bridge exposing market tools to AI agents). The architecture is event-driven: the agent's TickLoop polls matches, emits deltas, and triggers market creation/reveal/resolution skills. The web app provides a full dApp experience including a markets list, agent detail views, a status page, and documentation. Key reusable patterns include a generic proposition template system with ABI encoding/decoding, a CREATE2 salt miner for hook deployment, a commit-reveal skill with cryptographic safety, and a gasless staking flow that can be extracted for any EIP-3009-compatible token. The codebase is well-tested (172 web tests, 229 agent tests, 85 contract tests with 100% coverage on the hook) and actively maintained with CI/CD via GitHub Actions and Railway deployment.

This repository is a comprehensive plugin and skill set for Claude Code (and compatible CLI assistants like Codex CLI and OpenCode), designed to transform the AI into a semi-automated research assistant for academic and software development workflows. It is not a standalone application but a configuration package that installs skills, commands, agents, hooks, and rules into the user's Claude environment. The architecture follows a skill-based pattern: each skill is a directory with a SKILL.md entry point, references, examples, and optional scripts, all consumed by the AI at runtime. The repository covers the full research lifecycle—ideation, literature review (via Zotero MCP and arXiv APIs), experiment analysis, ML paper writing with conference-specific LaTeX templates (NeurIPS, ICLR, ICML, ACL, AAAI), reviewer response drafting, publication chart creation, and post-acceptance promotion. It also integrates deeply with Obsidian for project knowledge management and includes a meta-toolchain for developing and QA-ing skills themselves. While primarily an application configuration, it contains substantial research-oriented content (Kaggle competition analyses, citation verification workflows, writing pattern references), making it a hybrid tool that bridges software engineering and data science research. The codebase is actively maintained, well-documented, and demonstrates strong craftsmanship in its script utilities and hook infrastructure.