SenseNova-Skills is a composable collection of AI agent skills for office automation, built around the SenseNova model family. It provides production-grade capabilities for image generation and recognition, presentation (PPT) creation, Excel data analysis, deep research with structured evidence, and multi-source search (academic, social, code, finance). The skills are designed to run in Agent Skills-compatible runtimes (OpenClaw, hermes-agent) and are bundled into the Raccoon product for enterprise use. The architecture is modular: each skill is a self-contained directory with a SKILL.md manifest, scripts, prompts, and schemas. The deep research skill implements a multi-agent pipeline with formal JSON schemas and validators. The PPT skill has a multi-stage pipeline from user input to HTML-to-PPTX conversion via Playwright. The codebase demonstrates solid engineering with reusable components like a shared LLM/VLM client, export pipeline libraries, and validation infrastructure. However, it suffers from duplicated utility code across skills, complex environment variable fallback chains, hardcoded paths, and dependency on external APIs and headless browsers. The repo is actively maintained with biweekly reports and frequent commits.
PA Agent is a desktop application (PyQt6) that combines Al Brooks' price action theory with large language models (DeepSeek, MiMo, QClaw, etc.) to generate two-stage trading analysis: Stage 1 diagnoses market structure (cycle, pattern, direction), Stage 2 produces a trading decision (order type, entry, stop-loss, take-profit). The system ingests K-line data from multiple sources (MT5, TradingView, East Money, Tushare, AkShare) and provides real-time charting, AI reasoning streaming, decision tree visualization, and demo replay. It includes deterministic fallback nodes for data validation, direction voting, and pattern routing, reducing reliance on LLM output consistency. The architecture is modular with a data source abstraction, AI provider abstraction, event bus, incremental indicator computation, and a two-stage orchestration pipeline with retry and validation. While the codebase is well-structured and heavily tested (unit, integration, property-based), it suffers from complexity due to many provider connectors, hardcoded normalizer heuristics, and prompt engineering files that require ongoing maintenance.
This repository is an AI skill/prompt library for coding assistants (Claude, Cursor, GitHub Copilot, etc.). It contains a comprehensive security-focused markdown guide (SKILL.md) that AI assistants reference when generating code to ensure secure coding practices. The skill covers 60+ security vulnerabilities including IDOR, XSS, CSRF, SSRF, SQL injection, JWT misconfigurations, and more. It's designed to be installed in AI assistant skill directories to provide real-time security guidance during code generation. The repository has minimal structure - just three files (LICENSE, README.md, SKILL.md) with no traditional software components like tests, CI/CD, or package management. This is appropriate for its purpose as a static documentation resource for AI assistants. The security guidance is comprehensive and well-organized, covering both prevention strategies and common bypass techniques attackers use. Note: The last commit date (2026-02-17) appears to be in the future, which is unusual. The repository has 0 open issues and 94 forks, suggesting active adoption despite the odd timestamp.
This repository is the full-stack personal website of Max Stoiber (mxstbr.com), built with Next.js 16, TailwindCSS, and TypeScript. It serves a dual role: a public-facing blog and digital garden, and a private family productivity suite called 'MaxOS' that simulates a Windows 98 desktop environment. The public side includes MDX blog posts, Hashnode-synced notes, an RSS feed, and an investing page. The private side is a full-featured operating system shell with iframe-based apps: a calendar (with events stored in Redis), a finance portfolio tracker (pulling from Tiingo), a reminder system, a todo list, and a sophisticated chore management system (Chores2) for tracking kids' chores, rewards, and completions. The Chores2 subsystem is the most architecturally rich part of the codebase. It uses a layered domain-driven design with types, domain logic, commands, a service layer, a repository (with both in-memory and Redis implementations using compare-and-set transactions), MCP tool definitions for AI integration, and a notification outbox pattern for reliable Telegram delivery. The system supports time-window-based chore scheduling, period bonuses, approval workflows, and undo. It was recently rebuilt from a legacy version, with all features documented and verified in design docs. The codebase also integrates AI heavily: a Clippy chat assistant (powered by OpenAI) accessible via web and Telegram, and an MCP server that exposes tools for calendar, chores, and finance, enabling ChatGPT and other AI agents to read and mutate family data. The architecture is modern, with server actions, streaming, and Redis-backed state. However, the repo shows signs of being a single-developer project with some duplication (two active chore board UIs) and hardcoded secrets (parental PIN).
AgenticSeek is a private, local autonomous AI assistant built as an alternative to Manus AI. The system features a multi-agent architecture with six specialized agents (Casual, Coder, File, Browser, Planner, MCP) selected by a hybrid router using BART zero-shot classification and an adaptive few-shot classifier. It provides a React frontend, FastAPI backend with Celery, CLI with voice support, and Docker Compose orchestration for self-hosted services including SearxNG search and Redis caching. The codebase demonstrates solid engineering with clean abstractions for LLM providers (14+ options), tool execution, browser automation, and workspace isolation. It is under active development but shows signs of technical drift in deprecated components (llm_server, SerpApi-based web search) and fragile browser automation. The architecture is modular and contains several reusable patterns, though the codebase is tightly coupled to its specific agent system and has substantial external dependencies.
Entropic is a local-first desktop AI workspace built with Tauri and React. It provides a full desktop environment including chat with an AI agent, file management (Finder), web browsing, office document editing (OnlyOffice integration), voice control, task board with cron jobs, and an integration marketplace (OAuth for Google, Outlook, Slack, etc.). The application runs a sandboxed runtime (OpenClaw) inside Docker/Colima on macOS/Linux or WSL2 on Windows, ensuring secure execution of agent actions. Communication with the agent gateway happens via WebSocket with structured RPC frames. The system supports two modes: local API keys (user provides LLM keys) and managed proxy mode with hosted authentication and billing via Supabase/Stripe. The architecture is a monolith with separate microservices for browser automation (Playwright) and skill scanning (Cisco AI Defense). The frontend uses React 18, TypeScript, Vite 5, and Tailwind CSS 4, while the backend is Rust with Tauri v2 plugins for deep-link, updater, store, stronghold, and shell access. The codebase demonstrates strong engineering practices with reusable hooks for audio recording/transcription, a custom markdown renderer with workspace link support, and a resilient WebSocket client. However, some components are monolithic (Chat.tsx ~4000 lines, Files.tsx ~3000 lines) and there are hardcoded model lists and pricing that may drift over time.
OpenCrew is a multi-agent operating system designed to extend OpenClaw into a manageable AI team. It enables users to create specialized agents (Chief of Staff, CTO, Builder, CIO, Knowledge Officer, Operations, Research) that collaborate through messaging platforms like Slack, Discord, and Feishu. The system implements structured collaboration through role-based channels, thread-based task isolation, and agent-to-agent communication protocols. Key features include autonomy levels (L0-L3), task classification (QAPS), two-mode agent collaboration (delegation and discussion), and three-layer knowledge distillation. The application is actively maintained with recent updates focusing on cross-agent collaboration capabilities.
ChatClaw is a desktop AI assistant application built with Wails v3 (Go backend + Vue 3 frontend) that provides a local-first, multi-platform AI agent experience. It integrates with multiple messaging platforms (WeChat, QQ, DingTalk, Feishu, WeCom, WhatsApp) through gateway adapters and manages AI agents using the CloudWeGo Eino framework. The application features a knowledge base with full-text search (FTS5) and vector embeddings (sqlite-vec), document processing pipeline (parsing, splitting, RAPTOR hierarchical summarization), scheduled tasks with cron execution, a skill marketplace, MCP tool support, and native desktop capabilities like window snapping, floating ball, and text selection popups. It also bundles an OpenClaw Node.js runtime for advanced agent workflows. The frontend is Vue 3 with TypeScript, Pinia, and shadcn-vue UI components. The architecture is a monolith with service-oriented backend and multiple WebView windows. Note: The repo shows signs of hybridity as it includes substantial data/research components (RAPTOR, embeddings, document processing) but these serve the application's core functionality.
Continue is an open-source AI coding agent that provides chat, autocomplete, edit, and agent capabilities across VS Code, JetBrains IDEs, and a standalone CLI. The architecture centers on a shared TypeScript core (`core/`) that handles LLM interactions, context providers, tool definitions, indexing, and configuration management. This core is consumed by three frontends: a VS Code extension (`extensions/vscode/`), a JetBrains plugin (`extensions/intellij/`), and a CLI (`extensions/cli/`) with a React-based TUI. A separate React GUI (`gui/`) runs as a webview in the IDE extensions. The system supports 50+ LLM providers through a plugin architecture in `core/llm/llms/` and uses a YAML-based configuration system (`packages/config-yaml/`) with a Hub for sharing assistants. Codebase indexing uses a content-addressed Merkle tree approach with a Rust sync library (`sync/`). The repository is now read-only and deprecated as of the final 2.0.0 release, with the team recommending users migrate to the CLI.
This repository contains a cross-platform mobile application (iOS and Android) that functions as an AI assistant for Ray-Ban Meta smart glasses. The app connects to the glasses via the Meta Wearables DAT SDK to access camera and microphone streams, then provides various AI-powered features including real-time conversations (Live AI), image recognition (Quick Vision), food nutrition analysis (LeanEat), real-time translation, and experimental RTMP streaming. The architecture follows MVVM patterns on both platforms, with SwiftUI/Jetpack Compose for UI, ViewModels for state management, and service layers handling API communications with multiple AI providers (Alibaba Cloud, Google Gemini, OpenRouter). Key features include secure API key storage, Bluetooth audio routing for glasses microphones, and integration with external systems like OpenClaw. The application is actively maintained with recent commits and demonstrates solid engineering practices, though the multi-platform nature and reliance on external AI services introduce some complexity.
SYSTEM is an AI-powered macOS automation assistant enabling natural language control of Mac functions through a distributed architecture. It consists of a Tauri-based desktop app for local management, a CLI for setup/diagnostics, a local bridge server executing commands on the Mac, and a Cloudflare Worker serving as the AI agent using Anthropic's Claude. The system emphasizes privacy by keeping processing on user infrastructure, with secure Bearer token authentication between components. The architecture features a modular tool system where each capability (music, reminders, calendar, etc.) follows a consistent interface for easy extension. Communication occurs via HTTP/WebSocket: the UI sends requests to the Cloudflare Agent, which processes natural language with Claude and commands the local bridge. The bridge validates inputs, executes tools (using AppleScript/shell commands), and returns results. Real-time updates use WebSockets for scheduled tasks and notifications. Security is prioritized through command allowlisting, dangerous pattern blocking, and explicit macOS permission requirements. Key reusable components include secure command execution utilities and input validation patterns. The bridge server's validation and command modules isolate security concerns, while the tool interface pattern enables extensibility. The system is actively maintained with a pre-commit hook and low issue count, though distributed components risk drift. Dependencies show no known vulnerabilities (Dependabot Alerts: 0), but reliance on external services (Anthropic, Cloudflare) requires monitoring for API changes.
This repository implements a local AI assistant for Windows with a focus on privacy and offline operation. The application features a modern Qt-based GUI with multiple tabs for chat, planning, briefing, home automation, and web search. It includes a voice pipeline with wake word detection ('jarvis'), speech-to-text, intent classification via a fine-tuned FunctionGemma model, local LLM inference through Ollama, and text-to-speech using Piper TTS. Core functionalities encompass smart home control (TP-Link Kasa), calendar/task management, weather/news aggregation, and system monitoring. The architecture is modular, separating concerns into core services (LLM, router, function execution, voice assistant) and GUI components, with communication via Qt signals and slots. Data is stored locally in SQLite databases. The project demonstrates thoughtful engineering in areas like reactive settings management, model persistence for VRAM optimization, and reusable UI components, though it maintains some Windows-specific dependencies and tight coupling in certain areas.
This repository is the open-source CLI client for Amazon Q Developer (formerly CodeWhisperer), now deprecated in favor of the closed-source Kiro CLI. It is a Rust workspace with approximately 2000 files, building two main binaries: `q` (terminal chat assistant) and `qchat` (legacy chat binary). The codebase is dominated by auto-generated AWS SDK client crates (amzn-codewhisperer-client, amzn-codewhisperer-streaming-client, amzn-qdeveloper-streaming-client, amzn-consolas-client, amzn-toolkit-telemetry-client), which are Smithy-generated and checked in. Hand-written code includes the chat CLI interactive loop, an agent framework with MCP (Model Context Protocol) support, a semantic search client using local ONNX models (MiniLM) and BM25 indexing, authentication (OIDC with device grant flow), telemetry, and an OS abstraction layer. The architecture is essentially a monolithic CLI application with multiple supporting libraries. About 90% of the source files are generated code, which means the hand-crafted components are relatively small. The project was previously actively maintained but is now effectively archived; the README states only critical security fixes will be accepted.