Art & Design

🗺️ Think like a software architect, not just a coder — 21 architecture maps (incl. AI gateway, RAG, agents, inference serving, vector DB) + a language-agnostic system-design tutorial. Every template links to real open-source prototypes. 中英文双语。

Open-source reference files from the Builder's Playbook — CLAUDE.md, AGENTS.md, docs/sdlc.md, docs/product/contribute.md, .claude/skills/debug/SKILL.md, design/redesign-prompt.md. Synced from the (private) betonKemon repo by scripts/sync-companion.mjs.

Manage Ollama models and monitor system resources with this terminal-based interface designed to streamline your LLM workflows.

Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.

Build a scalable business using an open-source operating system. Apply proven framework files to your AI assistant for better decision-making and execution.

MCP server for Telegram with dual-mode support: Bot API (httpx) for quick bot integrations and MTProto (Telethon) for full user-account access.

Build stateful multi-agent workflows in Java — with graphs, retries, and persistence

ErgoLogix is an AI-powered, preventative workplace wellness companion designed specifically for software developers and remote students who spend massive stretches of time at their desks. The application serves as a smart, personal physical therapist by connecting real-time workflow telemetry with predictive machine learning.

re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better than plain language. Built for mid-to-high complexity tasks, featuring a Bypass branch to execute simple prompts directly without added cognitive overhead

Linux-native multi-agent terminal — GTK4/libadwaita + VTE shell, local Unix-socket API, first-class git worktrees, prompt-aware notifications. AGPL-3.0, alpha.

Visualize and manage your Hermes agent fleet through a unified browser dashboard for streamlined orchestration and task delegation.

Execute Python code in Blender from any MCP client using a local server for real-time scene control and bpy automation.

API documentation for Xquik - all-in-one X automation with 120 REST API operations, 2 MCP tools, 23 extraction types, HMAC webhooks, and SDK guides.

Edit and refine Codex context files through a local visual interface to maintain accurate AI model inputs and improve code generation results.

Build durable iMessage AI agents using Nitro, Chat SDK, and Vercel Workflow for reliable message routing and automated responses.

Equip LLMs with specialized Splunk knowledge for architecture, SPL development, administration, and Enterprise Security operations.

Curate a list of bootstrapped and pre-seed AI products built by independent founders.

MCP server for Fitbit — query daily activity, heart rate, sleep, and body data from your Fitbit account in any MCP-compatible AI client (Claude, Cursor, etc.).

🛡️ Professional AI Logic Hub: Accumulate, verify, and reuse high-quality code assets via MCP. Built for human liberation from mundane tasks.

CLI tool for PEC (certified email) — built for AI agents and developers

Local-first nutrition MCP for AI agents: food search, barcode/image lookup, meal logging, hydration, goals and Telegram/Hermes workflows.

MCP server for WHOOP — recovery, strain, sleep, and HRV data for AI agents via Model Context Protocol. Built for self-quantified humans.

Standalone observability dashboard and developer playground for the Laravel AI SDK. Zero build steps. Telescope for your AI agents.

An AI dev agent built local-first. It gives your models direct access to your codebase, file system, and developer tools, turning them from chat assistants into active developers that actually get things done. Works with various providers, just like Claude Code, but private and fully under your control.