workflowstacks
mcp-server

piyaz: Seamless Human‑AI Collaboration for Every Project

piyaz lets founders coordinate people and AI coding agents in a shared workspace, streamlining development and project management for tech teams.

From the repo · “The agentic workspace where people and AI coding agents work together on every project.”

196 stars18 forksTypeScriptGuide quality 8/10 · reviewed Oct 22Updated 10/23/2026100% free · open source
What it does

Piyaz provides an agentic workspace where human founders and AI coding agents collaborate on projects, streamlining startup project management.

When to use it
  • •When you need to automate repetitive coding tasks in your startup project
  • •When you want to leverage AI assistance for coding and project management
  • •When you're looking for a collaborative workspace for human and AI agents
Ready-to-paste prompt
Explore the Piyaz GitHub repository for examples of AI-assisted project management, such as collaborating on a new feature with `git branch feature/new-feature`
Heads up: Ensure you have Node.js and TypeScript installed on your system, as Piyaz is built with TypeScript and may require specific versions for compatibility
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/piyaz && curl -fsSL https://workflowstacks.com/api/skills/piyaz/claude-skill -o ~/.claude/skills/piyaz/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How piyaz: Seamless Human‑AI Collaboration for Every Project works
Codeflow
Free to inspect

Piyaz: Seamless Human‑AI Collaboration for Every Project is a very large TypeScript project (~105k lines across 551 code files, plus 233 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, AGPL-3.0 license, has a test suite.

Size
Very large codebase
~105k lines · 551 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 32 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Node.js · Docker
TypeScript 97%PLpgSQL 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    lib/db/index.ts
    Inside lib/ — the main logic begins here
What's in each folder
lib/Core code — the actual logic226 files
app/Core code — the actual logic88 files
components/Frontend / UI174 files
plugins/Sub-packages / plugins79 files
drizzle/Folder37 files
scripts/Helper scripts16 files
docker/Deployment / infrastructure9 files
hooks/Hooks — scripts that auto-run on events9 files
READMEHas testsDocumentedCI checksDocker readyAGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
FrkAk
Language
TypeScript
Category
mcp-server
Published
4/6/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/piyaz.svg)](https://workflowstacks.com/skills/piyaz?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 373,977
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,600
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 133,734
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 400
vigil
Vigil: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.
mcp-server★ 83,449
LobeHub: 24/7 AI Team Management
Founders get organized AI operations with LobeHub. For startup founders managing AI teams.
mcp-server★ 4,022
Rapid-MLX: Supercharge Local AI on Apple Silicon
Rapid-MLX gives founders a lightning‑fast, OpenAI‑compatible engine for Mac M1/M2 chips—4.2× quicker than Ollama with instant tool calling. Ideal for AI‑driven product prototypes. 4.0k+ GitHub stars.