workflowstacks
mcp-server

AIHelms: Unified AI Control

Get unified AI management for your startup with AIHelms, supporting OpenAI and more.
1,015 stars102 forksVueGuide quality 8/10Updated 8/14/2026100% free · open source
What it does

AIHelms provides a unified AI management platform for startups, supporting multiple AI models and tools, including OpenAI, and offers features like cost control, ROI quantification, and security auditing.

When to use it
  • •When you need to manage multiple AI models from different providers in one place
  • •When you want to control and optimize the costs of using AI resources in your startup
  • •When you need to implement security and identity authentication for your AI assets
Ready-to-paste prompt
Configure AIHelms to use OpenAI by adding the following to your `config.js`: `{ openai: { apiKey: 'YOUR_OPENAI_API_KEY' } }`
Heads up: Ensure you have the correct version of Node.js installed, as specified in the `package.json` file, to avoid compatibility issues when running AIHelms
Saves to your device
Use with Claude
New

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

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/aihelms && curl -fsSL https://workflowstacks.com/api/skills/aihelms/claude-skill -o ~/.claude/skills/aihelms/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 AIHelms: Unified AI Control works
Codeflow
Free to inspect

AIHelms: Unified AI Control is a large Python project (~58k lines across 324 code files, plus 21 test files). Setup is light: runs with Docker — add your API keys to .env. Last commit this month, GPL-3.0 license, has a test suite.

Size
Large codebase
~58k lines · 324 code files · ~8 h to skim
Setup
Light setup
Runs with Docker — add your API keys to .env.
Runs on
Docker
Needs API keys (.env)
Python 48%Vue 45%TypeScript 6%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    apps/main.py
    Where the program starts running
  4. 4
    .env.example
    The API keys and settings you must provide
What's in each folder
ui/Frontend / UI342 files
apps/Sub-packages / plugins159 files
docs/Documentation8 files
docker/Deployment / infrastructure27 files
dev/Folder5 files
.claude/Editor / agent settings8 files
READMEHas testsDocumentedNo CIDocker readyGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
beizhu-1209
Language
Vue
Category
mcp-server
Published
5/9/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 242,984
ECC: Optimize Performance
Get optimized performance with ECC, a research-first agent harness system for founders working with AI agents and developer tools like Claude Code and Codex
mcp-server★ 154,417
Dify: Streamline Workflow
Get a production-ready platform with Dify. For founders needing agentic workflow development.
mcp-server★ 150,115
open-webui: Easy AI Interface
Get a user-friendly AI interface with open-webui, supporting Ollama and OpenAI API, for founders, with 145k+ GitHub stars
mcp-server★ 113,199
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…
mcp-server★ 106,674
gemini-cli: AI in your terminal
Get AI power with gemini-cli, for founders, 105k+ GitHub stars
mcp-server★ 82,036
LobeHub: 24/7 AI Team Management
Founders get organized AI operations with LobeHub. For startup founders managing AI teams.