ai-evals

verifywise: Streamline AI Governance & LLM Evaluations for Startups

Name: verifywise: Streamline AI Governance & LLM Evaluations for Startups
Author: verifywise-ai

A TypeScript platform that lets founders align LLMs with the EU AI Act, ISO 42001, NIST AI RMF and 20+ other standards—ideal for compliance‑focused teams.

From the repo · “Complete AI governance and LLM Evals platform with support for EU AI Act, ISO 42001, NIST AI RMF and 20+ more AI frameworks and regulations. Join our Discord channel: https://discord.com/invite/d3k3E4uEpR”

intermediate⏱ 30 minutes💵 Free

367 stars+2★ this week126 forksTypeScriptGuide quality 9/10 · reviewed Oct 12Updated 10/24/2026100% free · open source

What it is

Verifies and audits AI systems to ensure they follow regulations and guidelines.

Real use case example

"A founder, Alex, needs to deploy an AI-powered chatbot to her e-commerce website. She uses Verifywise to create a compliance report that meets EU AI Act requirements, ensuring her system is transparent, explainable, and trustworthy. To do this, she: uploads her AI model to Verifywise, selects the relevant regulations, and gets a customized report in minutes."

Best insideAny AI Client

When to use it

•When you need to ensure AI compliance for your startup
•When managing AI-related risks and implementing governance is crucial
•When your startup requires support for multiple AI frameworks and regulations

Ready-to-paste prompt

Verify EU AI Act compliance for a given AI model by examining the provided examples and documentation in the VerifyWise repository

Heads up: Ensure you have the necessary permissions and access to implement the required frameworks and regulations, as some may require specific licenses or subscriptions

Saves to your device

Use with Claude

New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/verifywise && curl -fsSL https://workflowstacks.com/api/skills/verifywise/claude-skill -o ~/.claude/skills/verifywise/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.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

273.4M

source size

Other

license

Key files

package.json

README.md

File tree

.claude/

.cursor/

.github/

.husky/

.zap/

agents/

AIGateway/

ansible/

BackendDocs/

Clients/

CodeRules/

docs/

EvalServer/

EvaluationModule/

GRSModule/

kubernetes/

observability/

scripts/

sdks/

Servers/

shared/

Software layers analysis/

tools/

.dockerignore

Use with Claude

New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/verifywise && curl -fsSL https://workflowstacks.com/api/skills/verifywise/claude-skill -o ~/.claude/skills/verifywise/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.

Quick Actions

Details

Creator

verifywise-ai

Language

TypeScript

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.