AI Assistant

"Create a workflow that monitors GitHub PRs and posts to Slack when they're approved"

I've created a workflow with 3 nodes: GitHub webhook trigger, approval filter, and Slack notification. You can drag to reposition or click nodes to configure.

GENERATED NODES

GitHub Webhook

Filter: Approved

Slack Message

GitHub

Webhook Trigger

Event: pull_request.review

Filter

Condition Check

state == "approved"

Slack

Send Message

Channel: #dev-team

Bi-directional sync active • Changes reflect in code instantly

5

User Personas Supported

30-94%

Cost Savings vs Single-Model

10+

Built-in MCP Integrations

U

You 2 min ago

Help me implement JWT authentication for my Express.js API. I need signup, login, and a protected route middleware.

HC

Horns Code 2 min ago

I'll help you implement JWT authentication. Let me first check your project dependencies.

Read: package.json Completed

Found: express@4.18.2, mongoose@7.0.3
Missing: jsonwebtoken, bcryptjs

Installing required packages:

npm install jsonwebtoken bcryptjs Completed

+ jsonwebtoken@9.0.2
+ bcryptjs@2.4.3
added 2 packages in 1.2s

Here's the authentication middleware:

middleware/auth.js

const jwt = require('jsonwebtoken');

const authMiddleware = (req, res, next) => {
  const token = req.header('Authorization')
    ?.replace('Bearer ', '');

  if (!token) {
    return res.status(401)
      .json({ error: 'Access denied' });
  }

  try {
    const decoded = jwt.verify(
      token,
      process.env.JWT_SECRET
    );
    req.user = decoded;
    next();
  } catch (err) {
    res.status(401)
      .json({ error: 'Invalid token' });
  }
};

module.exports = authMiddleware;

✅ I've created the auth middleware. Would you like me to create the login/signup routes as well?

❯

Dual-Mode Interface

Switch between visual workflow builder and code mode instantly. Bi-directional sync keeps both in perfect sync - an industry first.

Multi-LLM Cost Optimizer

5 providers: Gemini, GPT-4o, Claude, Llama, DeepSeek. Route tasks to optimal models for 30-94% cost savings vs single-provider tools.

MCP Marketplace

10 built-in: GitHub, Slack, PostgreSQL, Stripe, SendGrid, Zapier, Twilio, AWS S3, Docker, Jira. Plus unlimited community extensions.

Multi-Persona Platform

Product Managers, Designers, QA, Developers, Analysts - everyone on your team can contribute. Visual mode for non-coders, code mode for devs.

Self-Hosted & Secure

Docker deployment, on-premise, air-gapped options. Full data sovereignty for HIPAA, SOX, and government compliance requirements.

Zero Vendor Lock-in

Export everything - full code ownership with no proprietary formats. Your workflows, your code, your data. Leave anytime with complete portability.

Unlike single-model tools: Switch AI providers based on task complexity and budget. Unlike no-code platforms: Full code transparency - see and edit generated code anytime. Unlike cloud-only solutions: Self-hosted option keeps sensitive data in your infrastructure.

G

Gemini 2.0 Flash

Fast multimodal model • 1M context • $0.10/M tokens

Default

O

GPT-4o

Complex reasoning • 128K context • $2.50/M tokens

C

Claude Sonnet 4

Nuanced coding • 200K context • $3/M tokens

🦙

Llama 3.3 70B

Run locally via Ollama • Complete privacy • Free

Local

D

DeepSeek V3

Cost-effective • 64K context • $0.14/M tokens

Self-Hosted

Free

Docker deployment

All 5 AI models
Visual + Code modes
MCP marketplace
Community support

Pro

$29/mo

Cloud hosted

Unlimited requests
All AI models
Priority support
Custom prompts

Team

$99/mo

Real-time collaboration

Everything in Pro
Shared workspace
WebSocket collab
Admin controls

Enterprise

Contact

On-premise / VPC

SSO / SAML
HIPAA / SOX ready
Air-gapped option
SLA guarantee

Multi-LLM Cost Savings: Route simple tasks to Gemini Flash ($0.10/M tokens) and complex tasks to GPT-4o ($2.50/M tokens). Average teams save 70-90% vs fixed-pricing tools.

Horns Code

What Makes Horns Code Different