convez.ai
AgenteDevOps & InfraestruturaAvançado
helixml

HelixML - Plataforma de Agentes IA Privada

helixml/helix

Agentes IA com stack GenAI privado, RAG e observabilidade completa

Ver no GitHub
BomPluginScore · de 0 a 100

Plataforma empresarial para construir e implantar agentes IA com suporte a RAG, integração de APIs, visão computacional e múltiplos provedores LLM. Oferece agendamento de GPU inteligente, orquestração de ferramentas multi-etapa e gerenciamento completo de conhecimento com rastreamento total de execução.

Instalação

$npx convez-ai helixml/helix

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
833
Forks
88
Acompanhando
8
Saúde
50%
Último commit
há 1 dia
Versão
2.12.61
Issues abertas
151
Contribuidores
28

Casos de uso

  • Construir agentes de suporte ao cliente a partir de documentação
  • Analisar documentos corporativos com RAG privado
  • Orquestrar workflows complexos com múltiplos LLMs e ferramentas
  • Alocar e gerenciar GPUs eficientemente para modelos de IA

Veredito

Solução robusta para organizações que precisam de agentes IA com controle total sobre dados e infraestrutura. A arquitetura de agentes com sessão, RAG integrado e observabilidade é completa, mas requer expertise em deployment e orquestração de GPUs.

README

A tradução para o português deste README ainda está na fila.

HelixML - AI Agents on a Private GenAI Stack

👥 Discord

Deploy AI agents in your own data center or VPC and retain complete data security & control.

HelixML is an enterprise-grade platform for building and deploying AI agents with support for RAG (Retrieval-Augmented Generation), API calling, vision, and multi-provider LLM support. Build and deploy LLM applications by writing a simple helix.yaml configuration file.

Our intelligent GPU scheduler packs models efficiently into available GPU memory and dynamically loads and unloads models based on demand, optimizing resource utilization.

✨ Key Features

🤖 AI Agents

  • Easy-to-use Web UI for agent interaction and management
  • Session-based architecture with pause/resume capabilities
  • Multi-step reasoning with tool orchestration
  • Memory management for context-aware interactions
  • Support for multiple LLM providers (OpenAI, Anthropic, and local models)

🛠️ Skills and Tools

  • REST API integration with OpenAPI schema support
  • MCP (Model Context Protocol) server compatibility
  • GPTScript integration for advanced scripting
  • OAuth token management for secure third-party access
  • Custom tool development with flexible SDK

📚 Knowledge Management

  • Built-in document ingestion (PDFs, Word, text files)
  • Web scraper for automatic content extraction
  • Multiple RAG backends: Kodit, LlamaIndex
  • Vector embeddings with PGVector for semantic search
  • Vision RAG support for multimodal content

Main use cases:

  • Upload and analyze corporate documents
  • Add website documentation URLs to create instant customer support agents
  • Build knowledge bases from multiple sources

🔍 Tracing and Observability

Context is everything. Agents can process tens of thousands of tokens per step—Helix provides complete visibility under the hood:

Tracing features:

  • View all agent execution steps
  • Inspect requests and responses to LLM providers, third-party APIs, and MCP servers
  • Real-time token usage tracking
  • Pricing and cost analysis
  • Performance metrics and debugging

🚀 Additional Features

  • Multi-tenancy with organization, team, and role-based access control
  • Scheduled tasks and cron jobs
  • Webhook triggers for event-driven workflows
  • Evaluation framework for testing and quality assurance
  • Payment integration with Stripe support
  • Notifications via Slack, Discord, and email
  • Keycloak authentication with OAuth and OIDC support

🏗️ Architecture

HelixML uses a microservices architecture with the following components:

┌─────────────────────────────────────────────────────────┐
│                      Frontend (React)                    │
│                     vite + TypeScript                    │
└────────────────────┬────────────────────────────────────┘
                     │
┌────────────────────▼────────────────────────────────────┐
│                  API / Control Plane (Go)                │
│  ┌──────────────┬──────────────┬──────────────────────┐ │
│  │   Agents     │  Knowledge   │   Auth & Sessions    │ │
│  │   Skills     │  RAG Pipeline│   Organizations      │ │
│  │   Tools      │  Vector DB   │   Usage Tracking     │ │
│  └──────────────┴──────────────┴──────────────────────┘ │
└─────────┬──────────────────────────────────┬───────────┘
          │                                  │
┌─────────▼──────────┐            ┌─────────▼──────────┐
│   PostgreSQL       │            │   GPU Runners      │
│   + PGVector       │            │   Model Scheduler  │
└────────────────────┘            └────────────────────┘
          │
┌─────────▼──────────────────────────────────────────────┐
│  Supporting Services: Keycloak, Kodit, GPTScript       │
│  Runner, Chrome/Rod, SearXNG                           │
└────────────────────────────────────────────────────────┘

Three-layer agent hierarchy:

  1. Session: Manages agent lifecycle and state
  2. Agent: Coordinates skills and handles LLM interactions
  3. Skills: Group related tools for specific capabilities
  4. Tools: Individual actions (API calls, functions, scripts)

💻 Tech Stack

Backend

  • Go 1.24.0 - Main backend language
  • PostgreSQL + PGVector - Data storage and vector embeddings
  • GORM - ORM for database operations
  • Gorilla Mux - HTTP routing
  • Keycloak - Identity and access management
  • NATS - Message queue
  • Zerolog - Structured logging

Frontend

  • React 18.3.1 - UI framework
  • TypeScript - Type-safe JavaScript
  • Material-UI (MUI) - Component library
  • MobX - State management
  • Vite - Build tool
  • Monaco Editor - Code editing

AI/ML

  • OpenAI SDK - GPT models integration
  • Anthropic SDK - Claude models integration
  • LangChain Go - LLM orchestration
  • GPTScript - Scripting capabilities
  • Kodit / LlamaIndex - RAG backends

Infrastructure

  • Docker & Docker Compose - Containerization
  • Kubernetes + Helm - Orchestration
  • Flux - GitOps operator

🚀 Quick Start

Install on Docker

Use our quickstart installer:

curl -sL -O https://get.helixml.tech/install.sh
chmod +x install.sh
sudo ./install.sh

The installer will prompt you before making changes to your system. By default, the dashboard will be available on http://localhost:8080.

For setting up a deployment with a DNS name, see ./install.sh --help or read the detailed docs. We've documented easy TLS termination for you.

Next steps:

Install on Kubernetes

Use our Helm charts for production deployments:

🔧 Configuration

All server configuration is done via environment variables. You can find the complete list of configuration options in api/pkg/config/config.go.

Key environment variables:

  • OPENAI_API_KEY - OpenAI API credentials
  • ANTHROPIC_API_KEY - Anthropic API credentials
  • POSTGRES_* - Database connection settings
  • KEYCLOAK_* - Authentication settings
  • SERVER_URL - Public URL for the deployment
  • RUNNER_* - GPU runner configuration

See the configuration documentation for detailed setup instructions.

👨‍💻 Development

For local development, refer to the Helix local development guide.

Prerequisites:

  • Docker Desktop (or Docker + Docker Compose)
  • Go 1.24.0+
  • Node.js 18+
  • Make

Quick development setup:

# Clone the repository
git clone https://github.com/helixml/helix.git
cd helix

# Start supporting services
docker-compose up -d postgres keycloak

# Run the backend
cd api
go run . serve

# Run the frontend (in a new terminal)
cd frontend
npm install
npm run dev

See local-development.md for comprehensive setup instructions.

📖 Documentation

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

By contributing, you confirm that:

  • Your changes will fall under the same license
  • Your changes will be owned by HelixML, Inc.

📄 License

Helix is licensed under a similar license to Docker Desktop. You can run the source code (in this repo) for free for:

  • Personal Use: Individuals or people personally experimenting
  • Educational Use: Schools and universities
  • Small Business Use: Companies with under $10M annual revenue and less than 250 employees

If you fall outside of these terms, please use the Launchpad to purchase a license for large commercial use. Trial licenses are available for experimentation.

You are not allowed to use our code to build a product that competes with us.

Why these license clauses?

  • We generate revenue to support the development of Helix. We are an independent software company.
  • We don't want cloud providers to take our open source code and build a rebranded service on top of it.

If you would like to use some part of this code under a more permissive license, please get in touch.

🆘 Support

🌟 Star History

If you find Helix useful, please consider giving us a star on GitHub!


Built with ❤️ by HelixML, Inc.

Ver o original no GitHub

Bom para

Relacionados