convez.ai
AgenteAutomaçãoAvançado
rootflo

Wavefront

rootflo/wavefront

Middleware de IA empresarial com agentes, workflows e RAG integrados

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Middleware de IA open-source para construir aplicações e workflows de IA em escala empresarial. Conecta múltiplas fontes de dados, LLMs e serviços, oferecendo autenticação, autorização e observabilidade nativa para agentes e automações.

Instalação

$npx convez-ai rootflo/wavefront

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
202
Forks
37
Acompanhando
5
Saúde
100%
Último commit
há 1 dia
Versão
wf/1.1.13
Issues abertas
33
Contribuidores
10

Casos de uso

  • Construir agentes de IA para automação de processos de negócio
  • Desenvolver aplicações RAG com múltiplas bases de conhecimento
  • Criar workflows de voz e conversacionais para vendas e atendimento
  • Conectar múltiplas fontes de dados e sistemas legados via APIs unificadas

Veredito

Solução robusta e bem-estruturada para orquestração de IA em empresas, com foco em conectividade, segurança e observabilidade. Posiciona-se como alternativa viável a plataformas comerciais consolidadas, embora em fase beta.

README

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

What is Wavefront ?

Wavefront AI is an open-source middleware platform designed to:

  • Seamlessly connect to any API, database or file storage system
  • Connect to any LLM or SLM
  • Build AI-driven agents, workflows, and automations across enterprise by connecting to multiple data sources, knowledge bases, and services
  • Provide authentication, authorization, observability, monitoring & evaluation for all agents & workflows

What people build with Wavefront ?

  • To build AI agents & workflows to audit, underwrite, supervise contact center, and automate business processes
  • To build knowledge bases & RAG ready applications for internal enterprise use
  • To build voice & conversational agents collections and sales use-cases
  • To build AI workflows to connect multiple data sources, knowledge bases, and services
Project InformationDetails
Release StatusBeta Release
Wavefront LicenseGNU AFFERO GENERAL PUBLIC LICENSE 3.0
FloAI LicenseMIT LICENSE

✨ Key Capabilities

  • 🔌 Unified API Layer
    Standardized APIs for developing, deploying, and managing AI workflows & agents across multiple use cases and frameworks.

  • 🔐 Enterprise-Grade Authentication & Authorization
    Native integrations with Google Auth and Microsoft AD/Entra for seamless SSO and access controls for client applications

  • 🌐 Comprehensive Data Connectivity
    Ingest data from OLAP/OLTP systems (BigQuery, Redshift), HDFS, cloud storage (S3, GCS), databases (PostgreSQL, MongoDB), and enterprise APIs (Salesforce, SAP).

  • 👥 Granular Role-Based Access Control
    Fine-grained permissions for both AI agents and data sources, ensuring compliance and least-privilege access.

  • 🤖 Open Source & Proprietary Model Support
    Works seamlessly with open-source LLMs/SLMs, custom models, and proprietary AI services.

  • 📊 Observability, Monitoring & Evaluation
    Built-in telemetry with Grafana and Prometheus support. Track agent performance, audit trails, and guardrail enforcement in real-time.

  • 🤖 No Code Agent & Workflow Builder Built-in capabilities to build and customize AI agents, and AI Workflows, connecting Data Sources, Knowledge Bases, in minutes

  • 🔊 Voice & Conversational Agents
    Integrated Voice-to-Voice Bots, ASR models, and agentic flows for contact center and conversational use cases.

  • 🧠 Knowledge Bases & RAG Ready
    Native support for Retrieval-Augmented Generation with MCP connectors and external knowledge bases.

  • 🎯 Modular AI Application Integration (Coming Soon)
    Deploy diverse AI agents for auditing, underwriting, contact center supervision, and business process automation without rebuilding infrastructure.

Quick Start

Option 1: Schedule a demo and we help you build immediately.

Option 2: Self-host for maximum control and customization. Please find the self-hosting instructions in the Wavefront Documentation.

Platform Components

As part of the project, we are building the following components

ComponentDescription
flo-aiFloAI library for Agent Building & A2A Orchestration. Detailed documentation is available here.
wavefront-serverCore Middleware Service, which connects everything and orchestrates the flows. Detailed documentation is available here.
wavefront-clientUnified frontend for configuring agents, workflows, AI models, Guardrails developer-friendly, RBAC etc. Details here.
wavefront-clifor configuring through cli, for full developer-friendly control (Coming Soon)

Release Timeline

QuarterMilestoneFeatures
Nov 2025Public README.mdPublish readme and take in community feedback
Dec 2025Open-source Beta ReleaseBeta with basic features
Q1 2026GA ReleaseAdvanced RBAC, More Data source Integrations
Q1 2026Rootflo Wavefront CloudMulti-tenant Cloud offering

See ROADMAP.md for detailed feature plans and contribution opportunities.

[!WARNING]

  • This project is under active development and APIs may change without notice. Please checkout the platform docs for the latest information.
  • The platform is not in the GA state, and there are unimplemented feature. Checkout ROADMAP.md for the list of features, and whats missing.

⭐ Show Your Support

If you find Wavefront AI useful, please consider:

  • Starring this repository ⭐
  • Sharing with your network
  • Contributing to the project
  • Providing feedback and feature requests

Next Steps

Text us! Twitter Vishnu Twitter Nitin

Ver o original no GitHub

Bom para

Relacionados