Skip to main content

🚀 Wavefront AI Middleware

Wavefront AI is an open-source middleware platform designed to seamlessly integrate AI-driven agents, workflows, and data sources across enterprise environments. It acts as a connective layer that bridges modular frontend applications with complex backend data pipelines, ensuring secure access, observability, and compatibility with modern AI and data infrastructures. Status: Pre-release (Under active development)
Beta release: Dec 2025
Wavefront License: GNU AFFERO GENERAL PUBLIC LICENSE 3.0
FloAI License: MIT LICENSE
Contributing: We welcome early feedback! See CONTRIBUTING.md.
Community: Join our discord at https://discord.gg/BPXsNwfuRU
FloAI documentation available at FloAI

✨ Key Capabilities

  • 🎯 Modular AI Application Integration
    Deploy diverse AI agents for auditing, underwriting, contact center supervision, and business process automation without rebuilding infrastructure.
  • 🔌 Unified API Layer
    Standardized APIs for developing, deploying, and managing AI workflows across multiple use cases and frameworks.
  • 🔐 Enterprise-Grade Authentication & Authorization
    Native integrations with Google Auth, LDAP, Auth0, Okta, and Microsoft AD/Entra for seamless SSO and access controls.
  • 🌐 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 customer 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.

🏗️ Architecture Overview

Rootflo

Layer Descriptions

LayerPurposeComponents
Frontend ApplicationsUser-facing AI interfacesSupervisors, Audit Agents, Underwriters, Copilots
API LayerStandardized communicationFrontend SDK, REST/GraphQL APIs
AuthenticationIdentity verification & SSOGoogle Auth, LDAP, Auth0, Okta, Microsoft AD
Authorization (Agents)Agent-level access policiesRole definitions, permission mapping
AI WorkflowsIntelligent automationAgentic flows, Voice agents, LLM integrations, RAG
Data ProcessingETL and API managementPipelines, transformations, HTTP endpoints
Authorization (Data)Data source access controlFine-grained permissions, audit logging
Data SourcesEnterprise data systems/ServicesDatabases, APIs, Cloud storage, Data warehouses, Servics like Salesforce, SAP etc.

Platform Components

As part of the project, we are building the following components
  • FloAI library for Agent Building & A2A Orchestration
  • Wavefront Core Middleware Service, which connects multiple frontend applications with complex backend ai pipelines, provides authentication, authorization, observability, monitoring & evaluation
  • Wavefront Control Panel Unified frontend for configuring agents, workflows, AI models, Guardrails developer-friendly, RBAC etc.
  • Wavefront cli for configuring through cli (Yet to Build), for full developer-friendly control

Release Timeline

QuarterMilestoneFeatures
Nov 2025Public README.mdPublish readme and take in community feedback
Dec 2025Open-source community editionCommunity edition release with working MVP
Q1 2026Enterprise EditionAdvanced RBAC, More Data source Integrations
Q1 2026Rootflo Wavefront CloudOne-click deployable Wavefront Cloud
Join our discord at https://discord.gg/BPXsNwfuRU to get early access to the platform and to provide feedback