Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 24 additions & 13 deletions documentation/docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -11,12 +11,23 @@
"navigation": {
"tabs": [
{
"tab": "Guides",
"tab": "Wavefront",
"groups": [
{
"group": "Getting started",
"pages": [
"index",
"index"
]
}
]
},
{
"tab": "FloAI",
"groups": [
{
"group": "Getting started",
"pages": [
"flo-ai",
"quickstart",
"development"
]
Expand Down Expand Up @@ -78,21 +89,21 @@
},
"contextual": {
"options": [
"copy",
"view",
"chatgpt",
"claude",
"perplexity",
"mcp",
"cursor",
"vscode"
]
"copy",
"view",
"chatgpt",
"claude",
"perplexity",
"mcp",
"cursor",
"vscode"
]
},
"footer": {
"socials": {
"x": "https://x.com/rootflo",
"github": "https://github.com/rootflo/flo-ai",
"github": "https://github.com/rootflo/wavefront",
"linkedin": "https://linkedin.com/company/rootflo"
}
}
}
}
95 changes: 95 additions & 0 deletions documentation/flo-ai.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
---
title: "Flo AI Documentation"
description: "Build production-ready AI agents with structured outputs, tool integration, and multi-LLM support"
---

## Welcome to Flo AI (Wavefront coming soon) 🌊

Flo AI is a Python framework that makes building production-ready AI agents and teams as easy as writing YAML. Think "Kubernetes for AI Agents" - compose complex AI architectures using pre-built components while maintaining the flexibility to create your own.

<Card
title="Quick Start"
icon="rocket"
href="/quickstart"
horizontal
>
Get started with Flo AI in minutes - from installation to your first agent.
</Card>

## Key Features

<Columns cols={2}>
<Card
title="🔌 Truly Composable"
icon="puzzle-piece"
href="/essentials/agents"
>
Build complex AI systems by combining smaller, reusable components.
</Card>
<Card
title="🏗️ Built-in observability"
icon="shield-check"
href="/essentials/telemetry"
>
Built-in observability for production deployments.
</Card>
<Card
title="📝 YAML-First"
icon="file-code"
href="/essentials/yaml-workflows"
>
Define your entire agent architecture in simple YAML configurations.
</Card>
<Card
title="🧠 LLM-Powered Routing"
icon="route"
href="/essentials/routing"
>
Intelligent routing decisions made by LLMs, no code required.
</Card>
</Columns>

## Core Capabilities

Everything you need to build sophisticated AI agents and workflows.

<Columns cols={2}>
<Card
title="Multi-LLM Support"
icon="brain"
href="/essentials/llm-providers"
>
Support for OpenAI, Anthropic, Google, Ollama, and more with consistent interfaces.
</Card>
<Card
title="Tool Integration"
icon="wrench"
href="/essentials/tools"
>
Easy tool creation with the @flo_tool decorator and LangChain compatibility.
</Card>
<Card
title="Visual Studio"
icon="palette"
href="/essentials/studio"
>
Design AI workflows visually with our React-based studio interface.
</Card>
<Card
title="OpenTelemetry"
icon="chart-line"
href="/essentials/telemetry"
>
Built-in observability with automatic instrumentation for production monitoring.
</Card>
</Columns>

## Get Started

<Card
title="View Examples"
icon="code"
href="https://github.com/rootflo/flo-ai/tree/main/flo_ai/examples"
>
Explore comprehensive examples and use cases in our GitHub repository.
</Card>
Binary file added documentation/images/wavefront-arc.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
181 changes: 87 additions & 94 deletions documentation/index.mdx
Original file line number Diff line number Diff line change
@@ -1,97 +1,90 @@
---
title: "Flo AI Documentation"
description: "Build production-ready AI agents with structured outputs, tool integration, and multi-LLM support"
title: "Project Overview"
---

<Note>Wavefront documentation will be updated soon, along with code release</Note>

## Welcome to Flo AI (Wavefront coming soon) 🌊

Flo AI is a Python framework that makes building production-ready AI agents and teams as easy as writing YAML. Think "Kubernetes for AI Agents" - compose complex AI architectures using pre-built components while maintaining the flexibility to create your own.

<Card
title="Quick Start"
icon="rocket"
href="/quickstart"
horizontal
>
Get started with Flo AI in minutes - from installation to your first agent.
</Card>

## Key Features

<Columns cols={2}>
<Card
title="🔌 Truly Composable"
icon="puzzle-piece"
href="/essentials/agents"
>
Build complex AI systems by combining smaller, reusable components.
</Card>
<Card
title="🏗️ Built-in observability"
icon="shield-check"
href="/essentials/telemetry"
>
Built-in observability for production deployments.
</Card>
<Card
title="📝 YAML-First"
icon="file-code"
href="/essentials/yaml-workflows"
>
Define your entire agent architecture in simple YAML configurations.
</Card>
<Card
title="🧠 LLM-Powered Routing"
icon="route"
href="/essentials/routing"
>
Intelligent routing decisions made by LLMs, no code required.
</Card>
</Columns>

## Core Capabilities

Everything you need to build sophisticated AI agents and workflows.

<Columns cols={2}>
<Card
title="Multi-LLM Support"
icon="brain"
href="/essentials/llm-providers"
>
Support for OpenAI, Anthropic, Google, Ollama, and more with consistent interfaces.
</Card>
<Card
title="Tool Integration"
icon="wrench"
href="/essentials/tools"
>
Easy tool creation with the @flo_tool decorator and LangChain compatibility.
</Card>
<Card
title="Visual Studio"
icon="palette"
href="/essentials/studio"
>
Design AI workflows visually with our React-based studio interface.
</Card>
<Card
title="OpenTelemetry"
icon="chart-line"
href="/essentials/telemetry"
>
Built-in observability with automatic instrumentation for production monitoring.
</Card>
</Columns>

## Get Started

<Card
title="View Examples"
icon="code"
href="https://github.com/rootflo/flo-ai/tree/main/flo_ai/examples"
>
Explore comprehensive examples and use cases in our GitHub repository.
</Card>
# 🚀 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](CONTRIBUTING.md).
**Community**: Join our discord at https://discord.gg/BPXsNwfuRU
Comment on lines +2 to +14
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

Verify external links and fix grammar issues.

Three concerns here:

  1. Link verification: Confirm that CONTRIBUTING.md exists and the Discord link is correct.
  2. Grammar – Split infinitive (Line 7): "designed to seamlessly integrate" should be restructured. Consider: "designed to integrate seamlessly AI-driven agents..." or "designed for seamless integration of AI-driven agents...".
  3. Grammar – Compound adjective (Line 35): "Open Source & Proprietary Model Support" should use hyphens: "Open-Source & Proprietary-Model Support" or restructure as "Support for Open-Source and Proprietary Models".

🏁 Script executed:

#!/bin/bash
# Description: Verify file and link references in index.mdx

# Check if CONTRIBUTING.md exists
if [[ -f "CONTRIBUTING.md" ]]; then
  echo "✓ Found: CONTRIBUTING.md"
else
  echo "❌ Missing: CONTRIBUTING.md"
fi

# Check if image exists
if [[ -f "documentation/images/wavefront-arc.png" ]]; then
  echo "✓ Found: documentation/images/wavefront-arc.png"
else
  echo "❌ Missing: documentation/images/wavefront-arc.png"
fi

Length of output: 74


I need to verify the missing image file location and check the Discord link. Let me gather more information:


---

🏁 Script executed:

```shell
#!/bin/bash
# Find all PNG files in documentation directory
echo "=== Searching for PNG files in documentation/ ==="
fd -e png documentation/

# Check the actual content of index.mdx around the image reference
echo -e "\n=== Checking image reference in index.mdx ==="
rg -n "wavefront-arc" documentation/

# List all files in documentation/images if it exists
echo -e "\n=== Contents of documentation/images/ directory ==="
ls -la documentation/images/ 2>/dev/null || echo "Directory not found"

Length of output: 615


🏁 Script executed:

#!/bin/bash
# Verify Discord link returns valid response
echo "=== Checking Discord link ==="
curl -s -o /dev/null -w "HTTP Status: %{http_code}\n" "https://discord.gg/BPXsNwfuRU"

Length of output: 46


Critical issue: Missing image directory and incorrect alt text. Verify grammar and link references.

The verification found:

  • CONTRIBUTING.md exists
  • ✓ Discord link is valid (HTTP 301 redirect)
  • documentation/images/ directory does not exist — the image referenced at line 55 (./images/wavefront-arc.png) cannot be found. Create the directory and add the image file, or update the image path if it's stored elsewhere.
  • Incorrect alt text (line 55): alt="Rootflo" should reflect Wavefront content, e.g., alt="Wavefront Architecture".

Also fix the grammar issues:

  1. Split infinitive (Line 7): Restructure "designed to seamlessly integrate AI-driven agents..." to "designed for seamless integration of AI-driven agents..." or "designed to integrate seamlessly across..."
  2. Compound adjective (Line 35): Use hyphens or restructure "Open-Source & Proprietary-Model Support" or "Support for Open-Source and Proprietary Models".
🧰 Tools
🪛 LanguageTool

[style] ~7-~7: Try moving the adverb to make the sentence clearer.
Context: ...I is an open-source middleware platform designed to seamlessly integrate AI-driven agents, workflows, and data sources across ent...

(SPLIT_INFINITIVE)

🤖 Prompt for AI Agents
In documentation/index.mdx around lines 2–14 (and referencing line 55), the
referenced image path ./images/wavefront-arc.png is missing because
documentation/images/ does not exist and the alt text is incorrect; create the
documentation/images/ directory and add the wavefront-arc.png file (or update
the image path to the correct existing location), change alt="Rootflo" to
alt="Wavefront Architecture", reword line 7 from "designed to seamlessly
integrate AI-driven agents..." to "designed for seamless integration of
AI-driven agents..." (or "designed to integrate seamlessly across..."), and
change the compound adjective on line 35 to "Support for Open-Source and
Proprietary Models" or use hyphens like "Open-Source & Proprietary-Model
Support" to correct grammar.


<Note>FloAI documentation available at [FloAI](/flo-ai)</Note>

## ✨ 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
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Fix apparent typo: "customer" → "custom".

Line 42 reads: "...build and customer AI agents...". This appears to be a typo; should be "custom AI agents".

Apply this diff to fix the typo:

-  Built-in capabilities to build and customer AI agents, and AI Workflows, connecting Data Sources, Knowledge Bases, in minutes
+  Built-in capabilities to build and customize AI agents, and AI Workflows, connecting Data Sources, Knowledge Bases, in minutes
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
Built-in capabilities to build and customer AI agents, and AI Workflows, connecting Data Sources, Knowledge Bases, in minutes
Built-in capabilities to build and customize AI agents, and AI Workflows, connecting Data Sources, Knowledge Bases, in minutes
🤖 Prompt for AI Agents
documentation/index.mdx around line 42: the phrase "build and customer AI
agents" contains a typo—replace "customer" with "custom" so the sentence reads
"build and custom AI agents"; update that single word at line 42 to correct the
typo.


- **🔊 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

<p align="center">
<img src="./images/wavefront-arc.png" alt="Rootflo" />
</p>

### Layer Descriptions

| Layer | Purpose | Components |
|-------|---------|------------|
| **Frontend Applications** | User-facing AI interfaces | Supervisors, Audit Agents, Underwriters, Copilots |
| **API Layer** | Standardized communication | Frontend SDK, REST/GraphQL APIs |
| **Authentication** | Identity verification & SSO | Google Auth, LDAP, Auth0, Okta, Microsoft AD |
| **Authorization (Agents)** | Agent-level access policies | Role definitions, permission mapping |
| **AI Workflows** | Intelligent automation | Agentic flows, Voice agents, LLM integrations, RAG |
| **Data Processing** | ETL and API management | Pipelines, transformations, HTTP endpoints |
| **Authorization (Data)** | Data source access control | Fine-grained permissions, audit logging |
| **Data Sources** | Enterprise data systems/Services | Databases, APIs, Cloud storage, Data warehouses, Servics like Salesforce, SAP etc. |

## Platform Components

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

- [FloAI](https://github.com/rootflo/flo-ai/tree/develop/flo_ai) 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

| Quarter | Milestone | Features |
|---------|-----------|----------|
| **Nov 2025** | Public README.md | Publish readme and take in community feedback |
| **Dec 2025** | Open-source community edition | Community edition release with working MVP |
| **Q1 2026** | Enterprise Edition | Advanced RBAC, More Data source Integrations|
| **Q1 2026** | Rootflo Wavefront Cloud | One-click deployable Wavefront Cloud

**Join our discord at https://discord.gg/BPXsNwfuRU** to get early access to the platform and to provide feedback
Binary file modified documentation/logo/dark.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified documentation/logo/light.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.