# NeuroLink Documentation (Summary)

> Enterprise AI Development Platform - Unified provider access, MCP integration, professional CLI

Generated: 2026-08-16T04:34:28.078Z
Full documentation: https://docs.neurolink.ink/llms-full.txt

---

## Project Overview

NeuroLink is an enterprise AI development platform that provides:
- Unified access to 13+ AI providers through a single consistent API
- 58+ MCP (Model Context Protocol) tools and integrations
- TypeScript SDK and professional CLI
- Production-ready features: Redis memory, failover, telemetry
- Multimodal support: text, images, PDFs, CSV, audio, video

## Supported Providers

- **OpenAI** (`openai`)
- **Anthropic Claude** (`anthropic`)
- **Google AI Studio (Gemini)** (`google-ai`)
- **Google Vertex AI** (`vertex`)
- **AWS Bedrock** (`bedrock`)
- **Azure OpenAI** (`azure`)
- **Mistral AI** (`mistral`)
- **LiteLLM (100+ models)** (`litellm`)
- **OpenRouter** (`openrouter`)
- **Ollama (Local)** (`ollama`)
- **Hugging Face** (`huggingface`)
- **AWS SageMaker** (`sagemaker`)
- **OpenAI-Compatible** (`openai-compatible`)

## API Signatures Summary

### Core Methods
- `neurolink.generate(options)` - Generate text response
- `neurolink.stream(options)` - Stream text response
- `neurolink.generateImage(options)` - Generate images (Gemini/Vertex)

### Configuration
- `new NeuroLink(config)` - Initialize SDK
- `neurolink.addExternalMCPServer(name, config)` - Add MCP server
- `neurolink.registerTool(tool)` - Register custom tool

### Common Options
- `provider` - AI provider slug (openai, anthropic, google-ai, etc.)
- `model` - Model name
- `input.text` - Prompt text
- `input.images` - Image attachments
- `maxTokens` - Response length limit
- `temperature` - Creativity (0-1)
- `thinkingLevel` - Extended thinking (minimal, low, medium, high)
- `structuredOutput` - Zod schema for typed responses

### CLI Commands
- `neurolink generate <prompt>` - Generate text
- `neurolink stream <prompt>` - Stream text
- `neurolink loop` - Interactive session
- `neurolink setup` - Configure providers
- `neurolink status` - Check provider health
- `neurolink mcp list` - List MCP tools

---

## Table of Contents

### Introduction
- NeuroLink

### Getting Started
- Getting Started
- AI Provider Guides
- Quick Start
- Installation
- Environment Variables Configuration Guide
- Anthropic Provider Guide
- AWS Bedrock Provider Guide
- Azure OpenAI Provider Guide
- ⚙️ Provider Configuration Guide
- Azure Speech Services
- Beatoven.ai Provider Guide (music)
- Redis Quick Start (5 Minutes)
- Cartesia TTS Provider Guide
- Cloudflare Workers AI Provider Guide
- Cohere Provider Guide
- D-ID Provider Guide (avatar)
- Deepgram Provider Guide
- DeepSeek Provider Guide
- ElevenLabs Music Provider Guide
- ElevenLabs Provider Guide
- Fireworks AI Provider Guide
- Fish Audio TTS Provider Guide
- Flatkey Provider Guide
- Google AI Studio Provider Guide
- Google Vertex AI Provider Guide
- Groq Provider Guide
- HeyGen Provider Guide (avatar)
- Hugging Face Provider Guide
- Ideogram Provider Guide (image-gen)
- Jina AI Provider Guide
- Kling AI Provider Guide (video)
- LiteLLM Provider Guide
- llama.cpp Provider Guide
- LM Studio Provider Guide
- Google Lyria Provider Guide (music)
- Mistral AI Provider Guide
- MuseTalk Provider Guide (avatar via Replicate)
- NVIDIA NIM Provider Guide
- Ollama Provider Guide
- OpenAI-Compatible Providers Guide
- OpenAI TTS Provider Guide
- OpenAI Provider Guide
- OpenRouter Provider Guide
- Perplexity Provider Guide
- Recraft Provider Guide (image-gen)
- Replicate Provider Guide
- Runway Provider Guide (video)
- Amazon SageMaker Provider Guide
- Stability AI Provider Guide
- Together AI Provider Guide
- Voyage AI Provider Guide
- xAI Grok Provider Guide

### SDK Reference
- SDK Reference
- API Reference

### CLI
- CLI Command Reference

### Features
- Feature Guides
- Audio Input & Transcription Guide
- Authentication Providers
- Auto Evaluation Engine
- Client SDK
- AutoResearch - Autonomous AI Experiment Engine
- Classifier Router
- Claude Proxy Architecture
- Claude Proxy Configuration Reference
- Claude Proxy Observability
- Claude Proxy Troubleshooting
- Claude Proxy
- Claude Subscription Testing Guide
- Claude Subscription Support
- CLI Loop Sessions
- Context Compaction
- Redis Conversation History Export
- Credential Validation
- CSV File Support
- Embeddings
- Enterprise Human-in-the-Loop System
- File Processors Guide
- Guardrails AI Integration with Middleware
- Guardrails Implementation Guide
- Guardrails Middleware
- Human-in-the-Loop (HITL) Workflows
- Image Generation Streaming Guide
- Interactive CLI - Your AI Development Environment
- LiveKit Voice Agent — Real-Time Voice over WebRTC
- MCP Enhancement Architecture Diagrams
- MCP Enhancements
- MCP Tools Ecosystem - Built-in Tools + Any MCP Server
- Memory Guide
- Multimodal Chat Experiences
- Multimodal Capabilities Guide
- Observability Guide
- Office Documents Support
- OpenCode Support for NeuroLink Proxy
- PDF File Support
- Per-Request Credentials
- PPT Generation - AI-Powered Presentations
- Provider Fallback & Model Chains
- Provider Orchestration Brain
- RAG Document Processing Guide
- Real-time Voice Services
- Regional Streaming Controls
- Skills Guide
- Speech-to-Speech Agents: Architecture and Gemini Live Integration Plan
- Streaming Guide
- Structured Output with Zod Schemas
- TaskManager - Scheduled & Self-Running Tasks
- Extended Thinking Configuration
- Text-to-Speech (TTS) Integration Guide
- Turn Time Budget
- Video Analysis
- Video Director Mode – Multi-Clip Generation & Merging
- Video Generation with Veo 3.1
- Real-Time Voice Agent - Streaming Voice Loop Design
- Workflow Engine Guide

### Examples
- Examples & Tutorials
- Advanced Examples
- Basic Usage Examples
- Business Applications
- Tool Blocking Feature Example
- Use Cases

---

# Introduction

## NeuroLink

<!-- Source: index.md -->

NeuroLink
  The Enterprise AI SDK for Production Applications
  30+ Providers | Voice (TTS/STT/Realtime) | 58+ MCP Tools | HITL Security | Redis Persistence

[[Image: npm version]](https://www.npmjs.com/package/@juspay/neurolink)

[Content truncated - see llms-full.txt for complete documentation]

---

# Getting Started

## Getting Started

<!-- Source: getting-started/index.md -->

# Getting Started

Welcome to NeuroLink! This section will help you get up and running quickly with the Enterprise AI Development Platform.

##  What You'll Learn


[Content truncated - see llms-full.txt for complete documentation]

---

## AI Provider Guides

<!-- Source: getting-started/providers/index.md -->

# AI Provider Guides

Complete setup guides for all supported AI providers.

##  Direct AI Providers

Access leading AI models directly from their creators:

### [Anthropic](/docs/getting-started/providers/anthropic)


[Content truncated - see llms-full.txt for complete documentation]

---

## Quick Start

<!-- Source: getting-started/quick-start.md -->

# Quick Start

Get NeuroLink running in under 2 minutes with this quick start guide.

##  Prerequisites

- **Node.js 18+**
- **npm/pnpm/yarn** package manager

[Content truncated - see llms-full.txt for complete documentation]

---

## Installation

<!-- Source: getting-started/installation.md -->

# Installation

Complete installation guide for NeuroLink CLI and SDK across different environments.

## Choose Your Installation Method

```bash
# Direct usage (recommended)
npx @juspay/neurolink generate "Hello, AI"


[Content truncated - see llms-full.txt for complete documentation]

---

## Environment Variables Configuration Guide

<!-- Source: getting-started/environment-variables.md -->

#  Environment Variables Configuration Guide

This guide provides comprehensive setup instructions for all AI providers supported by NeuroLink. The CLI automatically loads environment variables from `.env` files, making configuration seamless.


[Content truncated - see llms-full.txt for complete documentation]

---

## Anthropic Provider Guide

<!-- Source: getting-started/providers/anthropic.md -->

# Anthropic Provider Guide

**Direct access to Claude models with flexible authentication options**

-------- | -------------------------------------- | ------------------ |

[Content truncated - see llms-full.txt for complete documentation]

---

## AWS Bedrock Provider Guide

<!-- Source: getting-started/providers/aws-bedrock.md -->

# AWS Bedrock Provider Guide

**Enterprise AI with Claude, Nova, Llama, Mistral, DeepSeek, Qwen, and 110+ foundation models on AWS infrastructure**


[Content truncated - see llms-full.txt for complete documentation]

---

## Azure OpenAI Provider Guide

<!-- Source: getting-started/providers/azure-openai.md -->

# Azure OpenAI Provider Guide

**Enterprise-grade OpenAI models with Microsoft Azure infrastructure and compliance**

## Quick Start

### 1. Create Azure OpenAI Resource

```bash
# Via Azure CLI
az cognitiveservices account create \

[Content truncated - see llms-full.txt for complete documentation]

---

## ⚙️ Provider Configuration Guide

<!-- Source: getting-started/provider-setup.md -->

# ⚙️ Provider Configuration Guide

NeuroLink supports multiple AI providers with flexible authentication methods. This guide covers complete setup for all supported providers.

## Supported Providers

- **OpenAI** - GPT-4o, GPT-4o-mini, GPT-4-turbo

[Content truncated - see llms-full.txt for complete documentation]

---

## Azure Speech Services

<!-- Source: getting-started/providers/azure-speech.md -->

# Azure Speech Services

Azure Cognitive Services Speech provides both TTS and STT capabilities.

## Setup

```bash
# Required environment variables
AZURE_SPEECH_KEY=your-speech-key
AZURE_SPEECH_REGION=eastus
```


[Content truncated - see llms-full.txt for complete documentation]

---

## Beatoven.ai Provider Guide (music)

<!-- Source: getting-started/providers/beatoven.md -->

# Beatoven.ai Provider Guide

**Royalty-free background / cinematic music via Beatoven.ai**

## Quick Start

### 1. Get an API Key

[https://www.beatoven.ai/dashboard](https://www.beatoven.ai/dashboard)

### 2. Configure

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## Redis Quick Start (5 Minutes)

<!-- Source: getting-started/redis-quickstart.md -->

# Redis Quick Start (5 Minutes)

Get Redis storage up and running with NeuroLink in under 5 minutes.

## Prerequisites

- Docker installed **OR** Redis installed locally
- NeuroLink SDK installed (`pnpm add @juspay/neurolink`)


[Content truncated - see llms-full.txt for complete documentation]

---

## Cartesia TTS Provider Guide

<!-- Source: getting-started/providers/cartesia.md -->

# Cartesia TTS Provider Guide

**Low-latency text-to-speech — Cartesia's `sonic-2` model over the
synchronous `/tts/bytes` REST endpoint**

## Quick Start

### 1. Get an API Key

Sign up at [play.cartesia.ai](https://play.cartesia.ai/), open

[Content truncated - see llms-full.txt for complete documentation]

---

## Cloudflare Workers AI Provider Guide

<!-- Source: getting-started/providers/cloudflare.md -->

# Cloudflare Workers AI Provider Guide

**Open-model inference at the edge via Cloudflare Workers AI**

## Quick Start

### 1. Get Credentials

You need both:

- A Cloudflare **Account ID** (Cloudflare dashboard → right sidebar)

[Content truncated - see llms-full.txt for complete documentation]

---

## Cohere Provider Guide

<!-- Source: getting-started/providers/cohere.md -->

# Cohere Provider Guide

**Command R chat + Embed v3 embeddings via the Cohere API**

## Quick Start

### 1. Get an API Key

[https://dashboard.cohere.com/api-keys](https://dashboard.cohere.com/api-keys)

### 2. Configure

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## D-ID Provider Guide (avatar)

<!-- Source: getting-started/providers/d-id.md -->

# D-ID Provider Guide

**Lip-synced talking-head videos via the D-ID `/talks` API**

## Quick Start

### 1. Get an API Key

[https://studio.d-id.com/account-settings](https://studio.d-id.com/account-settings)

### 2. Configure

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## Deepgram Provider Guide

<!-- Source: getting-started/providers/deepgram.md -->

# Deepgram Provider Guide

**Fast, accurate speech-to-text with streaming, speaker diarization, and smart formatting**

> **STT-only in NeuroLink** — Deepgram is registered as the STT provider id

[Content truncated - see llms-full.txt for complete documentation]

---

## DeepSeek Provider Guide

<!-- Source: getting-started/providers/deepseek.md -->

# DeepSeek Provider Guide

**Text generation with DeepSeek-V3 (chat) and DeepSeek-R1 (reasoning) through a single API**

## Quick Start

### 1. Get an API Key


[Content truncated - see llms-full.txt for complete documentation]

---

## ElevenLabs Music Provider Guide

<!-- Source: getting-started/providers/elevenlabs-music.md -->

# ElevenLabs Music Provider Guide

**Music + sound-effect generation via the ElevenLabs Music / SFX API**

## Quick Start

### 1. Get an API Key

[https://elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys)


[Content truncated - see llms-full.txt for complete documentation]

---

## ElevenLabs Provider Guide

<!-- Source: getting-started/providers/elevenlabs.md -->

# ElevenLabs Provider Guide

**Studio-quality, multilingual text-to-speech with dynamic voice discovery and voice cloning**

-------------- | --------------------------------------------------- |

[Content truncated - see llms-full.txt for complete documentation]

---

## Fireworks AI Provider Guide

<!-- Source: getting-started/providers/fireworks.md -->

# Fireworks AI Provider Guide

**Open-model inference tuned for low-latency production workloads**

## Quick Start

### 1. Get an API Key

[https://fireworks.ai/account/api-keys](https://fireworks.ai/account/api-keys)

### 2. Configure Environment


[Content truncated - see llms-full.txt for complete documentation]

---

## Fish Audio TTS Provider Guide

<!-- Source: getting-started/providers/fish-audio.md -->

# Fish Audio TTS Provider Guide

**Low-cost text-to-speech — S2 Pro voice cloning, multilingual, ~80%
cheaper than ElevenLabs**

## Quick Start

### 1. Get an API Key

Sign up at [https://fish.audio/](https://fish.audio/) and create an API

[Content truncated - see llms-full.txt for complete documentation]

---

## Flatkey Provider Guide

<!-- Source: getting-started/providers/flatkey.md -->

# Flatkey Provider Guide

**One API key and one balance across 100+ supported AI models**

## Quick Start

### 1. Get an API Key

Create a key at [https://console.flatkey.ai/keys](https://console.flatkey.ai/keys).

### 2. Configure Environment


[Content truncated - see llms-full.txt for complete documentation]

---

## Google AI Studio Provider Guide

<!-- Source: getting-started/providers/google-ai.md -->

# Google AI Studio Provider Guide

**Direct access to Google's Gemini models with generous free tier and simple API key authentication**

## Quick Start

### 1. Get Your API Key

1. Visit [Google AI Studio](https://aistudio.google.com/)

[Content truncated - see llms-full.txt for complete documentation]

---

## Google Vertex AI Provider Guide

<!-- Source: getting-started/providers/google-vertex.md -->

# Google Vertex AI Provider Guide

**Enterprise AI on Google Cloud with Claude, Gemini, and custom models**

## Quick Start

### 1. Create GCP Project

```bash
# Create project
gcloud projects create my-ai-project --name="My AI Project"


[Content truncated - see llms-full.txt for complete documentation]

---

## Groq Provider Guide

<!-- Source: getting-started/providers/groq.md -->

# Groq Provider Guide

**Sub-100ms inference of open-weight models via Groq's LPU — best for
latency-sensitive applications**

## Quick Start

### 1. Get an API Key

Sign up at [https://console.groq.com/](https://console.groq.com/) and

[Content truncated - see llms-full.txt for complete documentation]

---

## HeyGen Provider Guide (avatar)

<!-- Source: getting-started/providers/heygen.md -->

# HeyGen Provider Guide

**Talking-head avatar videos via HeyGen's V2 API**

## Quick Start

### 1. Get an API Key + Avatar ID

[https://app.heygen.com/settings/api](https://app.heygen.com/settings/api)

[Content truncated - see llms-full.txt for complete documentation]

---

## Hugging Face Provider Guide

<!-- Source: getting-started/providers/huggingface.md -->

# Hugging Face Provider Guide

**Access 100,000+ open-source AI models through Hugging Face's free inference API**

## Quick Start

### 1. Get Your API Token

1. Visit [Hugging Face](https://huggingface.co/)

[Content truncated - see llms-full.txt for complete documentation]

---

## Ideogram Provider Guide (image-gen)

<!-- Source: getting-started/providers/ideogram.md -->

# Ideogram Provider Guide

**Text-aware image generation via Ideogram V3**

## Quick Start

### 1. Get an API Key

[https://ideogram.ai/manage-api](https://ideogram.ai/manage-api)

### 2. Configure

```bash
IDEOGRAM_API_KEY=your-key
```


[Content truncated - see llms-full.txt for complete documentation]

---

## Jina AI Provider Guide

<!-- Source: getting-started/providers/jina.md -->

# Jina AI Provider Guide

**Multilingual embeddings + reranking through the Jina AI API**

## Quick Start

### 1. Get an API Key

Sign up at [https://jina.ai/](https://jina.ai/) and grab a key from the
dashboard.

### 2. Configure Environment


[Content truncated - see llms-full.txt for complete documentation]

---

## Kling AI Provider Guide (video)

<!-- Source: getting-started/providers/kling.md -->

# Kling AI Provider Guide

**Image-to-video generation via Kling AI**

## Quick Start

### 1. Get API Credentials

Sign up at [https://kling.ai/](https://kling.ai/) and grab the Access Key
ID + Secret from the developer dashboard.

### 2. Configure


[Content truncated - see llms-full.txt for complete documentation]

---

## LiteLLM Provider Guide

<!-- Source: getting-started/providers/litellm.md -->

# LiteLLM Provider Guide

**Access hundreds of AI models across 100+ providers through the NeuroLink LiteLLM provider via a LiteLLM proxy server**

## Quick Start

### 1. Set Up a LiteLLM Proxy Server


[Content truncated - see llms-full.txt for complete documentation]

---

## llama.cpp Provider Guide

<!-- Source: getting-started/providers/llamacpp.md -->

# llama.cpp Provider Guide

**Fully offline GGUF inference — connect NeuroLink directly to a `llama-server` process**

## Quick Start

### 1. Install and Build llama.cpp

```bash
# Clone the repo
git clone https://github.com/ggerganov/llama.cpp

[Content truncated - see llms-full.txt for complete documentation]

---

## LM Studio Provider Guide

<!-- Source: getting-started/providers/lm-studio.md -->

# LM Studio Provider Guide

**Run any GGUF model privately on your own hardware — no cloud, no API key required**

## Quick Start

### 1. Download and Start LM Studio


[Content truncated - see llms-full.txt for complete documentation]

---

## Google Lyria Provider Guide (music)

<!-- Source: getting-started/providers/lyria.md -->

# Google Lyria Provider Guide

**Music generation via Google Lyria 3 Pro**

## Quick Start

### 1. Get an API Key

[https://aistudio.google.com/apikey](https://aistudio.google.com/apikey)

### 2. Configure

Any of these env vars work:

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## Mistral AI Provider Guide

<!-- Source: getting-started/providers/mistral.md -->

# Mistral AI Provider Guide

**European AI excellence with GDPR compliance and competitive free tier**

## Quick Start

### 1. Get Your API Key

1. Visit [Mistral AI Console](https://console.mistral.ai/)
2. Create a free account

[Content truncated - see llms-full.txt for complete documentation]

---

## MuseTalk Provider Guide (avatar via Replicate)

<!-- Source: getting-started/providers/musetalk.md -->

# MuseTalk Provider Guide

**Lip-synced avatar videos via the MuseTalk model on Replicate**

## Quick Start

### 1. Get a Replicate Token

[https://replicate.com/account/api-tokens](https://replicate.com/account/api-tokens)

### 2. Configure


[Content truncated - see llms-full.txt for complete documentation]

---

## NVIDIA NIM Provider Guide

<!-- Source: getting-started/providers/nvidia-nim.md -->

# NVIDIA NIM Provider Guide

**Hundreds of optimised AI models on NVIDIA's GPU-accelerated inference platform — or your own self-hosted NIM deployment**

## Quick Start

### 1. Get an API Key


[Content truncated - see llms-full.txt for complete documentation]

---

## Ollama Provider Guide

<!-- Source: getting-started/providers/ollama.md -->

# Ollama Provider Guide

**Run AI models locally with full privacy - no API key or cloud service required**

------------------ | ---------------------- | ------------------------------------------------- |

[Content truncated - see llms-full.txt for complete documentation]

---

## OpenAI-Compatible Providers Guide

<!-- Source: getting-started/providers/openai-compatible.md -->

# OpenAI Compatible Provider Guide

**Connect to any OpenAI-compatible API: OpenRouter, vLLM, LocalAI, and more**

---------------------- | ------------------------------------ | ---------------------- |

[Content truncated - see llms-full.txt for complete documentation]

---

## OpenAI TTS Provider Guide

<!-- Source: getting-started/providers/openai-tts.md -->

# OpenAI TTS Provider Guide

**High-quality neural text-to-speech with six distinct voices and HD quality option**

------------- | --------------------------------------------- |
| **Provider ID**  | `openai-tts`                                  |

[Content truncated - see llms-full.txt for complete documentation]

---

## OpenAI Provider Guide

<!-- Source: getting-started/providers/openai.md -->

# OpenAI Provider Guide

**Access GPT-5.4, GPT-5, GPT-4o, o-series reasoning models, and embedding models through the OpenAI API**

------ | --------------------------- |
| `openai`  | Canonical provider name     |

[Content truncated - see llms-full.txt for complete documentation]

---

## OpenRouter Provider Guide

<!-- Source: getting-started/providers/openrouter.md -->

# OpenRouter Provider Guide

**Access 300+ AI models from 60+ providers through a single unified API**

## Quick Start

### 1. Get Your API Key


[Content truncated - see llms-full.txt for complete documentation]

---

## Perplexity Provider Guide

<!-- Source: getting-started/providers/perplexity.md -->

# Perplexity Provider Guide

**Web-search-augmented generation via Perplexity's Sonar models**

## Quick Start

### 1. Get an API Key

[https://www.perplexity.ai/settings/api](https://www.perplexity.ai/settings/api)

### 2. Configure

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## Recraft Provider Guide (image-gen)

<!-- Source: getting-started/providers/recraft.md -->

# Recraft Provider Guide

**Raster + native SVG image generation via Recraft V3**

## Quick Start

### 1. Get an API Key

[https://www.recraft.ai/profile/api](https://www.recraft.ai/profile/api)

### 2. Configure

```bash
RECRAFT_API_KEY=your-key

[Content truncated - see llms-full.txt for complete documentation]

---

## Replicate Provider Guide

<!-- Source: getting-started/providers/replicate.md -->

# Replicate Provider Guide

**One auth token, five modalities — LLMs + image + video + avatar + music
under a single `REPLICATE_API_TOKEN`**


[Content truncated - see llms-full.txt for complete documentation]

---

## Runway Provider Guide (video)

<!-- Source: getting-started/providers/runway.md -->

# Runway Provider Guide

**Image-to-video generation via Runway Gen-3 / Gen-4**

## Quick Start

### 1. Get an API Key

[https://app.runwayml.com/settings/developer](https://app.runwayml.com/settings/developer)

### 2. Configure

```bash

[Content truncated - see llms-full.txt for complete documentation]

---

## Amazon SageMaker Provider Guide

<!-- Source: getting-started/providers/sagemaker.md -->

# Amazon SageMaker Provider Guide

**Custom model endpoints on AWS SageMaker infrastructure**

> **Version:** 9.26.x | **Status:** General Availability | **Streaming:** Not Available (see warning below)


[Content truncated - see llms-full.txt for complete documentation]

---

## Stability AI Provider Guide

<!-- Source: getting-started/providers/stability.md -->

# Stability AI Provider Guide

**Direct image generation — image-only provider with no chat / streaming
(use the `imageOutput.base64` field on the result)**

## Quick Start

### 1. Get an API Key


[Content truncated - see llms-full.txt for complete documentation]

---

## Together AI Provider Guide

<!-- Source: getting-started/providers/together-ai.md -->

# Together AI Provider Guide

**Open-source LLMs at production scale via the Together gateway**

## Quick Start

### 1. Get an API Key

[https://api.together.xyz/settings/api-keys](https://api.together.xyz/settings/api-keys)


[Content truncated - see llms-full.txt for complete documentation]

---

## Voyage AI Provider Guide

<!-- Source: getting-started/providers/voyage.md -->

# Voyage AI Provider Guide

**Top-tier RAG embeddings — text-only provider exposing `embed()` and
`embedMany()` (chat / streaming intentionally not supported)**

## Quick Start

### 1. Get an API Key


[Content truncated - see llms-full.txt for complete documentation]

---

## xAI Grok Provider Guide

<!-- Source: getting-started/providers/xai.md -->

# xAI Grok Provider Guide

**Text + vision generation with the Grok family through a single API**

## Quick Start

### 1. Get an API Key

Sign up at [https://console.x.ai/](https://console.x.ai/) and create an
API key under **API Keys**.


[Content truncated - see llms-full.txt for complete documentation]

---

# SDK Reference

## SDK Reference

<!-- Source: sdk/index.md -->

# SDK Reference

The NeuroLink SDK provides a TypeScript-first programmatic interface for integrating AI capabilities into your applications.

## Overview

The SDK is designed for:

- **Web applications** (React, Vue, Svelte, Angular)

[Content truncated - see llms-full.txt for complete documentation]

---

## API Reference

<!-- Source: sdk/api-reference.md -->

This page has moved to [SDK API Reference](/docs/sdk/api-reference).

---

# CLI

## CLI Command Reference

<!-- Source: cli/commands.md -->

# CLI Command Reference

The NeuroLink CLI mirrors the SDK. Every command shares consistent options and outputs so you can prototype in the terminal and port the workflow to code later.

## Install or Run Ad-hoc

```bash
# Run without installation

[Content truncated - see llms-full.txt for complete documentation]

---

# Features

## Feature Guides

<!-- Source: features/index.md -->

# Feature Guides

Comprehensive guides for all NeuroLink features organized by category. Each guide includes setup, usage patterns, configuration, and troubleshooting.


[Content truncated - see llms-full.txt for complete documentation]

---

## Audio Input & Transcription Guide

<!-- Source: features/audio-input.md -->

# Audio Input & Voice Conversations Guide

NeuroLink provides comprehensive audio input capabilities, enabling real-time voice conversations with AI models.

[Content truncated - see llms-full.txt for complete documentation]

---

## Authentication Providers

<!-- Source: features/authentication-providers.md -->

# Authentication Providers

> **Status**: Stable | **Availability**: SDK + CLI + Server

## Overview

NeuroLink ships with a pluggable authentication system that validates tokens, manages sessions, and enforces role-based access control (RBAC)...

[Content truncated - see llms-full.txt for complete documentation]

---

## Auto Evaluation Engine

<!-- Source: features/auto-evaluation.md -->

# Auto Evaluation Engine

NeuroLink provides an automated quality gate that scores every response using an LLM-as-judge pipeline.

[Content truncated - see llms-full.txt for complete documentation]

---

## Client SDK

<!-- Source: features/client-sdk.md -->

# Client SDK

> **Since**: v9.30.0 | **Status**: Stable | **Availability**: SDK

## Overview

The NeuroLink Client SDK provides type-safe libraries for accessing NeuroLink APIs from JavaScript and TypeScript applications.

[Content truncated - see llms-full.txt for complete documentation]

---

## AutoResearch - Autonomous AI Experiment Engine

<!-- Source: features/autoresearch.md -->

# AutoResearch - Autonomous AI Experiment Engine

## Overview

AutoResearch is an autonomous experiment loop that proposes code changes, executes experiments, evaluates results against a deterministic metric, and keeps or discards each change —...

[Content truncated - see llms-full.txt for complete documentation]

---

## Classifier Router

<!-- Source: features/classifier-router.md -->

# Classifier Router

> **Status**: Stable | **Availability**: SDK + CLI | **Opt-in** (disabled by default)

## Overview

The **Classifier Router** lets NeuroLink decide, per request, **which model to use** (and, optionally, **which tools to...

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Proxy Architecture

<!-- Source: features/claude-proxy-architecture.md -->

# Claude Proxy Architecture

## 1. System Overview

The Claude proxy is a local HTTP server that sits between Claude Code and the Anthropic API.

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Proxy Configuration Reference

<!-- Source: features/claude-proxy-config-reference.md -->

# Claude Proxy Configuration Reference

This document is the authoritative reference for every configurable aspect of the NeuroLink Claude proxy.

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Proxy Observability

<!-- Source: features/claude-proxy-observability.md -->

# Claude Proxy Observability

This guide explains how to read the OpenObserve dashboard used to operate the NeuroLink Claude proxy.

## Source Of Truth

- Dashboard definition: `docs/assets/dashboards/neurolink-proxy-observability-dashboard.json`

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Proxy Troubleshooting

<!-- Source: features/claude-proxy-troubleshooting.md -->

# Claude Proxy Troubleshooting

This guide covers every issue encountered during development and real-world usage of the NeuroLink Claude proxy. For general proxy documentation, see [Claude Proxy](/docs/features/claude-proxy).

## Common Issues


[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Proxy

<!-- Source: features/claude-proxy.md -->

# Claude Proxy

NeuroLink includes a Claude-API-compatible proxy server that sits between Claude Code and Anthropic. It pools multiple Claude accounts, handles rate-limit failover automatically, refreshes OAuth tokens on demand before they expire,...

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Subscription Testing Guide

<!-- Source: features/claude-subscription-testing.md -->

# Claude Subscription Testing Guide

This document provides comprehensive testing commands and examples for the Claude subscription feature in NeuroLink, covering API key authentication, OAuth authentication for Pro/Max subscribers, subscription...

[Content truncated - see llms-full.txt for complete documentation]

---

## Claude Subscription Support

<!-- Source: features/claude-subscription.md -->

# Claude Subscription Support

NeuroLink provides flexible access to Anthropic's Claude models through multiple subscription tiers and authentication methods. This guide covers setup, configuration, and best practices for each tier.

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## CLI Loop Sessions

<!-- Source: features/cli-loop-sessions.md -->

# CLI Loop Sessions

`neurolink loop` delivers a persistent CLI workspace so you can explore prompts, tweak parameters, and inspect state without restarting the CLI.

[Content truncated - see llms-full.txt for complete documentation]

---

## Context Compaction

<!-- Source: features/context-compaction.md -->

# Context Compaction

## Overview

NeuroLink's Context Compaction system automatically manages conversation context windows, preventing overflow errors and maintaining conversation quality as sessions grow longer.

[Content truncated - see llms-full.txt for complete documentation]

---

## Redis Conversation History Export

<!-- Source: features/conversation-history.md -->

# Redis Conversation History Export

> **Since**: v7.38.0 | **Status**: Stable | **Availability**: SDK + CLI

## Overview

**What it does**: Export complete conversation session history from Redis storage as JSON for analytics, debugging, and...

[Content truncated - see llms-full.txt for complete documentation]

---

## Credential Validation

<!-- Source: features/credential-validation.md -->

Added in **v9.59.0**, NeuroLink ships a typed `ModelAccessDeniedError` and a pre-flight `sdk.checkCredentials()` API. Together they let you validate provider credentials _before_ wiring them into a long-running flow — useful for setup wizards,...

[Content truncated - see llms-full.txt for complete documentation]

---

## CSV File Support

<!-- Source: features/csv-support.md -->

# CSV File Support

NeuroLink provides seamless CSV file support as a **multimodal input type** - attach CSV files directly to your AI prompts for data analysis, insights, and processing.

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## Embeddings

<!-- Source: features/embeddings.md -->

# Embeddings

> **Status**: Stable | **Availability**: SDK + CLI + Server

## Overview

Embeddings convert text into dense numerical vectors that capture semantic meaning.

[Content truncated - see llms-full.txt for complete documentation]

---

## Enterprise Human-in-the-Loop System

<!-- Source: features/enterprise-hitl.md -->

# Enterprise Human-in-the-Loop System

> **Since**: v7.39.0 | **Status**: Production Ready | **Availability**: SDK & CLI

:::note[Feature Status - Enterprise HITL]

[Content truncated - see llms-full.txt for complete documentation]

---

## File Processors Guide

<!-- Source: features/file-processors.md -->

# File Processors Guide

NeuroLink includes a comprehensive file processing system that supports 20+ file types with intelligent content extraction, security sanitization, and provider-agnostic formatting.

[Content truncated - see llms-full.txt for complete documentation]

---

## Guardrails AI Integration with Middleware

<!-- Source: features/guardrails-ai.md -->

# Guardrails AI Integration with Middleware

This document outlines the modern, simplified approach to integrating Guardrails AI with the NeuroLink platform using the new `MiddlewareFactory`.

[Content truncated - see llms-full.txt for complete documentation]

---

## Guardrails Implementation Guide

<!-- Source: features/guardrails-implementation.md -->

# Guardrails Implementation Guide

This document provides comprehensive documentation for the NeuroLink guardrails implementation, including pre-call filtering, content sanitization, and AI-powered evaluation.

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## Guardrails Middleware

<!-- Source: features/guardrails.md -->

# Guardrails Middleware

> **Since**: v7.42.0 | **Status**: Stable | **Availability**: SDK (CLI + SDK)

## Overview

**What it does**: Guardrails middleware provides real-time content filtering and policy enforcement for AI model outputs, blocking...

[Content truncated - see llms-full.txt for complete documentation]

---

## Human-in-the-Loop (HITL) Workflows

<!-- Source: features/hitl.md -->

# Human-in-the-Loop (HITL) Workflows

> **Since**: v7.39.0 | **Status**: Stable | **Availability**: SDK

## Overview

**What it does**: HITL pauses AI tool execution to request explicit user approval before performing risky operations like deleting...

[Content truncated - see llms-full.txt for complete documentation]

---

## Image Generation Streaming Guide

<!-- Source: features/image-generation.md -->

# Image Generation Streaming Guide

## Overview

NeuroLink supports image generation through AI models like Google Vertex AI's `gemini-3-pro-image-preview` and `gemini-2.5-flash-image`.

[Content truncated - see llms-full.txt for complete documentation]

---

## Interactive CLI - Your AI Development Environment

<!-- Source: features/interactive-cli.md -->

# Interactive CLI: Your AI Development Environment

> **Since**: v7.0.0 | **Status**: Production Ready | **Availability**: CLI

## Why Interactive Mode?


[Content truncated - see llms-full.txt for complete documentation]

---

## LiveKit Voice Agent — Real-Time Voice over WebRTC

<!-- Source: features/livekit-voice-agent.md -->

# LiveKit Voice Agent — Real-Time Voice over WebRTC

**A WebRTC voice agent that uses LiveKit for the real-time media loop and NeuroLink as the brain (LLM, tools, memory).**

## Problem Statement & Solution

### The Challenge


[Content truncated - see llms-full.txt for complete documentation]

---

## MCP Enhancement Architecture Diagrams

<!-- Source: features/mcp-enhancements-diagrams.md -->

# MCP Enhancement Architecture Diagrams

Visual guides for understanding the MCP enhancement architecture, data flows, and component interactions.


[Content truncated - see llms-full.txt for complete documentation]

---

## MCP Enhancements

<!-- Source: features/mcp-enhancements.md -->

# MCP Enhancements

> **Since**: v9.16.0 | **Status**: Stable | **Availability**: SDK

## Overview

The MCP Enhancements suite extends NeuroLink's Model Context Protocol integration with production-grade capabilities for managing tool calls at...

[Content truncated - see llms-full.txt for complete documentation]

---

## MCP Tools Ecosystem - Built-in Tools + Any MCP Server

<!-- Source: features/mcp-tools-showcase.md -->

# MCP Tools Ecosystem: Built-in Tools + Any MCP Server

> **Since**: v7.0.0 | **Status**: Production Ready | **MCP Version**: 2024-11-05

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## Memory Guide

<!-- Source: features/memory.md -->

# Memory Guide

> **Since**: v9.12.0 | **Status**: Stable | **Availability**: SDK

## Overview

NeuroLink includes a **memory engine** powered by the `@juspay/hippocampus` SDK.

[Content truncated - see llms-full.txt for complete documentation]

---

## Multimodal Chat Experiences

<!-- Source: features/multimodal-chat.md -->

# Multimodal Chat Experiences

NeuroLink provides full multimodal pipelines so you can mix text, URLs, and local images in a single interaction. The CLI, SDK, and loop sessions all use the same message builder, ensuring parity across workflows.


[Content truncated - see llms-full.txt for complete documentation]

---

## Multimodal Capabilities Guide

<!-- Source: features/multimodal.md -->

# Multimodal Capabilities Guide

NeuroLink provides comprehensive multimodal support, allowing you to combine text with various media types in a single AI interaction.

[Content truncated - see llms-full.txt for complete documentation]

---

## Observability Guide

<!-- Source: features/observability.md -->

# Observability Guide

Enterprise-grade observability for AI operations with Langfuse and OpenTelemetry integration.

## Overview

NeuroLink provides comprehensive observability features for monitoring AI operations in production:


[Content truncated - see llms-full.txt for complete documentation]

---

## Office Documents Support

<!-- Source: features/office-documents.md -->

# Office Documents Support

NeuroLink provides seamless Office document support as a **multimodal input type** - attach DOCX, PPTX, and XLSX documents directly to your AI prompts for document analysis, data extraction, and content processing.


[Content truncated - see llms-full.txt for complete documentation]

---

## OpenCode Support for NeuroLink Proxy

<!-- Source: features/opencode-proxy-support.md -->

# OpenCode Support for NeuroLink Proxy

## Status: Implemented & Verified

This document was originally written as a design proposal. Every item it called out as missing or to-be-built has since been implemented and verified end-to-end (see §11).

[Content truncated - see llms-full.txt for complete documentation]

---

## PDF File Support

<!-- Source: features/pdf-support.md -->

# PDF File Support

NeuroLink provides seamless PDF file support as a **multimodal input type** - attach PDF documents directly to your AI prompts for document analysis, information extraction, and content processing.

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## Per-Request Credentials

<!-- Source: features/per-request-credentials.md -->

# Per-Request Credentials

> **Status**: Stable | **Availability**: SDK only

## Overview

NeuroLink allows provider credentials to be supplied at two levels below the environment-variable default: on the `NeuroLink` constructor (instance level) and...

[Content truncated - see llms-full.txt for complete documentation]

---

## PPT Generation - AI-Powered Presentations

<!-- Source: features/ppt-generation.md -->

# PPT Generation - AI-Powered Presentations

NeuroLink enables AI-powered PowerPoint presentation generation from text prompts.

[Content truncated - see llms-full.txt for complete documentation]

---

## Provider Fallback & Model Chains

<!-- Source: features/provider-fallback.md -->

Added in **v9.58.0**, NeuroLink supports two complementary mechanisms for handling **model-access denial** errors at request time: the `providerFallback` callback (dynamic, code-driven) and the `modelChain` config (declarative).

[Content truncated - see llms-full.txt for complete documentation]

---

## Provider Orchestration Brain

<!-- Source: features/provider-orchestration.md -->

# Provider Orchestration Brain

The orchestration engine introduced in 7.42.0 pairs a task classifier with a provider/model router.

[Content truncated - see llms-full.txt for complete documentation]

---

## RAG Document Processing Guide

<!-- Source: features/rag.md -->

# RAG Document Processing Guide

> **Since**: v8.44.0 | **Status**: Stable | **Availability**: SDK + CLI

> **Provider Defaults:** When `--provider` (CLI) or `provider` (SDK) is not specified, NeuroLink defaults to **Vertex AI** with...

[Content truncated - see llms-full.txt for complete documentation]

---

## Real-time Voice Services

<!-- Source: features/real-time-services.md -->

NeuroLink integrates the two major realtime voice APIs behind a single, provider-agnostic interface: **OpenAI Realtime** (`openai-realtime`) and **Google Gemini Live** (`gemini-live`).

[Content truncated - see llms-full.txt for complete documentation]

---

## Regional Streaming Controls

<!-- Source: features/regional-streaming.md -->

# Regional Streaming Controls

Latency, compliance, and model availability often depend on which region you call. NeuroLink threads the `region` parameter through the generate/stream stack so you can target specific data centres when working with...

[Content truncated - see llms-full.txt for complete documentation]

---

## Skills Guide

<!-- Source: features/skills.md -->

# Skills Guide

> **Since**: v9.82.0 | **Status**: Stable | **Availability**: SDK, CLI, Server

## Overview

NeuroLink includes native **skills** support: versioned, discoverable instruction packs (SOPs, playbooks, workflows) the model consults...

[Content truncated - see llms-full.txt for complete documentation]

---

## Speech-to-Speech Agents: Architecture and Gemini Live Integration Plan

<!-- Source: features/speech-agents.md -->

# Speech-to-Speech Agents: Architecture and Gemini Live Integration Plan

Status: Proposal (Docs only)
Owner: NeuroLink Platform
Last updated: 2025-09-01

## Goals


[Content truncated - see llms-full.txt for complete documentation]

---

## Streaming Guide

<!-- Source: features/streaming.md -->

# Streaming Guide

> **Since**: v8.0.0 | **Status**: Stable | **Availability**: SDK + CLI
>
> **Provider Defaults:** When `--provider` (CLI) or `provider` (SDK) is not specified, NeuroLink defaults to **Vertex AI** with **gemini-2.5-flash**.

[Content truncated - see llms-full.txt for complete documentation]

---

## Structured Output with Zod Schemas

<!-- Source: features/structured-output.md -->

# Structured Output with Zod Schemas

Generate type-safe, validated JSON responses using Zod schemas. Available in `generate()` function only (not `stream()`).

## Quick Start

```typescript

const neurolink = new NeuroLink();


[Content truncated - see llms-full.txt for complete documentation]

---

## TaskManager - Scheduled & Self-Running Tasks

<!-- Source: features/task-manager.md -->

# TaskManager - Scheduled & Self-Running Tasks

## Overview

TaskManager adds scheduled and self-running task capabilities to NeuroLink.

[Content truncated - see llms-full.txt for complete documentation]

---

## Extended Thinking Configuration

<!-- Source: features/thinking-configuration.md -->

# Extended Thinking Configuration

Enable extended thinking/reasoning modes for AI models that support deeper reasoning capabilities. This feature allows models to "think through" complex problems before providing a response.

## Overview


[Content truncated - see llms-full.txt for complete documentation]

---

## Text-to-Speech (TTS) Integration Guide

<!-- Source: features/tts.md -->

# Text-to-Speech (TTS) Integration Guide

NeuroLink provides integrated Text-to-Speech (TTS) capabilities, allowing you to generate high-quality audio from text prompts or AI-generated responses.

[Content truncated - see llms-full.txt for complete documentation]

---

## Turn Time Budget

<!-- Source: features/turn-time-budget.md -->

# Turn Time Budget

Turn-lifecycle limits for agentic (multi-step tool-calling) turns, enforced
inside NeuroLink's native Vertex loops (Gemini and Claude-on-Vertex, both
`generate()` and `stream()`). NeuroLink sees every model call, every tool

[Content truncated - see llms-full.txt for complete documentation]

---

## Video Analysis

<!-- Source: features/video-analysis.md -->

# Video Analysis

Comprehensive video analysis for NeuroLink, powered by Gemini 2.0 Flash. This feature goes beyond basic visual description—it provides a deep logical audit of video sequences to understand "why" and "how" events occur.


[Content truncated - see llms-full.txt for complete documentation]

---

## Video Director Mode – Multi-Clip Generation & Merging

<!-- Source: features/video-director-mode.md -->

# Video Director Mode

Director Mode extends NeuroLink's [video generation](/docs/features/video-generation) capability to produce **multi-segment videos with seamless AI-generated transitions**.

[Content truncated - see llms-full.txt for complete documentation]

---

## Video Generation with Veo 3.1

<!-- Source: features/video-generation.md -->

# Video Generation with Veo 3.1

NeuroLink integrates multiple video-generation providers — Google's Veo 3.1 (default), Kling, Runway, and Replicate-hosted models — behind a single `nl.generate({ output: { mode: "video" } })` call.

[Content truncated - see llms-full.txt for complete documentation]

---

## Real-Time Voice Agent - Streaming Voice Loop Design

<!-- Source: features/voice-agent.md -->

# Real-Time Voice Agent - Streaming Voice Loop Design

**Automatic low-latency voice conversations with STT, LLM, TTS, and barge-in support**

## Problem Statement & Solution

### The Challenge


[Content truncated - see llms-full.txt for complete documentation]

---

## Workflow Engine Guide

<!-- Source: features/workflow-engine.md -->

# Workflow Engine Guide

> **Since**: v9.20.0 | **Status**: Stable (Testing Phase) | **Availability**: SDK + CLI
>
> **Provider Defaults:** When `--provider` (CLI) or `provider` (SDK) is not specified, NeuroLink defaults to **Vertex AI** with...

[Content truncated - see llms-full.txt for complete documentation]

---

# Examples

## Examples & Tutorials

<!-- Source: examples/index.md -->

# Examples & Tutorials

Learn NeuroLink through practical examples and step-by-step tutorials for real-world applications.

##  What You'll Find Here


[Content truncated - see llms-full.txt for complete documentation]

---

## Advanced Examples

<!-- Source: examples/advanced.md -->

# Advanced Examples

Complex integration patterns, enterprise workflows, and sophisticated use cases for NeuroLink.

## ️ Enterprise Architecture

### Multi-Provider Load Balancing

```typescript

class LoadBalancedNeuroLink {

[Content truncated - see llms-full.txt for complete documentation]

---

## Basic Usage Examples

<!-- Source: examples/basic-usage.md -->

# Basic Usage Examples

Simple examples to get started with NeuroLink in different scenarios and programming languages.

**Prerequisites**: Before running these examples, ensure you have configured at least one AI provider.

[Content truncated - see llms-full.txt for complete documentation]

---

## Business Applications

<!-- Source: examples/business.md -->

# Business Applications

Enterprise-focused examples demonstrating NeuroLink's value in business environments, ROI optimization, and organizational workflows.

##  Executive Decision Support

### Strategic Planning Assistant


[Content truncated - see llms-full.txt for complete documentation]

---

## Tool Blocking Feature Example

<!-- Source: examples/mcp-tool-blocking-example.md -->

# Tool Blocking Feature Example

This example demonstrates how to use the `blockedTools` feature to prevent specific tools from being executed on external MCP servers.

## Example Configuration

Create or update your `.mcp-config.json` file:


[Content truncated - see llms-full.txt for complete documentation]

---

## Use Cases

<!-- Source: examples/use-cases.md -->

This page has moved to [Real-World Use Cases](/docs/guides/examples/use-cases).

---

# Additional Documentation

This is a summary version. For complete documentation, see:
- Full text: https://docs.neurolink.ink/llms-full.txt
- Web docs: https://docs.neurolink.ink
- GitHub: https://github.com/juspay/neurolink