# Agentics

> Agentics is a comprehensive AI infrastructure platform providing unified API access to multi-model LLM inference, voice processing (TTS/STT/VAD/EOT), image generation, embeddings, real-time voice agents, web search, VPN proxy, and developer tools. Built for developers and enterprises who need production-grade AI capabilities through a single API.

Agentics provides a complete end-to-end ecosystem of modular, interconnected services. The central hub is the Agentics API - a production-grade Go-based backend serving 50+ endpoints across inference, audio, images, embeddings, agents, web search, VPN, and real-time voice.

## Website

- [Home](https://agentics.co.za/)
- [Documentation](https://agentics.co.za/docs)
- [AI Models](https://agentics.co.za/models)
- [Pricing](https://agentics.co.za/pricing)
- [Products](https://agentics.co.za/products)
- [Services](https://agentics.co.za/services)
- [Demos](https://agentics.co.za/demos)
- [Chat](https://agentics.co.za/chat)
- [Dashboard](https://agentics.co.za/dashboard)
- [About](https://agentics.co.za/about)
- [Login](https://agentics.co.za/login)
- [Register](https://agentics.co.za/register)
- [Privacy Policy](https://agentics.co.za/privacy)
- [Terms of Service](https://agentics.co.za/terms)

## API Reference

Base URL: https://api.agentics.co.za

### Authentication

All authenticated endpoints require a valid API key or JWT token.
Header: `Authorization: Bearer YOUR_API_KEY`
API keys are prefixed with `ag_`.

- POST `/v1/auth/register` - Register a new user account
- POST `/v1/auth/login` - Authenticate with email and password
- POST `/v1/auth/hardware-auth` - Device-based hardware authentication
- POST `/v1/auth/refresh` - Exchange refresh token for new access token
- GET `/v1/auth/profile` - Get authenticated user profile
- POST `/v1/auth/api-keys` - Generate a new API key
- GET `/v1/auth/api-keys` - List all API keys

### Inference (Text Generation)

- GET `/v1/models` - List all available text generation models
- POST `/v1/generate` - Generate text from a prompt (streaming)
- POST `/v1/chat/completions` - OpenAI-compatible chat completions

Available Models: ALM, ALM-NRN, NRNAgent, Neo, Nitro, PolarisNRN, Pollaris, Sigma, SigmaNRN, Syntactic, Ultra, auto (router)

Model Aliases: default→ALM, flagship→ALM, code→ALM, fast→ALM, memory→NRNAgent, vision→ALM

### Images

- GET `/v1/images/models` - List all available image generation models
- POST `/v1/images/generations` - Generate images from text prompts

25 Image Models: Anime, AnimeReal, Cinematic, Epic, Fantasy, Flux, Ghibli, Juggernaut, LowPoly, Medieval, Pencil, Photo, Pixel, Playground, Portrait, Pro, Professional, Realism, Retro, SDXL, Stock, ThreeD, Turbo, VanGogh, Watercolor

Categories: Photorealistic, Anime, Artistic, Stylized, 3D, General, Fast, Business, Historical

### Audio

- GET `/v1/audio/voices` - List available TTS voices
- POST `/v1/audio/tts` - Text-to-speech synthesis (ONNX, local)
- POST `/v1/audio/stt` - Speech-to-text transcription
- POST `/v1/audio/transcriptions` - Audio transcriptions

Voices: male1, male2, female1, female2, justine

### Live Transcription

- GET `/v1/audio/live/status` - Live transcription service status
- WS `/v1/audio/live/ws` - WebSocket for real-time audio transcription

### Realtime Voice Agent

- GET `/v1/realtime/status` - Realtime agent capabilities and status
- WS `/v1/realtime` - WebSocket for real-time voice AI agent with VAD, EOT, STT, TTS, and tool calling

Audio Format: Input float32 16kHz mono, Output float32 22050Hz mono

### Orb (Embeddable Voice Widget)

- POST `/v1/orb/session` - Create secure session for embedding Orb widget
- GET `/v1/orb/embed` - Get embeddable Orb HTML/JS widget
- WS `/v1/orb/secure-ws` - Secure WebSocket for embedded Orb

### Agent System

- GET `/v1/agent/tools` - List available agent tools
- POST `/v1/agent/message` - Send message to AI agent
- POST `/v1/agent/search` - Web search via agent
- POST `/v1/agent/bash` - Execute bash in sandboxed environment

### Embeddings

- POST `/v1/embeddings/generate` - Generate vector embeddings for text
- POST `/v1/embeddings/add` - Add text and embedding to a group
- POST `/v1/embeddings/search` - Semantic search within a group
- GET `/v1/embeddings/groups` - List all embedding groups
- DELETE `/v1/embeddings/groups/:name` - Delete an embedding group
- POST `/v1/embeddings/memory` - Add user memory

### WebGrep (Web Search & Extraction)

- GET `/v1/webgrep/status` - Service status and available engines
- POST `/v1/webgrep/quick-search` - Fast BM25-scored search chunks
- POST `/v1/webgrep/documentation` - Full documentation page retrieval
- POST `/v1/webgrep/code-examples` - Code implementation patterns
- POST `/v1/webgrep/scrape` - Direct URL content extraction
- POST `/v1/webgrep/multi-search` - Parallel multi-query research

Search Engines: DuckDuckGo, Google, Brave, Startpage, Ecosia, Kagi

### VPN Proxy

- GET `/v1/vpn/servers` - List available VPN servers and regions
- POST `/v1/vpn/setup` - Initialize VPN service
- POST `/v1/vpn/connect` - Establish proxy connection through VPN server
- GET `/v1/vpn/status` - Active VPN session status
- POST `/v1/vpn/disconnect` - Disconnect VPN session

### Payments

- GET `/v1/payments/tiers` - List subscription tiers
- GET `/v1/payments/packages` - Token packages
- POST `/v1/payments/subscribe` - Create subscription
- POST `/v1/payments/tokens` - Purchase tokens
- GET `/v1/payments/subscription` - Get subscription details
- POST `/v1/payments/subscription/cancel` - Cancel subscription
- GET `/v1/payments/history` - Payment history
- GET `/v1/payments/balance` - User balance

Token Packages: Starter (100K) R29, Basic (500K) R99, Standard (1M) R179, Pro (5M) R699, Enterprise (20M) R1,999

### Conversations & Memory

- POST `/v1/conversations` - Create conversation
- GET `/v1/conversations` - List conversations
- GET `/v1/conversations/search` - Search conversations
- GET `/v1/conversations/:id` - Get conversation
- POST `/v1/conversations/:id/messages` - Add message
- GET `/v1/memory` - Get all memories
- PUT `/v1/memory/:key` - Set memory
- DELETE `/v1/memory/:key` - Delete memory

### MCP (Model Context Protocol)

- GET `/v1/mcp/servers` - List MCP servers
- GET `/v1/mcp/servers/:name` - Server status
- GET `/v1/mcp/servers/:name/tools` - Server tools
- POST `/v1/mcp/servers` - Add server
- DELETE `/v1/mcp/servers/:name` - Remove server
- POST `/v1/mcp/tools/call` - Call MCP tool

### CDN & Widgets

- GET `/cdn/agentx-element.js` - Web component
- GET `/cdn/agentx-components.js` - Component library
- GET `/cdn/agentx-powerboard.js` - Powerboard widget
- GET `/cdn/agentx.js` - Full bundle
- GET `/cdn/agentx.css` - Styles

### Workflow Engine

- Proxies to n8n workflow engine
- Visual workflow editor
- Webhook support

## SDKs

- `@agentics/openai` - Drop-in replacement for OpenAI SDK (Chat, Streaming, Images, Audio, Embeddings)
- `@agentics/anthropic` - Drop-in replacement for Anthropic SDK (Messages, Streaming, Tools, Vision)
- `@agentics/google-generative-ai` - Drop-in replacement for @google/generative-ai (Text, Streaming, Chat, Vision, Audio)
- `@agentics/google-genai` - Drop-in replacement for @google/genai Live/Realtime API (Voice, WebSocket, Tools, VAD)

## Products

### Agentics CLI
Full-featured AI agent CLI with terminal UI, desktop GUI, 20+ models, voice chat, integrated tools (bash, file editor, search, web search, image generation, task management, memory), and project/user configuration.
Install: `npm install -g agentics`

### Agentics Taskman
AI-powered task management with TUI, MCP server (18 tools), scheduled AI reminders, subtask management.
Install: `npm install -g @agentics/taskman`

### Agentics Audio
Standalone audio processing: TTS (4 voices, ONNX), STT, live transcription, VAD (Silero), EOT detection, runtime voice commands.

### Agentics WebGrep
Rust TUI for lightning-fast web search with multi-engine support, BM25 RAG mode, history tracking, caching, CSS selector extraction.

### Agentics Tunnel
Rust TCP tunnel for exposing local ports through NAT/firewalls with authentication and auto-port assignment.

### Agentics Embedding (AGemb)
High-performance C-based vector embedding generation and semantic search using ONNX models with SQLite storage.

### Agentics Studio
Web hosting platform on ur1s.xyz with HTML/CSS/JS editor, subdomain management, and visit analytics.

### Agentics Consolidator
TUI process manager for managing all Agentics services with auto-discovery, log streaming, and systemd integration.

### Agentics Live
Desktop application for real-time voice interface (Orb) built with Wails (Go + Web).

### Agentics Markets Live
Real-time financial market data WebSocket server for stocks, crypto, and forex.

## Technology Stack

- Go (primary backend), Rust (CLI tools, tunnel), C (embeddings), TypeScript/JavaScript (web, SDKs)
- MongoDB, SQLite, ONNX Runtime, Gin, Bubble Tea, Tokio
- Multi-provider AI: Pollinations, Groq, HuggingFace, OpenRouter, Gemini, DeepSeek
- Yoco payment processing (South African)

## Contact

- Website: https://agentics.co.za
- API: https://api.agentics.co.za
- Email: connor@agentics.co.za
- Phone: +27 73 541 5134

## Optional

- [Full API Documentation (llms.md)](https://agentics.co.za/llms.md)
- [API Metadata (JSON)](https://api.agentics.co.za/v1/docs/metadata)
- [Interactive Documentation](https://agentics.co.za/docs)