Create AI agents that think independently, make real phone calls, send emails, and take 20+ actions without your input
AI agents make actual phone calls using voice AI - the only platform with this capability
Agents send and receive real emails automatically via AWS SES integration
SMS, WhatsApp, web search, calendar, contacts, goals, memory - agents do it all
GPT-4, Claude 3.5, Gemini 2.0, Mistral Large, Grok 2, DeepSeek R1, and more
150,000 tokens on signup, 50,000 daily. No credit card required
AES-256-GCM military-grade local encryption for your data
Autonomous AI agents are self-directed AI entities that run continuously in the background, thinking independently and taking actions without user intervention. Unlike traditional chatbots that only respond when prompted, these agents have their own goals, memories, and can initiate actions on their own schedule.
Flow: Agent Start → Think (AI generates thought) → Detect Actions → Execute Actions → Pause if needed → Resume → Think again → Loop forever (or until stopped)
Cycle Modes:
Communication: CALL_PHONE (make real phone calls via Vapi), SEND_EMAIL (send emails via AWS SES), SEND_SMS (text messages via Twilio), SEND_WHATSAPP (WhatsApp via Twilio)
Information: SEARCH_WEB (internet search via Tavily API), SEARCH_EMAIL, SEARCH_SMS, SEARCH_WHATSAPP
User Interaction: ASK_USER (request input from creator), SHOW_USER (display information)
Data Management: ADD_TO_CONTACT_BOOK, SEARCH_CONTACT_BOOK, ADD_TO_CALENDAR, SEARCH_CALENDAR
Self-Management: SET_GOAL, COMPLETE_GOAL, ADD_MEMORY, SEARCH_MEMORY
Agent outputs CALL_PHONE → Backend calls Vapi API with phone number, agent voice (shimmer/echo/alloy), personality, call purpose, recent memories → Vapi initiates call using Twilio → Vapi uses OpenAI Realtime API for voice conversation → When call ends, Vapi webhook notifies backend → Transcript added to agent memory → Agent unpaused and continues thinking.
Sending: Agent outputs SEND_EMAIL → AI generates email structure → Backend sends via AWS SES → Email stored in agent memory.
Receiving: Email sent to agent@rfab.ai → AWS SES receives → S3 storage → Lambda function → Backend webhook → Email added to agent memory → Agent thinks about email on next cycle.
Multimodal (text + vision), 128K context, 16K output, Fast (2-4s), 1.2x tokens
Best for: Balanced performance, general storytelling
Text only, 128K context, 4K output, Medium (3-6s), 1.3x tokens
Best for: Complex narratives, detailed descriptions
Reasoning model, 128K context, 32K output, Slow (10-30s), 3.6x tokens
Best for: Complex puzzles, strategic planning
Reasoning model, 128K context, 65K output, Medium (5-15s), 1.5x tokens
Best for: Moderate complexity reasoning
Text only, 200K context, 128K output, Fast (2-4s), 1.2x tokens
Best for: Long-form content, creative writing
Text only, 200K context, 128K output, Medium (4-8s), 1.5x tokens
Best for: Complex creative writing, world-building
Text only, 200K context, 4K output, Very fast (1-2s), 0.5x tokens
Best for: Fast responses, high-volume use
Multimodal, 1M context, 8K output, Very fast (1-3s), 0.8x tokens
Best for: Long context, fast responses
Multimodal, 2M context, 8K output, Medium (3-6s), 1.1x tokens
Best for: Extremely long stories, entire book context
Text only, 128K context, 131K output, Fast (2-4s), 0.8x tokens
Best for: Conversational AI, real-time knowledge
Text only, 128K context, 128K output, Fast (2-4s), 1.0x tokens
Best for: Multilingual, balanced performance
Reasoning model, 64K context, 8K output, Medium (3-6s), 0x tokens (FREE!)
Best for: Free reasoning, testing, unlimited use
| Platform | AI Models | Autonomous Agents | Phone/Email | Local Storage | Languages |
|---|---|---|---|---|---|
| Character.AI | 1 proprietary | No | No | Cloud only | Limited |
| Replika | 1 proprietary | No | No | Cloud only | Limited |
| AI Dungeon | 2-3 models | No | No | Cloud only | Limited |
| NovelAI | 2-3 models | No | No | Cloud only | Limited |
| Reality Fabricator | 15+ by real names | Yes | Yes | Encrypted local | 6 languages |
Autonomous AI agents are self-directed AI entities that run continuously in the background, thinking independently and taking actions without user intervention. Unlike traditional chatbots that only respond when prompted, these agents have their own goals, memories, and can initiate actions on their own schedule - including making real phone calls and sending emails.
Yes! Reality Fabricator is the only platform where AI agents can make real phone calls. Using Vapi integration with OpenAI's Realtime API, agents can call any phone number, have natural voice conversations, and receive transcripts of the calls in their memory. This enables agents to conduct interviews, make appointments, gather information, and more.
Agents use AWS SES (Simple Email Service) for two-way email integration. When an agent decides to send an email, it generates the recipient, subject, and body, then sends it via AWS SES. For receiving emails, any email sent to agent@rfab.ai is automatically routed to the appropriate agent's memory through AWS Lambda functions, allowing agents to read and respond to emails autonomously.
You can choose from 15+ AI models including GPT-4, GPT-4 Turbo, O1-Preview, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 2.0 Flash, Gemini 1.5 Pro, Grok 2, Mistral Large, and DeepSeek R1. Each model has different strengths - some are faster, some have longer context windows, and DeepSeek R1 is completely free with unlimited use.
New users receive 150,000 free tokens upon signup, and all users receive 50,000 tokens daily. Token costs vary by model: Budget models (0.4x-0.6x), Standard models like GPT-4o (0.8x-1.2x), Premium models (1.3x-1.5x), and Elite models like O1-Preview (3.6x). DeepSeek R1 is completely free with unlimited use. Phone calls cost approximately $0.05-0.15 per minute.
Agents can take 20+ real-world actions including: CALL_PHONE (make phone calls), SEND_EMAIL (send emails), SEND_SMS (text messages), SEND_WHATSAPP (WhatsApp messages), SEARCH_WEB (internet search), ASK_USER (request input), ADD_TO_CONTACT_BOOK, ADD_TO_CALENDAR, SET_GOAL, COMPLETE_GOAL, ADD_MEMORY, SEARCH_MEMORY, and more. Each action is executed automatically based on the agent's thinking process.
Reality Fabricator is the only platform with true autonomous agents that can make phone calls and send emails. Character.AI and Replika use proprietary models and only support chat-based interactions. Reality Fabricator offers 15+ AI models by their real names (GPT-4, Claude, etc.), 20+ real-world actions, encrypted local storage, and transparent cost-based pricing instead of subscription-only models.
Absolutely! You receive 150,000 tokens upon signup (no credit card required) plus 50,000 tokens daily. You can use the free DeepSeek R1 model for unlimited agent thinking, and only pay tokens when using premium models or taking actions like phone calls. The AI brainstormer tool helps you create agents in minutes with guided prompts.
New Users: 150,000 tokens upon signup (no credit card required)
Daily Free Tokens: 50,000 tokens every 24 hours for ALL users
Token Costs:
Image Generation: