AI assistant providing access to top AI models without sign-up or ads
Private personal AI for Mac that knows your work
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Freemium
Freemium
Pricing
Free plan with 102 daily queries; Merlin Pro at $19 per month billed annually. Free users get 102 queries daily with GPT 3.5, Gemini, and Claude 3 Haiku consuming 1 query each; GPT 4, Gemini 1.5, and Mistral Large consuming 30 queries each.
Not given
Key features
Access to multiple AI models including ChatGPT, Claude, Gemini, DeepSeek, and Mistral
Real-time web search integration
YouTube video summarization and transcription
Chrome extension for one-click answers
Social media content generation and posting
Email composition with AI
Custom knowledge bases and projects
Code snippets and web components generation
Diagram and flowchart generation
AI image generation with Flux 1.1 Pro
Chat to ask about work with answers sourced from your messages, calls and notes
Dictation in any text box on Mac, including browsers and code editors
Voice to talk to Jelly from any app and get spoken answers
Meeting prep, live assist and notetaker with no bot joining the call
Open Loops to track what you promised people and tick off when done
Create emails, documents, sheets and slides from conversations
Agents to do tasks on the web with transparency and payment confirmation
MCP to share chosen memory with Claude, ChatGPT or Cursor
Encrypted memory on Mac with option to use your own API key
Works offline for local processing with no screen recording
What makes it different
Free access to multiple top AI models without separate subscriptions
Works without sign-up or ads
Available in 200+ countries where ChatGPT is restricted
All AI tools consolidated in one affordable subscription
Works seamlessly across all devices with synchronized history
All AI features in one subscription instead of paying for separate apps
Memory stays encrypted on your Mac, never sent to cloud unless you choose
One memory connects all features so each knows what you're working on
Scored 87.6% on BEAM public test for long-term memory accuracy
Agents work in their own browser and stop to ask before paying