
A native macOS floating workspace that keeps AI conversations, project memory, files and live voice together on your Mac.
A native macOS floating workspace that keeps AI conversations, project memory, files and live voice together on your Mac.
Proto-Mind is a native macOS app from VIRENCORE that collapses AI chat, a browser, project files and saved project memory into one floating workspace you can fold into a cube when you want your screen back. Each conversation can run on its own model and account — a ChatGPT account with Codex access, supported model APIs, or a local model through Ollama — and tasks can run in parallel while you add corrections mid-run. Project memory keeps decisions and preferences attached to a project so you start over less often, and you can review, edit or delete anything it has remembered. Live voice lets you open a project or dispatch a task by speaking, and companion windows detach and resize around your desktop. Mac file and command access is off until you explicitly enable it, and conversation history and memory stay on your Mac. It is an early public beta for Apple Silicon, with the installer and Apache 2.0 source both available.

A native macOS floating workspace that keeps AI conversations, project memory, files and live voice together on your Mac.
Proto-Mind works by combining Floating Cube Workspace: Hover the cube to reveal the workspace and click to pin it, or move away to hide it while tasks keep running in the background., Per-Conversation Model Routing: Each chat picks its own model and account — ChatGPT with Codex access, supported model APIs, or a local Ollama model., Editable Project Memory: Notes, decisions and preferences stay attached to a project and carry into later conversations, and you can review, change or remove any of them., Live Voice Control: Speak to open a project, steer a running task or send new work, and add a correction while the task is still going., Detachable Companion Windows: Pull out and resize a browser, a file or a second conversation so reference material sits beside the work. to help users with Long-Running Project Work: Keep a website or client project's decisions in project memory so each session resumes instead of re-explaining the brief., Brief to Deliverable: Have the agent read a client brief and save a proposal document, then open it in a companion window next to the conversation., Parallel Task Execution: Start several tasks across different models at once and check back on them without blocking the conversation you are in., Hands-Free Steering: Dictate a correction or open a project by voice while your hands are busy elsewhere on the Mac., Privacy-Sensitive Drafting: Run a local Ollama model so conversation content never leaves the machine..
Key features include Floating Cube Workspace: Hover the cube to reveal the workspace and click to pin it, or move away to hide it while tasks keep running in the background., Per-Conversation Model Routing: Each chat picks its own model and account — ChatGPT with Codex access, supported model APIs, or a local Ollama model., Editable Project Memory: Notes, decisions and preferences stay attached to a project and carry into later conversations, and you can review, change or remove any of them., Live Voice Control: Speak to open a project, steer a running task or send new work, and add a correction while the task is still going., Detachable Companion Windows: Pull out and resize a browser, a file or a second conversation so reference material sits beside the work..
Proto-Mind is useful for anyone interested in Long-Running Project Work: Keep a website or client project's decisions in project memory so each session resumes instead of re-explaining the brief., Brief to Deliverable: Have the agent read a client brief and save a proposal document, then open it in a companion window next to the conversation., Parallel Task Execution: Start several tasks across different models at once and check back on them without blocking the conversation you are in., Hands-Free Steering: Dictate a correction or open a project by voice while your hands are busy elsewhere on the Mac., Privacy-Sensitive Drafting: Run a local Ollama model so conversation content never leaves the machine..
Proto-Mind is free to use.
Visit https://virencore.com/ to sign up and explore Proto-Mind.
Browse by use case: Code Generation · Voice & Audio · Automation & Productivity
Compare Proto-Mind: vs Ami · vs Duvi · vs AskDeck · vs Amy by Jellyfish