← Back to iRun

What's New in iRun Studio

All the latest feature releases, model additions, Apple Silicon optimizations, and studio improvements.

v0.4.0

🚧 IN PROGRESS · EARLY SEPTEMBER 2026

The upcoming major milestone introduces the revolutionary Brain Engine with context-driven long-term persistent memory, deterministic execution, structured prompts, expanded tool suites, and major 2D & 3D generation updates to the Design tab.

✨ Upcoming Features & Architecture

  • Brain & Context-Driven Long-Term Memory: Persistent cross-session intelligence that remembers project contexts, architectural decisions, and user preferences over time without prompt bloating.
  • Deterministic Execution & Structured Prompts: Guaranteed reproducible inference with strict JSON/Schema grammar compliance and deterministic seed locking.
  • More Autonomous Tools: Expanded tool suite including direct file synthesis, advanced code runners, arithmetic tools, and custom API webhooks.
  • Design Tab Updates (2D & 3D): Major updates to the Design workspace featuring high-resolution 2D canvas generation and native 3D mesh/object rendering directly on Apple Silicon.
  • Metal Memory Optimizations: Further reduction in memory footprint and accelerated time-to-first-token (TTFT).

v0.3.0

LATEST RELEASE

Comprehensive workstation update adding nested subagents, thinking and functioning loops, code/chat completion, expanded context architecture, font customization, light themes, and major stability patches.

🚀 Highlights & Additions

  • Nested Subagents: Multi-level subagent orchestration and real-time execution telemetry on the 120Hz ProMotion Subagent Bar.
  • Thinking & Functioning Loops: Autonomous execution loops alternating between plan, build, and bughunt.
  • Code & Chat Completion: Fast on-device autocompletion, streaming token generation, and syntax-aware formatting.
  • Expanded Context Architecture: Context preservation techniques that deliver deep memory and recall even with smaller context windows.
  • Font Customization: Full typography selector across SF Pro, JetBrains Mono, New York (Serif), Inter, and Menlo.
  • Light Themes Added: New light glassmorphic palettes including Sakura Frost and Ocean Deep alongside dark themes.
  • Categorized Model Browser: Dedicated Language, Vision, and Logic tabs with 1-click Hugging Face GGUF downloads and real-time web_search.
  • Major Patches & Bug Fixes: Fixed multi-turn conversation memory leaks and optimized Apple Silicon Unified Memory kernel speeds.

v0.2.0

Introduced the React harness, improved tool calling protocols, initial Design tab with 2D and 3D spatial generation, and enhanced lightweight system prompts.

🎨 Key Features

  • React Harness Integration: Live component preview harness and interactive UI sandboxing.
  • Improved Tool Calling: Low-latency autonomous tool execution with real-time argument validation.
  • Design Tab (2D & 3D): Introduced the dedicated Design studio supporting 2D asset creation and 3D spatial models.
  • Enhanced & Lighter System Prompts: Streamlined prompt templates that boost reasoning speed while reducing token overhead.
  • Universal Device Parity: Full feature access across Mac, iPhone, and iPad via Universal Purchase.

v0.1.0 — Studio Inception

Initial release establishing native local AI on Apple Silicon with Stable Diffusion, beta MLX support, response sliders, and customizable themes.

🌟 Initial Release Additions

  • Stable Diffusion Image Gen: Native on-device CoreML Stable Diffusion generation on the Apple Neural Engine.
  • Apple MLX Framework (Beta): Integrated Apple MLX neural framework support alongside the native GGUF engine.
  • Response Sliders: Granular real-time controls for Temperature, Top-P, Repetition Penalty, and Context Length.
  • Customizable Themes & Personas: Native dark glassmorphic themes (Space Obsidian, Midnight, Synthwave) and persona creation.
  • 100% On-Device Privacy Architecture: Zero telemetry, zero external logging, and airplane-mode ready with zero API fees.