Palette Neat

Palette Neat is SiMa.ai's agentic development environment for Physical AI, launched in 2026 as what the company describes as the industry's first tool of its kind. It combines a Physical AI execution library with an agent workflow layer, letting developers describe a system in natural language rather than hand-writing low-level porting and integration code for new silicon.

General
Release date	2026
Developer	SiMa.ai
Type	Open-source agentic IDE for Physical AI
License	Open source
Documentation	SiMa.ai Developer Center

Core Features

Natural-language development — developers issue natural-language commands to build entire application systems, abstracting away low-level compute complexity.
Legacy code reuse — preserves roughly 90% of existing application code when porting to Modalix hardware, rather than requiring a full rewrite.
Physical AI execution library — a purpose-built runtime layer for robotics, automotive, drones, industrial automation, aerospace and defense, smart vision, and healthcare workloads.
Hardware pairing — works with the full-production Modalix MLSoC System-on-Module or its PCIe companion card for high-demand Physical AI deployments.

Tools and Resources

SiMa.ai Developer Center — developer.sima.ai, full documentation for Palette Neat and the broader Palette platform.
SiMa.ai GitHub — github.com/sima-neat/apps, example applications built with Palette Neat.

Ecosystem and Integrations

Pairs with Modalix MLSoC hardware, from the DevKit through the production System-on-Module and PCIe card form factors.
Sits alongside SiMa.ai's broader Palette platform and ModelSDK/ModelZoo tooling for the full model development cycle.

Start from the SiMa.ai Developer Center or the Palette Neat example applications repository.

Edit on GitHub

SiMa Palette Neat top builders

Explore the top contributors showcasing the highest number of SiMa Palette Neat app submissions within our community.

sima-ai SiMa Palette Neat AI technology Hackathon projects

Discover innovative solutions crafted with SiMa Palette Neat, developed by our community members during our engaging hackathons.

Recall

Recall turns first-person recordings, like footage from smart glasses, into a memory you can ask questions. You can ask "When was I fixing my bike?", "What was I doing before I started coding?" or "Where did I leave the wrench?", and Recall answers with a timestamp and the video clip or frame that backs it up. Everything runs locally. FFmpeg samples each video at 2 frames per second using its real timestamps. Grounding DINO Tiny finds objects and hands, and RelateAnything works out how they relate, for example holding, on, or beside. A tracker links sightings over time. From those sightings, rules build activity episodes and object states, and all of it is stored in SQLite. A FastAPI backend and a plain web UI answer questions from that data. We built it to be honest. Location answers say "last seen" and never claim to know where something is now. If a question is ambiguous or a recording failed to process, Recall says so instead of guessing. It never uses upload time as a stand-in for capture time. There is no cloud inference and no API key.

AI Conversational Fashion Agent

Modalix Edge AI Conversational Fashion Stylist delivers personalized outfit guidance through a live video feed with real-time person detection and tracking. Running on SiMa.ai Modalix and Neat, it uses YOLO26 on the MLA accelerator to detect people and an IoU tracker to assign temporary track IDs as they move through the scene. Users can visually select any detected person and request recommendations through a conversational interface. The application preserves separate chat history, styling preferences, occasion details, cultural context, and recommendations for each selected individual. Switching people loads the appropriate saved conversation and context without mixing information, while switching back restores the earlier session. A locally deployed Qwen3-VL model analyzes visible clothing, understands occasion, location, climate, culture, and dress-code requirements, and generates relevant real-time suggestions. Annotated video and metadata are streamed to Neat Insight, allowing users to view live tracking, selections, and recommendations together. The system does not perform identity recognition or infer sensitive personal attributes.

Baseline

This project demonstrates real-time edge AI video analytics on SiMa.ai Modalix hardware. It receives H.264 video over RTSP, decodes the stream, and runs a compiled YOLOv8n object-detection model on the Modalix MLA accelerator. The pipeline preserves a shared timeline between video and inference, ensuring detection metadata stays synchronized with the corresponding frames. Processed H.264 video and object-detection metadata are streamed to Neat Insight, where users can view live bounding boxes, COCO labels, confidence scores, and performance statistics in a browser. The application is configurable for model paths, source streams, thresholds, and Insight endpoints, and includes build, deployment, validation, and health-monitoring instructions for running the complete workflow on a Modalix DevKit.