SiMa.ai

SiMa.ai was founded in 2018 by Krishna Rangasayee and is headquartered in San Jose, California. The company builds a co-optimized hardware and software platform for what it calls "physical AI," bringing computer vision, multimodal language understanding, and generative AI out of the cloud and onto embedded edge devices where power, size, and weight are constrained.

General
Company	SiMa.ai
Founded	2018 by Krishna Rangasayee
Headquarters	San Jose, California, USA
Website	sima.ai
Documentation	SiMa.ai Developer Guide
GitHub	github.com/SiMa-ai
Type	Edge AI Semiconductor and Software Platform

Core Products

MLSoC

SiMa.ai's Machine Learning System-on-Chip pairs computer vision and ML acceleration processors with an ARM application processor running Linux, delivering a complete edge inference solution in a low-power package.

MLSoC Modalix

A multi-modal edge AI product family supporting CNNs, Transformers, LLMs, LMMs, and generative AI at the edge, built for more than 10x the performance per watt of alternative edge chips.

Palette Software Platform

Palette covers the full model development cycle, from taking a trained model through optimization and compilation to deploying a fully accelerated application on the MLSoC.

Developer Resources

SiMa.ai provides an SDK and precompiled model library for developers building and deploying computer vision and generative AI pipelines on MLSoC hardware.

Helpful Links

SiMa.ai Developer Guide — Palette and ModelSDK documentation
SiMa.ai Models GitHub — precompiled ModelZoo repository
GitHub — open-source recipes, layers, and sample applications
SiMa.ai DevKit — development kit for evaluating MLSoC hardware
Palette SDK — software platform overview

Key Features

ModelSDK Part of Palette, ModelSDK prepares machine learning models for MLSoC deployment, including conversion to lower-precision data types the chip computes more efficiently.

ModelZoo A library of more than 350 precompiled, MLA-ready models drawn from sources like Torchvision, the ONNX Model Zoo, and OpenVINO's Open Model Zoo, letting developers validate workloads without building from scratch.

Framework-Agnostic Pipeline Palette takes a model from any major framework through optimization, packaging, and deployment as an end-to-end accelerated application on SiMa.ai hardware.

Use Cases

Embedded Computer Vision Run object detection, segmentation, and classification pipelines, including multi-camera setups, directly on MLSoC hardware for robotics, industrial, and smart-camera deployments.

Generative AI at the Edge Deploy LLMs, LMMs, and other generative models on MLSoC Modalix for applications that need physical-world AI without a cloud round trip.

ElderSteady Private — fall alert with proof

Every camera product for an aging parent asks the family to watch, or to trust a company they cannot check. ElderSteady Private runs the camera's brain in the room: YOLO26-m pose on the SiMa Modalix MLA at 8 ms per picture, board-local on NVMe, no cloud. The box counts every picture it sees and destroys, and measures its own network egress on its own interface — 3.36 MB of video in, 11 KB of words out (1:303) — a number a judge can check in one command over serial. When she falls (by lean, or lying on the floor for 3 seconds), it texts the family, not 911, with a receipt instead of a clip; for 60 seconds it listens for "I'm okay" or "help" and nothing is recorded.\ The product is what comes before the fall: sit-to-stand time, seconds on the floor, company minutes, daily rhythm and night wandering — all computed from pose on the MLA, only numbers leave. Thresholds are calibrated to one room and labelled guessed; the 30-day view is fixture and says so; four controlled on-camera tests are in the repo. Built in two days by one founder with an architect session, Codex build lanes, three Claude Code lanes and a GPT-6 research lane, with Senso as shared memory. Repo: github.com/aayushdixit27/eldersteady-private

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.

Recall

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.

AI Conversational Fashion Agent

SafePath Guardian

SafePath Guardian is a camera-based safety copilot designed for autonomous mobile robots operating in busy warehouses. Running on the SiMa.ai Modalix platform, it processes live RTSP video with hardware-accelerated decoding and YOLO26n inference on the Machine Learning Accelerator. The system detects and tracks people across frames, then evaluates their location, confidence, approach motion, and proximity to configurable safety zones. Instead of returning detections alone, SafePath Guardian converts perception into actionable, explainable motion decisions: CLEAR, CAUTION, SLOW, or STOP. A state machine uses persistence and hysteresis to respond quickly to genuine hazards while avoiding unstable commands caused by brief or noisy detections. Each transition includes a human-readable reason, risk score, tracked person ID, and simulated velocity command. The application supports up to four camera streams through a shared detector and presents annotated video, tracking metadata, safety zones, and current decisions in SiMa Insight. It also records structured safety events for later analysis. SafePath Guardian demonstrates how efficient edge AI can provide responsive and transparent collision-risk awareness without relying on cloud processing.