Luxonis

October 27th, 2026. https://t.co/d2EjQ8lyn6

Test with a prompt, a link to the release, and our MCP installed https://t.co/ewKYIpRVZM

Build an OAK app around a VLM in about 15 minutes. One prompt to a coding agent with the Luxonis Agent Toolkit gets you live video, a scene description every 15 seconds from LFM2.5-VL-450M on OAK4, and a searchable history of every frame…

Depth AI 3.11 Release: one pipeline, several OAK 4 cameras. Add cameras with addDevice(), sync their frames, and calibration them into one coordinate system with the new MultiDeviceCalibration node (beta). No calibration target. In depth…

You can now run vision-language models on OAK4. Ask the camera if a pallet is fully wrapped and get an answer, generated entirely on-device. New llama.cpp and ONNX Runtime support means no conversion step for VLMs and other larger models.…

Custom model training now in Luxonis Hub, Part 2: Label your data, train, and convert the model for OAK in one workflow. Here's how each step works! 🧵👇 https://t.co/Sxp7F3322t

Custom model training is now live in Luxonis Hub! Label your images, train, evaluate, and deploy to OAK. When the model misses something in the field, snap it from the camera and train the next version. Teams already in hub can try this at…

We just released a new customer story on our blog! Cavalla's autonomous forklifts run with the support of OAK-D Pro W PoE as their main mapping sensor. IP65 for warehouse dust. Global shutter so vibration doesn't wreck depth. One locking…

Getting a working computer vision pipeline shouldn't take you weeks, and with the Luxonis Agent Toolkit... it doesn't. You can now go from Prompt to Pipeline quicker than ever before. Connect the Toolkit to your preferred coding agent and…

Worried you can't get accurate dimensions on your line because your camera can't be straight over top of the conveyor? With OAK 4 and our new Box Dimensioning Solution, this doesn't matter. Due to our ground plane calibration, boxes can be…

Worried you can't get accurate dimensions on your line because your camera can't be straight over top of the conveyor? With OAK 4 and our new Box Dimensioning Solution, this doesn't matter. Due to our ground plane calibration, boxes can be…

UPDATE: Luxonis Chat just went agentic. Ask it anything about OAK or DepthAI and it researches across our docs, examples, Zoo models, shop pages, and the forum before answering. For tricky DepthAI v3 questions it reads a read-only…

Need live dimensions of your boxes saved and stored with time stamps? With OAK 4 and our Box Dimensioning Solution, we save this data for you to reconcile down the road if needed. Live snapshots of what was seen when the box comes, and…

Need live dimensions of your boxes saved and stored with time stamps? With OAK 4 Box Dimensioning, we save this data for you to reconcile down the road if needed. Live snapshots of what was seen when the box comes, and results! Learn more:…

UPDATE: DepthAI 3.10.0 is now available, with quite a big update! Here are some of the main improvements: - Stitching Node arrives in beta - More flexible RVC4 alignment - Saving and reloading Depth AI messages - Improved RVC4 ToF Support…

How does box dimensioning work on an OAK camera? Well the first step is calibration. Angled or top down, doesn't matter! Calibrate your ground plane and measure against real world values. It's as simple as one click, even if camera…

Use our Toolkit in Codex CLI: $luxonis routes the request, the Luxonis MCP server supplies current docs and models, and the agent builds and verifies an OAK app end to end. Install: codex plugin marketplace add luxonis/skills codex plugin…

Install the Luxonis Agent Toolkit (Luxonis MCP + skills) now in Claude, Codex, and Cursor for a better way to build with OAK. It's never been easier to deploy visual intelligence to the edge Github: https://t.co/ge6SlWtfIC Full Release:…