@RidgeRunAI

Computer Vision and Analytics

 Minnesota, USA
ridgerun.ai
Joined September 2022
  • Tweets141
  • Following42
  • Followers32
44Media
🚀 Learn how to convert ONNX models into DLA binaries for the MediaTek Genio 700 NPU using TensorFlow Lite and NeuroPilot. 🔗 Read the step-by-step guide: ridgerun.ai/post/how-to-conv…
1
16
🚀 Getting started with the MediaTek Genio 700? Explore Yocto-based development, system image flashing, and UART setup in our latest technical guide. 🔗 ridgerun.ai/post/first-steps… #MediaTek #Genio700 #EdgeAI #EmbeddedLinux
2
21
What stood out at @OpenAI DevDay 2026? AI agents that keep working, new models, and more tools for developers. We break down Dots, GPT-6.1 Sol, Codex Cloud, the Agents API, and more in our full recap: ridgerun.ai/post/openai-devd… #OpenAI #DevDay

OpenAI DevDay 2026: Everything Announced

OpenAI DevDay 2026 introduced Dots, ChatGPT Space, GPT-6.1 Sol, new Codex capabilities, faster inference, agent APIs, and major updates for developers building AI-powered applications.

ridgerun.ai
2
63
Using DeepStream 9 skills, an AI coding agent built a 12-camera system on Jetson AGX Thor and lifted throughput from 1.72 to 30.27 FPS/camera! 3D tracking, bird’s-eye view, heatmaps, restricted-zone alerts & NVIDIA Cosmos VLM reasoning, autonomously. 🚀 bit.ly/4hatnft

Using DeepStream Skills to Build a Multi-Camera Tracking and Alerting System

See NVIDIA DeepStream skills in action through a 12-camera AI tracking pipeline powered by RF-DETR. Explore multi-stream processing, AI inference, real-time tracking, and analytics for warehouse...

ridgerun.ai
2
33
How far can you push LLM efficiency on @NVIDIAAI Jetson? We benchmarked Qwen 2.5 across PyTorch and TensorRT Edge-LLM to reduce its memory footprint and compared its impact in inference speed and model quality. Read the results:
ridgerun.ai/post/nvidia-jets…
🤖 Made with AI
RidgeRun AI graphic promoting an analysis of running generative AI models on NVIDIA Jetson with reduced memory. It highlights an FP16, INT8, and INT4 comparison of memory usage, throughput, and model quality, alongside an NVIDIA Jetson development board.

ALT RidgeRun AI graphic promoting an analysis of running generative AI models on NVIDIA Jetson with reduced memory. It highlights an FP16, INT8, and INT4 comparison of memory usage, throughput, and model quality, alongside an NVIDIA Jetson development board.

2
61
AI deployment on NVIDIA Jetson is often a balance between memory, performance, and accuracy. In our latest guide, we explore practical techniques to optimize deep learning models for efficient edge deployment in your @NVIDIAAI Jetson platform. ridgerun.ai/post/nvidia-jets…

Memory Optimization Best Practices to run AI models on NVIDIA Jetson

Learn practical techniques to reduce AI model memory usage on NVIDIA Jetson using TensorRT, FP16 and INT8 quantization, static input shapes, pruning, and other deployment optimizations, while...

ridgerun.ai
2
27
Is your AI software production-ready? RidgeRun.ai Code Audits help identify performance bottlenecks, architecture risks, and scalability issues before they impact your product. Let’s review your code: ridgerun.ai/contactus
Promotional graphic for RidgeRun AI asking, “Is Your Code Production-Ready?” It advertises code audits to identify architectural issues, reduce risks, optimize performance, and improve performance, code quality, architecture, reliability, and scalability, with a magnifying glass over code and a checkmark.

ALT Promotional graphic for RidgeRun AI asking, “Is Your Code Production-Ready?” It advertises code audits to identify architectural issues, reduce risks, optimize performance, and improve performance, code quality, architecture, reliability, and scalability, with a magnifying glass over code and a checkmark.

3
49
🚀RidgeRun.ai will be attending Automate 2026 in Chicago on June 22–23. If your team is exploring what’s next in AI, robotics, computer vision, or industrial automation, let’s meet and talk. Schedule a meeting with RidgeRun.ai:  ridgerun.ai/contactus
Automate 2026, June 22-25, Chicago Illinois. Reach out to connect with RidgeRun.ai

ALT Automate 2026, June 22-25, Chicago Illinois. Reach out to connect with RidgeRun.ai

1
6
RidgeRun.ai retweeted
SkalskiP
@skalskip92Jun 16
RF-DETR keypoints is finally out preview release: real-time transformer keypoint detection Apache 2.0 71.8 AP on COCO, 9.7ms on T4. outperforms YOLO11-pose and YOLO26-pose at similar latency
31
152
12
1,318
98,988
Voice agents are built as speech-to-speech (s2s) or as cascades of transcription, llm and synthesis. The former is fast, the later is smart. @SakanaAILabs presents KAME: combining LLMs with s2s. Fast and smart! pub.sakana.ai/kame/

Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture

KAME augments a responsive speech-to-speech model with asynchronous knowledge injection from a backend LLM.

pub.sakana.ai
1
1
25
Curious about running your AI models on the @AxeleraAI Metis using GStreamer? We’ve put together a starter guide to help you integrate your AI accelerator seamlessly into your applications with the power of GStreamer pipelines. ridgerun.ai/post/gstreamer-i…

How to Run a GStreamer Inference Pipeline on Axelera

Deploy a GStreamer inference pipeline on Axelera AI hardware using the Voyager SDK. Learn how to build, run, and extract AI results step-by-step.

ridgerun.ai
1
3
108
The Metis M.2 lived up to the hype! We're excited to explore its full potential in upcoming projects. Kudos to the @AxeleraAI team for their constant releases and their quick support.
Axelera AI
@AxeleraAI16 Jul 2025
Great work from @ridgerunai getting the Metis M.2 AI accelerator running on Raspberry Pi 5 🔥 They break down setup, deployment with Voyager SDK & real-world benchmarks. Great guide if you’re into embedded AI, or looking for someone to help with your AI project/build 👇 🔗 eu1.hubs.ly/H0lN_Py0 #EdgeAI #RaspberryPi #MetisAIPU @Raspberry_Pi
2
8
254
About to assemble our SO-ARM101, a @huggingface compatible robotic arm! 🦾 🤗
A box with a set of 3D printed pieces and a sticker that reads: "HuggingFace LeRobot Official Hardware Partner"

ALT A box with a set of 3D printed pieces and a sticker that reads: "HuggingFace LeRobot Official Hardware Partner"

1
1
3
116
ok, half way there 😮‍💨
a table with a robotic arm half built

ALT a table with a robotic arm half built

2
28
LLMs excel at function calling, but they’re often too resource-intensive for edge devices. In our latest blog post we share how we fine-tuned a compact, local model: 𝗝𝘂𝗻𝗶𝗽𝗲𝗿, to perform reliable tool invocation. ridgerun.ai/post/introducing…

Introducing Juniper: How We Fine-Tuned a Small and Local Model for Function Calling

This post will take you through our journey on how we fine-tuned a model for function calling.

ridgerun.ai
1
1
34
The result? 𝗝𝘂𝗻𝗶𝗽𝗲𝗿 outperforms GPT-4o in our function-calling tasks and other standard benchmarks, all while running efficiently on limited hardware. 🚀
25
Ready to play with out new @AxeleraAI Metis M.2 board 😎. Stay tuned for the full walkthrough!
A hand holding an electronic card that reads Axelera. The cards is sitting on a paper that reads Metis M.2

ALT A hand holding an electronic card that reads Axelera. The cards is sitting on a paper that reads Metis M.2

1
3
9
194
One of the most exciting mergers of history. @OpenAI to be merged with Jonny Ive's company: IO
This quoted post is unavailable.
Try viewing anyway · View on X
1
74
🚀 Automate 2025 is here! 🤖✨ We’re excited to be part of the Automate Show this week! Come meet the RidgeRun.ai team and see how our cutting-edge AI solutions can supercharge your next project. 💡💻 📍 Want to chat? Let’s connect — our engineers are ready to meet you at the show! 🤝
A conference hall with several banners announcing the Automate 2025 conference

ALT A conference hall with several banners announcing the Automate 2025 conference

1
41
A few months ago @AnthropicAI announced the Model Context Protocol: an open standard to interconnect language models with external tools and data sources. Learn how to build your own MCP server in our most recent post: ridgerun.ai/post/how-to-writ…

How to Write Your MCP Server in Python

Discover how to build a simple MCP server in Python to manage a to-do list example using the Model Context Protocol (MCP). This step-by-step guide walks you through creating the server, connecting it...

ridgerun.ai
1
37
Load more