Actuate 26: Foxglove introduces agentic data platform for physical AI and Semantic Search

Adds AI interface to Foxglove’s data platform and integrates Cosmos into Semantic Search

Foxglove

By Robotics 24/7 Staff    August 21, 2026         

Actuate 26: Foxglove introduces agentic data platform for physical AI and Semantic Search

Foxglove

At its Actuate 26 conference, Foxglove announced the agentic data platform for physical AI and Semantic Search capabilities.

Email Sign Up

Get news, papers, media and research delivered. Sign up for our free newsletters.

Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get weekly market intelligence with Robotics 24/7.

Robotics 24/7 newsletter
Actuate 26: Foxglove introduces agentic data platform for physical AI and Semantic Search

Foxglove

At its Actuate 26 conference, Foxglove announced the agentic data platform for physical AI and Semantic Search capabilities.

At Actuate 26 in San Francisco, robotics development software provider Foxglove’s annual event, the company made two announcements related to AI and its platforms.

First, the company introduced the agentic data platform for physical AI, enabling users to collect, debug, search and curate robotics data across the full lifecycle - with agents built into the platform.

Next, Foxglove added the Semantic Search feature to its platform, allowing users to search image and video topics in recordings with a plain-language prompt.

Speeding up the physical AI learning loop

Through the introduction of the agentic data platform for physical AI, Foxglove said that it is enabling developers to rapidly build, monitor and improve robots across the data lifecycle. The company said that these capabilities help developers easily connect and collect data from live robots; more effectively triage and debug robot performance; more quickly search and curate recordings to find the events that matter.

Foxglove said that Agent Sidebar, which is built into the app, is the agentic front door to the platform. Developers no longer need to move between screens to search and load recordings, create layouts or get answers to questions. The company said that the agent derives the intent of the user’s request based on the context. Users can describe what they need in natural language, and the agent searches, reasons, configures and acts - grounded in actual robotics data.

“It replaces a whole flow for me. Instead of writing scripts or tabbing through all the plot fields myself, it just creates everything for me,” said Alex David, software engineer at Cobot and a user of the agentic data platform for physical AI.

Click here to learn more about these agentic AI capabilities.

Speeding up search

As part of the agentic data platform, Foxglove said that Semantic Search lets users search for objects or scenes in image and video topics in their recordings, using plain-language text prompts. The company said that it comes with several other improvements to make the search experience more intuitive.

On the search page, Foxglove said that users can now search using a visual description instead of specifying exact metadata. Results come back in a gallery view, so users can preview them and open only the ones that matter.

The company said that Semantic Search is powered by vector search over frame embeddings. While ingesting data, Foxglove decodes image and video topics, samples frames (a frame per topic per second), and runs them through an image embedding model. The vectors are stored in Lance tables in the object storage.

Foxglove said that the prompt goes through the same model, and results are ranked by cosine similarity. Structured conditions are applied first: device, time range, and topic narrow the candidate set, and then the vector search orders what’s left. The company said that Semantic Search understands two levels of context. Object and scene search finds matches within a single frame. Action search, powered by NVIDIA Cosmos open world models, reasons across sequences of frames to recognize motion and events that no single image can capture.

Foxglove said that image and video support is just the first step in Semantic Search. The company said that its goal is to extend the same concept (the ability to search based on description) to all other data types that robots emit.

Click here to learn more about Semantic Search features and capabilities.

 

Latest in Research & Development

Latest in Artificial Intelligence

Article Topics

Artificial Intelligence   Machine Learning   Software   Data Management   Robot Operating System   Simulation   News   Press Release   Artificial Intelligence   Foxglove   Research & Development   Software  

All topics

Enjoyed this article? Add Robotics 24/7 as a preferred source in Google Search.

Editors' Picks

Jensen Huang resigns as NVIDIA CEO amid affairs scandal
Jensen Huang resigns as NVIDIA CEO amid affairs scandal

Colette Kress, current EVP and CFO of NVIDIA named interim CEO

SoftBank’s proposed $5.4B acquisition of ABB Robotics blocked by China
SoftBank’s proposed $5.4B acquisition of ABB Robotics blocked by China

China's Office of the Working Mechanism for Foreign Investment Security…

White House targets robotics imports in new national security trade review
White House targets robotics imports in new national security trade review

President Trump orders a review of robotics imports over national security…

OSARO SightWorks advances AI-powered robotic picking and packing
OSARO SightWorks advances AI-powered robotic picking and packing

Platform helps robots adapt to complex tasks