Foxglove adds AI tools for robotics data workflows. Foxglove announced a new intelligent AI layer that enables robotics developers to search, visualize, compare, debug, and curate multimodal datasets by simply describing what they need in natural language. Foxglove's new agentic capabilities are available through the Agent Sidebar, a built-in agent inside the Foxglove app, and the Foxglove MCP server, which lets external AI agents interact with Foxglove. These new AI-powered capabilities automate the work required to turn raw multimodal data into high-value datasets, evaluations, and insights that improve models and performance. Foxglove also introduced Semantic Search powered by the open NVIDIA Cosmos world models, Comparison Mode, and Remote Access, new capabilities that make it easier for developers to find critical events across large robotics datasets, compare system behavior across runs, and debug robots in the field without needing to send engineers onsite. Robotics programs advance at the rate teams can close the loop between a failure in the field and a validated fix. Today that loop consumes much of an autonomy team's engineering capacity, while most of the data a fleet collects is never reviewed. Foxglove raises the yield on data teams have already paid to collect and store, converting it into more model improvements per quarter. It frees engineers for model development and lets teams diagnose field incidents the same day, without scheduling an onsite visit. Foxglove and NVIDIA collaborate to bring semantic search to Physical AI. Foxglove Semantic Search enables users to describe a behavior or scenario in natural language, and Foxglove retrieves matching multimodal segments from across large volumes of unlabeled data. Each result stays connected to the synchronized sensor data, telemetry, logs, and system signals recorded around that moment, so developers move directly from finding an event on camera to understanding what the rest of the robot was doing when it happened. Foxglove Semantic Search is powered by NVIDIA Cosmos, a video-text embedding model purpose-built for Physical AI. General-purpose image-text models are trained on internet data and lose accuracy on complex manipulation tasks, driving scenes, and temporal action data. NVIDIA Cosmos is a frontier foundation model trained on robotics, driving, and ego-centric human action data, which delivers state-of-the-art retrieval accuracy on physical AI benchmarks. Foxglove and NVIDIA collaborated to bring Semantic Search powered by Cosmos to physical AI teams, with fully managed indexing and inference infrastructure requiring zero operational overhead and maintenance. When combined with Foxglove's Bring-Your-Own-Storage (BYOS) architecture, Semantic Search is able to index and search over raw logs stored directly in customer cloud storage, without any unnecessary duplication of data. Turning production data into a learning loop. As robotics fleets scale, teams generate more data across more robots, environments, and model versions. The events that drive improvement are rare, and their value depends on how quickly developers can find them, understand what happened, and turn them into fixes, evaluations, or training data. Foxglove's new capabilities connect and accelerate each step: * Agent Sidebar coordinates work across the platform, allowing developers to find data, create visualizations, investigate failures, compare runs, and curate results into datasets. * Semantic Search powered by NVIDIA Cosmos finds relevant behaviors and events across large volumes of unlabeled robot data. * Comparison Mode synchronizes two or more runs so teams can understand where behavior diverged across models, software versions, robots, or scenarios. Comparisons are a critical tool for understanding drift between model versions and validating each release. * Remote Access streams every topic from a remote robot directly to the browser, letting engineers observe and debug a deployed system in real time from anywhere. Camera, lidar, telemetry, and logs arrive at low latency in the same application teams use to visualize recorded data, so field issues can be diagnosed without sending anyone onsite. Every capability announced today rests on the same foundation: time-synchronized data from cameras, lidar, radar, transforms, telemetry, and logs, connected as a single record of what a robot actually did. That grounding is what makes agentic workflows dependable in Physical AI, where every answer has to hold up against the physical world. As companies scale from a handful of robots to fleets in production, Foxglove is where the data they collect becomes the engine behind every improvement they ship.

Foxglove launches unified data platform to accelerate physical AI development. Discover more Factory Automation E-commerce Foxglove has launched "Data Search and Curation", a new set of capabilities that helps robotics teams replace fragmented, manual data workflows with a unified platform to find and curate the mission-critical events, anomalies, and system behavior that matter most across growing volumes of operational data. The company also expanded the Foxglove Data Platform with Bring Your Own Storage (BYOS), a new self-hosted data lake deployment model allowing customers to maintain full control over data at rest while still providing the benefits of a fully managed database, and a new free Basic Seat tier to expand access to visualization across teams. As robotics companies scale from prototype to production, the critical path is shifting from generating more data to finding the most essential data quickly enough to debug issues, investigate failures, review safety-critical events, and improve system performance. Foxglove's latest product updates are designed to address that shift by enabling teams to inspect more data faster, bring more people into key workflows, and support more flexible operations across complex deployments. Adrian Macneil, co-founder and CEO, Foxglove, says: "Robotics teams are generating more data than ever, but the real challenge is finding the critical 1 percent that drives improvement in the real world. "Companies that win in physical AI are the ones with the strongest data flywheel, turning production robot data into better decisions, faster model improvements, and new robot capabilities. "Data Search and Curation helps teams uncover that high-value 1% faster so they can learn faster and improve robot performance in the real world." Find the data that matters faster. Foxglove is launching Data Search and Curation to help robotics teams find, organize, and operationalize data more effectively. With Data Search, users can directly query multimodal robotics data, making it faster to identify events of interest without needing to preprocess or ingest data into a separate data warehouse. New data curation capabilities help teams tag, annotate, and enrich events, making it easier to preserve key findings, build training and validation datasets, and support repeatable analysis across programs. Together, these capabilities help robotics developers improve iteration speed, streamline collaboration, and turn growing volumes of robotics data into actionable insights. For teams operating in complex or safety-critical environments, faster access to relevant data can accelerate debugging, model training, validation, and overall system improvement, strengthening the data flywheel that helps teams learn faster and improve systems over time. Shared visibility across teams. Foxglove is introducing a new free Basic Seat tier to make it easier for robotics organizations to extend access beyond engineering to teams involved in QA, triage, safety review, and management. Basic Seats give more stakeholders direct visibility into robot behavior, system performance, and operational events. By giving more teams access to the same data and workflows engineering relies on, Basic Seats help organizations reduce handoff friction, accelerate issue investigation, and improve alignment across development and operations. The result is a more scalable way to support collaboration, speed decision-making, and bring the right people into critical workflows as robotics programs grow. Enterprise-grade data control, without the complexity. Foxglove is introducing BYOS, a bring your own storage deployment model that gives enterprise robotics companies more control over how their data is stored and managed without needing to manually provision cloud infrastructure. With BYOS, customers host all multimodal log data in their own cloud object storage, while Foxglove provides the managed compute and services to make that data usable, including indexing, query, search, evaluation, and metadata workflows. For enterprise teams, BYOS offers the ability to scale Foxglove in environments with stricter data, infrastructure, or residency requirements. It gives customers tight control over their data while reducing the operational burden that comes with running a self-hosted Kubernetes deployment. The result is a more flexible deployment model that helps organizations move faster without compromising on enterprise requirements. One platform to manage the physical AI data lifecycle. Together, these product updates reflect Foxglove's evolution from observability into a comprehensive physical AI data platform to capture and learn from all types of multimodal data. As the industry scales, Foxglove will continue to expand the platform to help customers turn growing volumes of robotics data and deployment complexity into faster decisions, better performance, and a stronger path to production.