Detections
Infrastructure for Physical AI
Build and orchestrate computer vision with agents
Connect data, models, human input and compute in one executable graph. Build from ready nodes, or describe your workflow to an AI agent.
Import from Cloud Storage
Predict YOLO
Filter Low Confidence
Labeling
118labeled
In progress17%Awaiting review13%Accepted61%Rejected10%
Check for Drift
Notify Team
Built by the team behind Supervisely used by
One platform across the computer vision stack
Curate datasets, organize human labeling, train models, understand where they fail, compare alternatives and put the result into production.
Data Curation
Understand your data
Profile dataset quality, catch outliers and label errors, explore embeddings, and version every result.
Explore data curation
AI-Powered Labeling
Annotate at scale
Label images, video and 3D point clouds with smart tools, custom review workflows and quality gates.
Explore labelingMore than 125 computer vision nodes
From foundational data operations to specialized filters and model workflows, the same nodes recombine into hundreds of project-specific pipelines.
Browse templates built from these nodesModel Training
Train without losing the thread
Fine-tune on versioned datasets and trace every checkpoint back to the data, parameters and run that produced it.
Explore model training
Evaluation & Deployment
See which model wins, and why
Benchmark models on the same data, compare metrics side by side, and deploy the winner as an API endpoint.
Explore model evaluation
See the whole workflow, not just the final model
Real projects are loops, branches, retries, experiments, human decisions and competing models — not a simple linear pipeline. A shared graph keeps the logic visible and executable.
Orchestrate scattered tools into one executable system
Keep every run
Each run keeps its inputs, outputs, logs and artifacts.
Reuse complex logic
Break large flows into subgraphs the team can operate and improve.
Keep your existing stack
Connect existing tools, models, storage, and compute instead of replacing them.
Share one map of the work
Give engineers, operators, and stakeholders the same view of how work runs.
Bring experts into the flow
Let specialists inspect, run, and adjust workflows directly.
Loop where work loops
Label, train and review cycles are normal parts of a flow.
Build computer vision workflows that don’t fall apart after the demo
Turn recurring computer vision work into an operational process that survives new inputs and data drift. Automate the predictable steps, track every experiment and result, and bring people in only where judgment adds value.
Run updated models on new assetsIngest and trigger automaticallyDetect drift and flag uncertain resultsApply feedback from humans
Connected storageNew assets
OvalBee
workflow
workflow
Selective review Humans only when needed
Retrain &
improve
improve
- Ingest and trigger automatically
- Detect drift and flag uncertain results
- Apply feedback from humans
- Run updated models on new assets
Ready to use. Open to change.
Begin with a proven template or a request in AI Chat, reshape the workflow by hand or with the agent as project reality changes, and plug in the tools you already use.
Start from proven workflows
Pick a ready template for dataset preparation, labeling, training, or evaluation, or describe the task and let the agent assemble the first draft.
detection.graph132 nodes
defect-review.graph84 nodes
active-learning.graph118 nodes
Adapt the graph to reality
Rewire steps, swap nodes, and tune inputs yourself, or ask the agent to make the change as requirements and edge cases emerge.
Import dataSource
Prepare datasetTransform
Custom filterProject logic
Export resultsDestination
Bring your own code and tools
Connect your storage, models, and internal services through the API and SDK, so workflows run on the stack you already have.
def run_node(input):
frames = input.images
result = model(frames)
return resultPython
API
SDK
Docker
Operate every workflow as a team
Keep workflows observable, controlled, and connected as they move from an engineer’s first run into everyday operation across your organization.
Deploy on your terms
Use our cloud, a dedicated instance, or your own infrastructure without changing how the team builds and operates workflows.
OvalBee Cloud
Dedicated VPC
On-premises
AWS
Azure
Google Cloud
Roles and permissions
Control who can design, run, review, or administer workflows while keeping members, secrets, storage, and infrastructure settings organized by workspace.
MemberAccessScope
MCMaya ChenAdminAll projects
TRTom ReyesEditorWorkflows
DODavid OkaforReviewerReview queues
SLSara LindholmViewerReports
Monitor every run
See what is running, waiting, completed, or failed, then inspect progress, duration, logs, outputs, and errors in one place.
run · detector-v7running
Ingest frames12.4k
Sample + deduplicate3.1k
Pseudo-label3.0k
Train detector62%
Evaluate modelqueued
Trace every result back
Follow a model, report, or export through the runs, dataset versions, annotations, parameters, and artifacts that produced it.
Dataset · v10draft · uncommitted
Dataset · v914,205 samples
Dataset · v813,002 samples
Dataset · v712,480 samples · production model
SelectedDataset · v611,860 samples
Dataset · v5night scenes added
Dataset · v49,950 samples
Connect your existing stack
Bring in storage, labeling systems, proprietary models, webhooks, and internal services without rebuilding the surrounding stack.
For large teams
Enterprise-grade by design
OvalBee gives computer vision teams the controls, deployment options, and hands-on support they need to run annotation workflows at scale.
Access control & security
Connect any SAML or OIDC provider, use roles, audit logs and encrypted secrets.
On-premise or cloud-hosted
Run on our managed cloud, or self-host to meet any compliance requirements.
Integration with cloud storages
Connect existing data on AWS S3, Google Cloud or Azure without re-uploading.
Hands-on enterprise support
Dedicated channels
Slack or Teams access for fast support, rollout questions, and hands-on onboarding.
Computer vision experts
Personalized training with experts who help build flows for your use case.
Full customization
Custom invoicing, contracts, SLAs, and deep feature customization.
FAQ
Common questions
What is OvalBee?
OvalBee is a visual platform for building and operating complete computer vision workflows. Data preparation, labeling, training, evaluation, deployment, human review, and automation live in one executable graph. The graph is not documentation for work happening elsewhere: its nodes run real jobs and keep their inputs, outputs, logs, and artifacts.
What can I build with OvalBee?
Build repeatable processes for dataset curation, labeling and review, model training, evaluation, deployment, monitoring, and continuous improvement. Start from a template, combine ready-made nodes, or model a project-specific loop with schedules, branches, human decisions, and external services.
How does OvalBee fit alongside Roboflow, Supervisely, or our existing tools?
OvalBee does not require a rip-and-replace migration. It provides an executable graph for connecting data, labeling, models, evaluation, compute, and human review across the whole project. Keep specialized platforms and internal services where they already work, then connect them through ready nodes, storage integrations, APIs, or custom steps.
Where can OvalBee and its jobs run?
Use OvalBee Cloud as a managed service, or run OvalBee in your own cloud account, VPC, data center, or Kubernetes environment. Jobs can use managed compute, your own GPUs, or infrastructure close to the data. During the private beta, we help teams choose and configure the right deployment.
Can I start for free?
Yes. OvalBee Cloud has a Free plan with no credit card required. Access is still invite-only during the private beta, so request an invite and tell us what you want to build. A free self-hosted Community edition is also planned but is not yet available for download.
How far can I customize a workflow?
Start visually with templates and ready nodes, then change parameters, branches, schedules, and review steps. When the project needs something specific, connect internal services and proprietary models through the API and Python SDK or add custom code and integrations. During the private beta, we build and validate custom nodes together with your team.
Can I connect my own AI agent?
Yes. Use AI Chat inside OvalBee, or connect an MCP client such as Claude Code or Codex to the OvalBee MCP server. Your agent can search the node library, build and change flows, inspect failures, and request node runs using the permissions of your workspace. Actions that execute or revert work still require approval.
Will OvalBee lock in my data or models?
OvalBee is designed to work with the stack you already have. Connect S3-compatible storage, Azure storage, filesystems, external labeling systems, and your own compute instead of moving everything into one proprietary environment. Import and export data, models, reports, and flow definitions, and self-host when infrastructure or data must remain under your control.
Do I need to write code?
No. Build on the visual canvas from ready-made nodes, start from a template, or describe the workflow to the AI agent. Engineers can use code where it adds value, while annotators, reviewers, domain experts, and operators work with the same flow without maintaining scripts.
Get OvalBee now
Join the leaders of tomorrow to future proof your documentation today
Start in Cloud
Signup for a free account in 5 minutes, no credit card
Coming soonDownload from GitHub
Self-hosted free and source-available version
Coming soon