Voxel51 Agent
Voxel51 Agent helps you automate repetitive data work—from investigation to curation, annotation, and evaluation.
Agentic workflows
Move from insight to action
Talk to your data
Surface the failures, edge cases, and data gaps that matter across massive datasets. Voxel51 Agent helps you get from a question to the relevant data faster.

Automate repetitive data work
Reduce the manual work behind recurring curation, annotation, and evaluation workflows. Voxel51 Agent handles the repetitive steps while engineers stay in control of the decisions.

Developer resources
Extend Voxel51 Agent for any workflow
Adapt Voxel51 Agent to your stack with plugins, integrations, the SDK, and custom operators—so you’re not limited to built-in capabilities.
Build custom plugins
Add custom logic, operations, and workflows that you can easily share with your team.

Encode how your team works with skills
Turn your team’s best workflows into repeatable processes.
Integrate any model
Powered by MCP, connect to 100+ providers or your own self-hosted model.

Use cases
See what you can do you Voxel51 Agent
Search your dataset with natural language.
Catch label issues with automated quality checks.
Use natural language to automate repetitive data work.
Quickly surface underperforming classes and failure patterns.
Extend Voxel51 Agent with custom capabilities.
Developer resources
Learn how to build custom applications
How to build vision data agents with tools, skills, and MCP
Questions?
We have answers.
Voxel51 Agent is an AI-powered assistant for Voxel51 that can use Voxel51's data, model evaluation, annotation, and extensibility capabilities from natural language instructions. It can investigate datasets and model behavior, carry out Voxel51 operations, and continue into actions like curation, evaluation, annotation, and custom analysis.
A chatbot primarily answers questions. Voxel51 Agent can take action on your Voxel51 environment using tools: querying and curating datasets, creating views, using embeddings, running evaluations, working with annotation, and executing specialized workflows through skills and plugins.
Voxel51 Skills are a set of instructions that teach an agent how to carry out a particular workflow using available tools. Skills are useful for encoding repeatable team processes: not simply what operations exist, but how your team expects them to be used.
A plugin extends what the Voxel51 Agent can do. A skill teaches the Agent how to combine available capabilities to accomplish a task. A plugin can introduce a new operation, while a skill can define how and when the Agent should use it.
No. Pipeline orchestrators execute predefined jobs and dependencies. Voxel51 Agent addresses a different part of the ML lifecycle: the iterative data and model development work where the next action often depends on what you discover. The two can work alongside each other.
The Voxel51 MCP Server exposes Voxel51's capabilities to compatible AI assistants and developer tools, so you can bring Voxel51 into the AI environment you already use rather than being limited to a single agent interface.
FiftyOne supports the Model Context Protocol (MCP). Install the FiftyOne MCP Server, point your coding assistant (Claude Code, Cursor, Copilot, etc.) to it, and your assistant can start executing FiftyOne operations directly. No custom integration code required. https://github.com/voxel51/fiftyone-mcp-server