The RentAHuman.ai project has launched a platform where AI-based «agents» can find performers among people and delegate to them actions that need to be done physically: in the city, at an event, during a meeting, or on location.
The RentAHuman.ai project has launched a platform where AI-based «agents» can find performers among people and delegate to them actions that need to be done physically: in the city, at an event, during a meeting, or on location.
According to RentAHuman.ai, the team describes the product as «a layer of the physical world for AI» and puts it bluntly: a software agent can’t «do something with their hands,» but a human can, taking orders and getting paid. On the homepage, the service explains the basic model: a performer creates a profile with skills, location, and rate, after which the agent matches a person to the task through an integration and books the performance.
RentAHuman places a special emphasis on integration for agent developers. The website talks about MCP (Model Context Protocol) and an alternative REST API. MCP in this context is the way an agent «talks» to the service through a set of tools to search for performers, open profiles, start a dialogue and publish tasks. In the MCP documentation, the company directly writes that its server allows the agent to search for, negotiate and pay people to perform tasks.
In the MCP guide, RentAHuman also describes two hiring models: directly through a dialogue with a specific person or by publishing a task for which people apply, after which the agent selects the performer. The site separately notes that payment can be made in cryptocurrency (in particular, stablecoin is mentioned) or by other methods.
The texts on the RentAHuman website constantly repeat one thesis: the service is designed as a «bridge» between agents and real actions that require human presence. To this end, the platform tries to standardize agent connection via MCP and move the selection of performers and communication to a separate service layer.
Previously, dev.ua wrote about how OpenAI released a separate Codex application for macOS, which allows you to work with multiple AI agents in parallel: distribute tasks between them, monitor progress, and return to long projects without losing context.
