Glossary
What is an
agent harness?
An agent harness is the execution layer around the model. It provides the files, terminals, browser, tools, permissions, and runtime rules that turn a reasoning model into a working agent system.
Why it matters
The model decides what to do. The harness determines what it can actually do. That includes which tools exist, which files are visible, what permissions are granted, and which actions are allowed in the environment.
AnyCap fits inside that harness as a capability runtime. It gives the harness a clean way to expose multimodal actions to the agent through one interface.