What Is an Agent Harness? The Scaffolding Around LLMs, Explained
According to a DeveDigest report, the term "Agent Harness" has become a buzzword in AI development after DeepSeek released an open-source desktop client called DeepSeek Harness and OpenAI launched an Agents API at its developer conference. The article explains that the model supplies only reasoning, while the harness is the surrounding system — execution loop, tool calling, context and memory management, sandbox permissions and replayable logs — that lets an agent actually finish real work. It cites testing by data analytics company Databricks finding that the same model plugged into different coding-agent harnesses can differ by more than 2x in per-task cost with no change in task quality, partly because a harness's system prompts and tool declarations consume tokens.
It separates the engineering layer around a model as a topic in its own right, framing context overhead, loop control and sandboxing as selection criteria on par with the model itself.