Coding Agents Evals Benchmarks Harness Engineering

DeepSeek Harness

Everything is a plugin

Open-source, locally runnable agent harness and coding-agent development/runtime environment built around swappable plugins for models, tools, sessions, sandboxes, storage, loops, scheduling, and UI.

Recent stories

1 linked story

newsSECONDARY2026-08-23

Practitioners propose a standard harness for agent benchmarks

Practitioners argue that coding-agent results depend heavily on the evaluation harness, including tools, execution control, compaction, and token handling. They propose stable common harnesses rather than vendor-specific setups.