Agent framework · Pro

How do the others do it?

Six real harnesses, eleven layers, and at every crossing a finding with source code from a pinned commit. Three ways in: through a challenge, through a topic, or through the portrait of one harness.

Preview

From Pro: the matrix per challenge, all eleven topics with citations, and the architecture portrait of every harness. Freely visible are the six short portraits:

  • OpenClaw - The multi-channel personal agent - a half-million-line estate of gateway, channels and tooling whose loop core shares its lineage with Pi.
  • Hermes - Nous Research's Python harness - deterministic loop, a skill system, and an error path that escalates in stages instead of just giving up.
  • Pi - The coding agent with a deliberately small core - every layer hand-built and kept readable, from the provider package to the session file.
  • HybridClaw - The enterprise runtime - sandboxed execution, approvals, and credentials that travel through context as references instead of plain text.
  • DeepSeek Harness - The plugin radical - “everything is a plugin” is meant literally here: providers, tools and the loop itself are modules on the Cordis core.
  • NanoClaw - The minimalist - small enough to understand in full: the model layer moves behind the Claude Agent SDK, isolation into a container.

Sign in to see this content

This section is reserved for members. Log in to keep reading.

Sign in