Skip to main content
When your agent is code — a framework implementation rather than harness markdown — Helix applies approved fixes by editing that code and opening a pull request on GitHub, the same as for harness agents.

Mastra

Agents built on the Mastra framework.

Claude Agent SDK

Agents built on the Claude Agent SDK.

DeepAgents

Agents built with DeepAgents.

Pydantic AI

Agents built with Pydantic AI.

​
How a fix lands

The flow mirrors harness targets: Diagnose ranks a remedy, you approve it, Helix prepares the code change on a branch, and it opens a GitHub pull request for you to review and merge. Code changes go through the same approval gate — nothing merges without you. Declare a code target in your config:
.mutagent/config.yaml
The loop is the same whether your agent is markdown or code — Evaluate scores it, Diagnose root-causes it, and Optimize applies the approved fix as a PR. Only the target differs.