# continualcode

> Continual learning coding agent harness

Published: 2026/02/10 • Author: Surya Dantuluri • Canonical: https://sdan.net/projects/continualcode

*Still in progress — actively iterating on the harness and the eval. If that's interesting to you, reach out: [@sdand](https://x.com/sdand) or surya@llmh.com.*

Inspired by SDPO — a minimal Claude Code that learns from your corrections in real-time, built on Tinker. The agent improves continuously as you use it, turning each correction into training signal.

Benchmarked on LiveCodeBench with Qwen3-4B and Qwen3-30B. Both show an early jump in pass@1 then plateau — the interesting question is how far continual learning can push coding agents. `pip install continualcode`.