About AdaptOrch

AdaptOrch records what an AI coding agent ran, which checks were available and what still needs human review. You connect Claude Code, Codex CLI or Cursor through the hosted MCP server, the CLI or the Python SDK, and use your own model provider key.

The hosted change-explanation template reviews the text you supply and returns a summary, missing information and review questions. It does not inspect code or verify correctness. The claim boundary lists what we do and don't claim.

The research behind AdaptOrch is the paper AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence by Geunbin Yu (arXiv 2602.16873, submitted 2026-02-18). The paper describes task-adaptive multi-agent orchestration. Its research results are separate from the hosted product and are not a claim about how the product performs on your code.

ClassicMate (클래식메이트) · Representative: 최인호 · Business registration number 805-36-01586

51 Uncheon-ro, 707-ho (Wondong), Osan-si, Gyeonggi-do, Republic of Korea

Contact: ingeng2004@gmail.com · Trust Center · Security

• Connection documentation
• Pricing
• Public MCP client repository (GitHub)
• adaptorch on PyPI · adaptorch-mcp · adaptorch-client
• Paper on arXiv