Hyperresearch Adds OpenAI Codex Integration
Hyperresearch, a deep-research skill for Claude Code and OpenAI Codex, has added a Codex integration that installs the full pipeline, including the entry skill, step procedures, subagents as custom agents, and a Stop hook. The project says its tier-adaptive 16-step pipeline produces adversarially audited reports with source provenance and stores sources in a persistent, searchable vault. Its README claims a first-place DRACO benchmark result for the Claude Code pipeline. The new Codex port has not yet been benchmarked, and the project says its lint checks structural issues but cannot guarantee factual accuracy.
The integration makes the same research workflow available in Claude Code and OpenAI Codex. Its source-provenance checks, citation auditing, and persistent searchable vault are designed to support repeatable and auditable research, although the project notes that automated checks cannot guarantee factual accuracy.
Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai

The Most Powerful Deep Research Harness: a deep research skill for Claude Code and OpenAI Codex
Hyperresearch turns Claude Code into a deep research agent, and it's #1 on the DRACO deep research benchmark, ahead of Claude Research, ChatGPT, Gemini and Perplexity. It runs in OpenAI Codex too. A tier-adaptive 16-step pipeline takes one prompt and produces an adversarially-audited report with full source provenance. Every source it reads lands in a persistent, searchable vault, so each session starts smarter than the last.