Open-source Hyperresearch turns Claude Code into a deep research agent with a compounding local knowledge vault

JafarNajafov · x · 2026-09-28

Developer JafarNajafov introduces Hyperresearch, a free open-source tool that turns Claude Code into a deep research agent claimed to outperform ChatGPT Deep Research.

It tackles the core flaw of deep research tools: reports are generated once and every source read is thrown away, so each question starts from zero. Hyperresearch instead keeps everything — every source lands in a searchable local vault of plain Markdown files, checked before hitting the web, so research compounds across sessions.

One prompt triggers a full pipeline: break the question into pieces, read 250+ sources in a single run, write 3 drafts in parallel, have 4 AI critics attack the report for weak spots, and let a locked patcher fix only what the critics found — it cannot rewrite the whole report. Citations are preserved throughout.

Related event: Hyperresearch Turns Claude Code into a Deep Research Agent(2 posts)→

Original post →

More from coding & agent

coding & agent channel →