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)→
More from coding & agent
- "Markets for everything": why fully automated AI firms may run internal markets to price disagreements — morqon · 2026-09-28
- VibeDefend Launches a Security Guard for AI Coding Agents — Shruti_0810 · 2026-09-28
- What an agent must save so a failed run can be safely replayed and resumed — tomibrumen · 2026-09-28
- iLands' Agent Society Experiment Has a Strange Hole: No Buyer Role — Adorable-Community-9 · 2026-09-28
- Hermes Desktop is coming to the browser via a 182-commit PR to hermes-agent — Teknium · 2026-09-28
- DeepLearning.AI launches spec-driven development course to make vibe coding reliable — ZabihullahAtal · 2026-09-28