Hyperresearch uses Claude Code locally to draft 80,000-word dissertations from 250+ sources
Shruti_0810 · x · 2026-07-23
Hyperresearch turns one prompt into a dissertation workflow
- A new open-source project called Hyperresearch runs locally with Claude Code instead of a cloud app or wrapper.
- It can pull 250+ sources in parallel, generate multiple independent drafts, use AI critics to challenge its own conclusions, and verify every citation against the original source.
- It also deduplicates overlapping news coverage and builds a local research vault that improves over time.
- The project advertises a Dissertation Mode that takes 4–8 hours and can produce 300–450 sources, 25,000–80,000 words, and up to 10 chapters.
The pitch is simple: most tools are built to impress investors, while this one is designed to survive fact-checking.
Related event: Hyperresearch: Open-Source Agent for Local Paper Generation(2 posts)→
More from coding & agent
- SymbolPeek lets coding agents read symbols instead of whole files, saving 1.61M tokens — Real_Veterinarian851 · 2026-07-23
- AgenC defaults to one agent after papers found multi-agent swarms underperformed — tetsuoai · 2026-07-23
- AgenC now defaults to one agent after multi-agent systems fell 39%–70% behind — tetsuoai · 2026-07-23
- An AI coding agent broke a database schema with six migrations and 400 lines of ALTERs — Comfortable-Roof4278 · 2026-07-23
- Five frontier models all solved the same bugs, but cost varied 14x and Claude refused 40% — PromptPhanter · 2026-07-23
- LLMs may help most in the manual refinement phase of decompilation — OwariDa · 2026-07-23