hyperresearch

Name: hyperresearch
Author: jordan-gibbs

byjordan-gibbs· 1 MCP server

Stars

1.4k

Forks

151

How to install hyperresearch?

jordan-gibbs/hyperresearch

$git clone https://github.com/jordan-gibbs/hyperresearch

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install hyperresearch by running `git clone https://github.com/jordan-gibbs/hyperresearch`, then use it for the current task and follow its documentation at https://github.com/jordan-gibbs/hyperresearch.

Files · 1

View on GitHub

README.md

1	<p align="center">
2	<img src="assets/banner.png" alt="HYPERRESEARCH" width="700">
3	</p>
4
5	<h3 align="center">The Most Powerful Deep Research Harness</h3>
6
7	<p align="center">
8	<a href="https://pypi.org/project/hyperresearch/"><img src="https://img.shields.io/pypi/v/hyperresearch" alt="PyPI version"></a>
9	<a href="https://pypi.org/project/hyperresearch/"><img src="https://img.shields.io/pypi/pyversions/hyperresearch" alt="Python 3.11+"></a>
10	<a href="LICENSE"><img src="https://img.shields.io/github/license/jordan-gibbs/hyperresearch" alt="License: MIT"></a>
11	<a href="https://github.com/jordan-gibbs/hyperresearch"><img src="https://img.shields.io/github/stars/jordan-gibbs/hyperresearch?style=social" alt="GitHub stars"></a>
12	</p>
13
14	---
15
16	Hyperresearch turns Claude Code into a deep research agent: one that currently leads the DeepResearch-Bench RACE leaderboard (benchmarked internally). 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.
17
18	<p align="center">
19	<img src="assets/benchmark.png" alt="DeepResearch-Bench top-5 hyperresearch leads the chart ahead of Grep Deep Research, Cellcog Max, nvidia-aiq, Gemini Deep Research, and OpenAI Deep Research" width="780">
20	</p>
21
22	<p align="center"><sub>Forward-looking projection from a stratified pilot against the DeepResearch-Bench leaderboard snapshot (https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard). Third party validation is pending.</sub></p>
23
24	## Why it wins
25
26	- 250+ sources in a single run. The `premier` scale profile targets 100–130 in the width sweep alone; citation chasing and gap-fill fetches more than double what actually lands in the corpus.
27	- Every citation is verified before the report ships. A skeptical cite-checker audits whether each cited source actually supports its sentence. Hallucinated quotes and unacknowledged retractions are hard blocks at the gate.
28	- Syndication doesn't count as consensus. An independence audit clusters derivative copies, so five reprints of one press release argue with the weight of one source.
29	- Adversarial by construction. Four critics attack every draft in parallel, and a tool-locked patcher can only apply surgical edits. It physically cannot rewrite the report.
30	- Nothing is thrown away. Every source lands in a searchable markdown-plus-SQLite vault that your next session reuses before it fetches anything new.
31	- Crashed runs resume. Each run keeps a manifest; `run resume` picks up at the exact step where it died.
32	- Scales from 30 minutes to a dissertation. Bounded queries auto-route to a 5-step fast path. Opt-in dissertation runs write 25K–80K words across chapters, from 300–450 sources.
33
34	## Install
35
36	```bash
37	cd your-project
38	pip install hyperresearch && hyperresearch install
39	```
40
41	Then `/hyperresearch <anything>` in Claude Code.
42
43	> Python 3.11–3.13. (3.14 not yet supported. Use `pyenv install 3.13`, `uv venv -p 3.13`, or `py -3.13 -m venv .venv`.)
44	>
45	> Power users: `hyperresearch install --global` makes `/hyperresearch` reachable from every Claude Code session anywhere, at the cost of ~15 lines in every session's system reminder. Per-project install (above) keeps unrelated CC sessions clean.
46
47	---
48
49	## The 16-step research pipeline
50
51	The entry skill is a thin router. It pins down the canonical research query, then invokes one step skill per phase via Claude Code's `Skill` tool. Each step's procedure loads into context only when that step actually runs. That's what stops a long pipeline from quietly dropping steps as its context rots.
52
53	\| # \| Step \| What it does \| Tiers \|
54	\|---\|---\|---\|---\|
55	\| 1 \| Decompose \| Canonical query → atomic items + coverage matrix + tier classification \| all \|
56	\| 1.5 \| Chapter partition \| Group atomic items into 4–10 chapters; steps 2–10 then loop per chapter \| dissertation \|
57	\| 2 \| Width sweep \| Multi-pe

6 picks

Type

Install hyperresearch by running `git clone https://github.com/jordan-gibbs/hyperresearch`, then use it for the current task and follow its documentation at https://github.com/jordan-gibbs/hyperresearch.

hyperresearch

How to install hyperresearch?

Related

hyperresearch

How to install hyperresearch?

Related