Consensus

active

Research engine showing whether scientific literature supports or contradicts claims. 200M+ papers (via Semantic Scholar), unique 'consensus meter.' Deep Search reads 1,000+ papers per query.

Score 38

Where it wins

Unique 'consensus meter' showing scientific agreement level — no competitor has this

200M+ papers via Semantic Scholar

Deep Search: reads 1,000+ papers per query

126 HN pts / 51 comments (2023)

Best for quick 'does the literature support X?' questions

Freemium pricing — accessible to students

Where to be skeptical

Deep Search HN launch: only 11 pts (Jul 2025) — concerning adoption signal

No API — cannot be integrated into programmatic workflows

HN signal is aging (2023)

Binary claim-level answers — less depth than Elicit for full systematic reviews

Editorial verdict

#2 in academic/scientific research subcategory. Unique consensus meter for claim-level evidence checking — no competitor has this. 200M+ papers via Semantic Scholar. Deep Search (1,000+ papers/query) launched but low HN signal (11 pts) raises adoption concerns.

Source

Found via SkillPack? ★ Star us on GitHub

Research

#10of 12

Quick claim-level evidence checking — 'does the literature support X?'

GPT Researcher

Open-source autonomous deep research agent. CMU DeepResearchGym #1 on citation quality, report quality, info coverage. 25.8K stars, 15.9K weekly PyPI downloads. Apache 2.0.

Tongyi DeepResearch

First fully open-source deep research agent matching closed-source leaders on benchmarks. HLE 32.9 (exceeds OpenAI's 26.6), 30.5B params / 3.3B active (MoE), runs locally. 18.5K stars. Apache 2.0.

STORM (Stanford)

Stanford's LLM-powered knowledge curation system. Generates Wikipedia-style articles with citations in ~3 min. 28K stars, 84.8% citation recall / 85.2% precision (peer-reviewed). MIT license.

Perplexity Deep Research

Research-first search engine with inline citations. Fastest deep research (15-30s), 93.9% SimpleQA accuracy, 50+ sources per report. $20/mo Pro.

Public evidence

strong2023-08-17

HN: 126 pts / 51 comments

Good signal, though aging (2023).

126 pts, 51 commentsHN community

moderate2025-07-10

Deep Search: reads 1,000+ papers per query — 11 HN pts

Feature launched but low engagement suggests limited buzz. Adoption unclear.

11 ptsHN community

moderateSelf-reported2026

Unique consensus meter — shows scientific agreement on claims

Differentiated feature. No competitor shows claim-level scientific agreement.

Product featureConsensus team

Raw GitHub source

GitHub README could not be fetched right now.