Used by students and researchers from

What it is

Trusted knowledge from A / A* conference papers for your AI agent.

No open-web noise. No workshop papers, findings, tutorials, short papers, abstracts, or demos.

Full-text semantic search

Search across the papers in plain language, all at once.

Citation tracing

See what a paper builds on and what it leads to.

Research best practices

Battle-tested research guidance, surfaced whenever it is relevant.

Knowledge cutoff

Richard Hamming
Bell Labs
Andrej Karpathy
Anthropic
Bill Freeman
MIT
Nicholas Carlini
Anthropic
John Schulman
OpenAI
Jacob Steinhardt
UC Berkeley
Michael Nielsen
Astera Institute
Christopher Olah
Anthropic

Tap into the minds of the great

Search across the talks, interviews and notes of the people who shaped the fields.

What you get

Highest quality answers at every step of your research workflow.

From the first literature search to the final draft, every step rests on evidence, never guesswork.

Find what matters, locate research gaps

ClaudeLune MCP

You

I'm new to retrieval-augmented generation. What are the foundational papers, and what exactly do they claim?

Your agent

ClaudecalledLunesearch_papers ·get_paper_fulltext [1]

RAG [1], REALM [2] and Fusion-in-Decoder [3] anchor the area; Self-RAG [4] lets the model decide when to retrieve. Here is RAG's setup, in its own words:

full text · Lewis et al., NeurIPS 2020

We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever.

Evidence

ClaudeLune MCP

You

Idea: have a RAG model abstain or re-retrieve when its retrieved context looks weak. Is this novel, and where's the real gap?

Your agent

ClaudecalledLunesearch_papers ·search_research_guidance "novelty"

Self-RAG [1] already trains a model to decide when to retrieve, so that alone won't read as novel. The open gap: it is brittle under domain shift, and almost nobody evaluates it cost-aware.

Evidence

Asai et al.ICLR 2024
Novelty barBest-practices library

ClaudeLune MCP

You

Design the evaluation for my retrieval method. What baselines and ablations will reviewers expect?

Your agent

ClaudecalledLunesearch_research_guidance "baselines, ablations" ·search_papers

Reviewers will expect BM25, a dense retriever like DPR [1], and a no-retrieval control, measured on Natural Questions [2]. Dropping that control is the most common desk-reject here.

Evidence

Karpukhin et al.EMNLP 2020
Kwiatkowski et al.TACL 2019
Review patternsBest-practices library

ClaudeLune MCP

You

Draft the related-work sentence positioning my method against prior RAG work.

Your agent

ClaudecalledLuneget_paper_fulltext [1], [2]

Drafted, with every citation checked against the source it names:

Unlike REALM [1], which trains a latent retriever against a masked language modeling objective, and Fusion-in-Decoder [2], which encodes passages independently and fuses them in the decoder, our method reranks before generation to keep the reader's context budget small.

Evidence

ClaudeLune MCP

You

I'm new to retrieval-augmented generation. What are the foundational papers, and what exactly do they claim?

Your agent

ClaudecalledLunesearch_papers ·get_paper_fulltext [1]

RAG [1], REALM [2] and Fusion-in-Decoder [3] anchor the area; Self-RAG [4] lets the model decide when to retrieve. Here is RAG's setup, in its own words:

full text · Lewis et al., NeurIPS 2020

We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever.

Evidence

How it works

Install Lune to Claude/ChatGPT and the like via connector plugin.

Lune grounds your agent in trusted knowledge from top-tier academic papers, so there are no hallucinated facts or noise from the open web.

Your AI app

Lune connector

Top-tier papers

Talent Database

Top-tier CS talent profiles built from top-tier track records.

A database of talent profiles with complete publication track records and contact information. Semantic search finds people by name, school, research area and more.

Semantic search by research area
Describe the expertise in your own words, and see who has published on it.
Track records you can check
Each profile lists the researcher's papers, top venues and years active.
Email for cold outreach
Every profile comes with an email address, so you can reach out directly.

EMNLP ×10
Danqi Chen
Princeton University
LLM training · Retrieval
d***@cs.princeton.edu
NeurIPS ×23
Mingsheng Long
Tsinghua University
World models · AI for science
m***@tsinghua.edu.cn
ICCV ×9
Mohamed Elhoseiny
KAUST
Multimodal LLMs · Audio-visual reasoning
m***@kaust.edu.sa
CVPR ×15
Andrea Vedaldi
University of Oxford
4D reconstruction · 3D generation
v***@robots.ox.ac.uk
ACL ×4
Preethi Jyothi
IIT Bombay
Speech recognition · Multilingual NLP
p***@cse.iitb.ac.in
CVPR ×4
Alvaro Soto
Pontificia Universidad Católica de Chile
Continual learning · Visual reasoning
a***@ing.puc.cl
EMNLP ×10
Danqi Chen
Princeton University
LLM training · Retrieval
d***@cs.princeton.edu
NeurIPS ×23
Mingsheng Long
Tsinghua University
World models · AI for science
m***@tsinghua.edu.cn
ICCV ×9
Mohamed Elhoseiny
KAUST
Multimodal LLMs · Audio-visual reasoning
m***@kaust.edu.sa
CVPR ×15
Andrea Vedaldi
University of Oxford
4D reconstruction · 3D generation
v***@robots.ox.ac.uk
ACL ×4
Preethi Jyothi
IIT Bombay
Speech recognition · Multilingual NLP
p***@cse.iitb.ac.in
CVPR ×4
Alvaro Soto
Pontificia Universidad Católica de Chile
Continual learning · Visual reasoning
a***@ing.puc.cl

How to use

No apps to download.

Install Lune as a plugin or connector to your AI app.

MCP

Install the plugin or connect via a custom connector.

https://mcp.luneresearch.com

Access Lune's core features

CLI

Use Lune without leaving the terminal.

npm install -g @retrograde-labs/lune-cli

Install & use Lune from the command line

Cloud Agents

Custom-designed agents, with Lune MCP built in.

Assist Critique Workspace

Use Lune on the web

Pricing

We have a plan for every kind of researcher.

Pick a plan with a standard daily allowance. If you go past it, just top up extra usage credits.

Free

$0

10 requests / day

All of Lune, no feature gates
One personal account
Sign in with Google or email
Top up with credits any time

Sign up free

Pro

Popular

$4.99

/ month · 300 requests / day

Everything in Free
300 queries or email reveals a day
Share plan and credits with your team
Connect any AI client you use

Try Pro

Max

$9.99

/ month · 600 requests / day

Everything in Pro
600 queries or email reveals a day, twice Pro's
Share plan and credits with your team
Priority email support

Try Max

Busy day? Top up with credits at $0.99 for 300 extra requests. Credits never expire, and they work on every plan.

Trustworthy AI for Scientific Research

Free to start. No credit card required.

Try Lune

AI Research,AI Research,AI Research,Academic Writing,Literature Review,Experimental Design,Peer Review, Free of AI slop

Trusted knowledge from A / A* conference papers for your AI agent.

Full-text semantic search

Citation tracing

Research best practices

Highest quality answers at every step of your research workflow.

Install Lune to Claude/ChatGPT and the like via connector plugin.

Top-tier CS talent profiles built from top-tier track records.

Semantic search by research area

Track records you can check

Email for cold outreach

No apps to download.

MCP

CLI

Cloud Agents

We have a plan for every kind of researcher.

Free

Pro

Max

Trustworthy AI for Scientific Research

AI Research, Free of AI slop