AI Research, Free of AI slop

Connect AI agents to top-tier computer science literature, research skills and best practices,
get grounded and trustworthy answers.

Install MCP

Add toClaude ChatGPT

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, findings, tutorial, short, abstract, or demo papers.

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

Turn your AI agent into a top-notch researcher.

Lune gives it the tools to search, read and cite top-tier papers, right inside the AI app you already use.

You already have

Your AI client

Claude Code
ChatGPT
Cursor
Antigravity
Perplexity
+37

Lune MCP

Research tools

Semantic search
Full-text reading
Citation tracing
Claim checking

It reads

Top-tier papers

CORE A* or CCF A conferences, most in full text

Best practices

Literature reviews, evaluation design, writing

Lune grounds your agent in trusted knowledge from top-tier academic papers, so there are no hallucinated facts or noise from the open web. It's free to start, never includes ads, works with the AI apps you already use, and keeps your privacy protected.

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

10 requests / day

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

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.

Turn your AI agent into a top-notch researcher.

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