AI academic paper summarizer

Yomu AI

Writing · Multi-model (GPT-4o/5, Claude Sonnet/Opus, Gemini Flash)

6.9

AI writing assistant built specifically for students and academic researchers.

Genei

RAG · GPT-3 (per public site)

6.8

AI research assistant that summarizes PDFs and web pages and answers questions across your document library.

Scite

RAG · Multi-model

8.2

AI research assistant that grades citations as supporting, contrasting, or mentioning across 1.6B citation statements.

Khoj

Agents · Multi-model

7.9

Open-source personal AI that builds agents, searches your documents, and automates research across local files and the web.

Emergent Mind

RAG · Undisclosed

7.2

AI-curated arXiv discovery layer that summarizes frontier papers and aggregates social discussion around them.

LLMEval

Evaluation · Multi-model

7.2

Open academic benchmark suite for stress-testing LLMs on contamination-resistant, domain-specific tasks.

Elicit

RAG · Claude Opus 4.5

7.1

AI research assistant that searches, screens, and extracts data from 138M+ academic papers at scale.

FutureHouse Platform

RAG · Multi-model

7.1

Multi-agent AI research stack for scientists, with retrieval over 175M+ papers, patents, and trials.

Jenni AI

Writing

7.1

AI writing workspace built specifically for academic papers, theses, and cited research.

QuillBot

Writing · Undisclosed (proprietary)

7.1

AI paraphrasing and grammar suite that grew into an all-in-one writing toolkit.

VisualWebArena

Evaluation · Model-agnostic (GPT-4V, Gemini, Claude, open VLMs)

7.1

Open benchmark for evaluating multimodal web agents on realistic visual browsing tasks.

alphaXiv

RAG · Multi-model

7.0

AI reading layer over arXiv with grounded Q&A, auto-summaries, and line-by-line discussion on every preprint.

SMMRY

Writing

7.0

Veteran web-based summarizer that condenses articles, books, and YouTube videos into digestible bullet points.

YouTube Summary with ChatGPT & Claude

Writing · Multi-model (ChatGPT, Claude, Gemini, Mistral)

7.0

Browser extension that pipes YouTube transcripts, articles, and PDFs into ChatGPT, Claude, Gemini, or Mistral for instant summaries.

Chat With PDF by Copilot.us

RAG

6.9

Conversational PDF Q&A bundled into a multi-app productivity membership.

SciSpace

RAG · Multi-model

6.9

AI research assistant that turns dense PDFs and literature reviews into searchable, citation-backed answers.

TubeSum

Agents

6.9

Chrome extension that turns long YouTube videos into AI-generated summaries with clickable timestamps.

YouTube Summary & ChatGPT by Glasp

Agents · Multi-model (GPT-3.5, GPT-4, Claude, Mistral, Gemini)

6.9

Chrome extension that surfaces YouTube transcripts and AI-generated video summaries alongside one-click access to ChatGPT.

ChatPDF

RAG · GPT-4o / GPT-4o-mini

6.8

Conversational Q&A over PDFs and other documents with citation-backed answers.

Explainpaper

RAG · Undisclosed (tiered basic vs. advanced)

6.8

AI reading companion that decodes dense academic papers by highlighting and chatting with the PDF.

Sourcely

Writing · GPT-4

6.8

AI source-finder that scans your draft and pulls citable academic papers to back each claim.

Spell

Writing

6.8

AI-native document editor that drafts and rewrites in natural language, pitched as a Google Docs alternative.

Brave Search MCP

MCP Servers

Give any MCP client web and local search powered by the Brave Search API.

Exa MCP Server

MCP Servers · Exa neural search index (in-house)

Web search, code search, and company research for AI assistants over MCP

Kagi MCP Server

MCP Servers

Official Kagi Search MCP server: search and extract the web from any MCP-compatible agent.

Ernie Bot

Agents · Baidu ERNIE 4.0 / ERNIE X1 / ERNIE Turbo (in-house)

8.7

Baidu's Mandarin-first ChatGPT rival, powered by the ERNIE model family

LiveBench

Evaluation · Multi-model

8.2

Contamination-free LLM benchmark that refreshes its questions monthly to keep frontier models honest.

CAMEL-AI

Agents · Multi-model

8.0

Open-source Python framework for building multi-agent systems and synthetic data pipelines.

Reflect

Writing · OpenAI GPT-4 + Whisper

8.0

Networked note-taking app with GPT-4 and Whisper baked into the writing surface.

Sesame

Audio · Sesame CSM (1B / 3B / 8B)

8.0

Conversational voice AI aiming to cross the uncanny valley with context-aware, emotionally aware speech.

STORM

Writing · Multi-model (via LiteLLM)

7.5

Stanford's open-source research agent that turns a topic into a Wikipedia-style article with citations.

MathEval

Evaluation · GPT-4 grader / DeepSeek-LLM-7B verifier

7.3

Holistic benchmark suite for evaluating mathematical reasoning in large language models.

Rayyan

RAG

7.3

AI-assisted systematic review platform for screening, deduplicating, and extracting data from large literature corpora.

OneKE

RAG · Multi-model (OneKE-13B, LLaMA3, Qwen2.5, GPT, DeepSeek-R1)

7.2

Open-source multi-agent framework for schema-guided knowledge extraction from documents.

Runcell

Coding · Multi-model (GPT, Claude, Gemini)

7.1

Jupyter-native AI agent built for multi-week ML and data science projects.

SEAL Leaderboard

Evaluation · Multi-model (GPT, Claude, Gemini, Llama, etc.)

7.1

Private, expert-graded leaderboards from Scale AI that rank frontier LLMs on domains contaminated public benchmarks can no longer measure.

YouTube Summary with ChatGPT & Claude

Agents · Multi-model (ChatGPT, Claude, Gemini, Mistral)

7.1

Browser extension that pipes YouTube transcripts, articles, and PDFs into ChatGPT, Claude, Gemini, or Mistral for instant summaries.

Graphify

RAG · Multi-model

7.0

Open-source on-device knowledge graph engine that turns code, docs, papers, meetings and images into a queryable graph.

LMQL

Coding · Multi-model (OpenAI, Hugging Face Transformers, llama.cpp)

7.0

A query language for LLMs that bolts types, templates, and constraints onto prompting.

OlympicArena

Evaluation · GPT-4o, Claude-3.5-Sonnet, Doubao-Pro-32k, DeepSeek-Coder-V2, Qwen2-72B-Instruct

7.0

Olympiad-level multi-discipline benchmark for stress-testing reasoning in LLMs and multimodal models.

CocoIndex

RAG · Bring-your-own (embeddings + LLM)

6.9

Open-source incremental data framework that keeps RAG indexes and agent context continuously fresh.

Folo

Agents · DeepSeek

6.9

Open-source AI RSS reader that summarizes feeds and cuts noise from 1M+ sources.

Merlin AI

Writing · Multi-model (GPT-4o, Claude 3.7, Gemini 2.5, Llama 3.1, Mistral, Deepseek)

6.9

Browser-based multi-model AI assistant that puts GPT-4, Claude, and Gemini one keystroke away on any webpage.

ShyEditor

Writing · Multi-model (GPT-4, Grok)

6.9

AI-native writing environment that bolts an assistant, citation manager, and knowledge base onto a distraction-free markdown editor.

TPOT

Coding · Genetic programming over scikit-learn

6.9

Open-source AutoML library that evolves scikit-learn pipelines with genetic programming.

IntelliBar

Writing · Multi-model (GPT-4o, Claude 3.5, Gemini, o1, Llama, DeepSeek, Ollama)

6.8

Native macOS menu-bar client that talks to every major LLM with your own API keys.

Nexus AI

Writing · Multi-model

6.8

All-in-one AI workspace bundling writing, image, voice, and chat into a single subscription.

Recall

RAG · Multi-model (GPT, Claude, Gemini)

6.8

AI-powered personal knowledge base that summarizes, links, and quizzes you on everything you save.