Sponsor
SPONSORYour tool here. In front of builders picking their next AI tool.Your tool here.Grab a slot →
Job · Updated Oct 22, 2026

🔎 Research & search

Answers with citations, plus grounded chat over your own docs.

TL;DR: Perplexity for fast answers with sources you can click, NotebookLM when the answers have to come only from your own files. Full breakdown →
01

Perplexity

Answer engine with citations.

Fast sourced answers. Click through to verify.

BEST FOR: QUICK SOURCED ANSWERSFree plan · paid tiers

02

NotebookLM

Chat grounded in your own docs, plus audio overviews.

Only answers from what you upload. Great for studying a pile of PDFs.

BEST FOR: YOUR OWN SOURCESFree · paid tiers

New in research & search this week

Penmentor: An open-source mentor that checks your handwritten math and marks it up visually, like a teacher with a red pen, using the Claude, Codex, or Antigravity CLI you already have. The maker says it's currently tuned to his own Arch Linux and i3 setup. source ↗

Exa 3.0: Exa's search API for AI agents got its biggest upgrade: a larger embedding model, Dynamic Highlights now generally available (it uses 95% fewer tokens than full page text), and billions of new documents, including shopping listings, local businesses, flights, events, and live news, sports, and weather. There's a new Lite search type at $4 per 1,000 requests; Auto is $7. Exa says it ranks first on every benchmark it tested. source ↗

Yila: A research agent that searches scholarly databases, reads 50+ full papers, compares methods and how strong the evidence is, then drafts a citation-backed review you keep editing. It can also reformat a manuscript to a journal's or thesis office's template. source ↗

Llmspeed: A free, open-source site that shows how fast a local model would actually type on a given Mac or GPU, using community benchmarks where they exist and estimates where they don't. source ↗

Elorian Glimpse: A visual reasoning model from ex-DeepMind folks. It zooms into image regions and rewatches video frames to check its own work before answering. Available now by API. source ↗

Liquid AI d1-ultra: A multimodal model built to say "I don't know" instead of making things up. It now tops the Artificial Analysis Decision Index. source ↗

Rankings are editorial and can't be bought. Sponsored placements are always labeled. How we rank →