Loading…
Research · SciSpace
AI research assistant: search, read, and review the literature.
AI workspace for academics that searches a corpus of 280M+ papers, runs literature reviews, and answers questions over PDFs with citations. Adds writing aids like a paraphraser and citation generator. Formerly Typeset.io; introduced agentic 'Deep Review' literature search in 2025. Free Basic tier with paid upgrades.
Model support
Uses frontier LLMs over its paper corpus; exact models not disclosed.
Where it runs
Tags
Related in Research
Consensus
AI search over 200M+ peer-reviewed papers, with citations.
An academic search engine that runs natural-language questions against a corpus of more than 200 million peer-reviewed papers and synthesizes the findings with inline citations. Its Consensus Meter aggregates how much the studies agree or disagree, and a copilot helps draft literature reviews. Aimed at researchers, students, and clinicians.
AI insight: Its 'Consensus Meter' summarizes whether a body of papers agrees or disagrees on a question, going beyond surfacing individual citations.
Elicit (formerly Ought)
AI research assistant for literature review and evidence synthesis.
Searches, summarizes, and extracts structured data across 125M+ academic papers, with sentence-level citations. Goes beyond chat-over-papers with a guided systematic-review workflow covering search, screening, extraction, and report synthesis. A free Basic plan offers unlimited search and summaries; paid tiers add data-extraction volume and the review pipeline.
AI insight: One of the few research tools with a real systematic-review screening pipeline, benchmarked against Cochrane reviews.
Prototype with Gemini — prompts, multimodal, and instant API keys.
Google's free playground for building with Gemini — prompt design, multimodal input, structured output, and one-click export to API code. The fastest way to start building on Gemini.
AI insight: The free front door to the Gemini API — prototype in the browser, then export the exact call as code with one click.
Assaf Elovic / Tavily
Autonomous AI agent that runs deep multi-source web research and writes cited reports.
An open-source autonomous research agent that plans a task, runs parallel multi-source web searches, validates sources, and synthesizes a cited report. It runs locally as a Python package, FastAPI server, or MCP server, and works with any LLM provider plus a search/retriever backend. Free and Apache-2.0 licensed — you only pay your own LLM and search-API costs.
AI insight: An open-source take on 'deep research' — it fans out parallel searches and cites sources, runnable as a library or an MCP server.
Khoj AI
Open-source AI second brain that chats with your docs and the web, local or hosted.
An open-source "AI second brain" for chatting with local or online models, searching across your personal documents and the internet, building custom agents, and automating research. Self-host it on your own machine, or use plugins for Obsidian, Emacs, desktop, and mobile. Licensed AGPL-3.0; a paid managed cloud tier also exists, so it's freemium.
AI insight: Lives inside the tools you already use — Obsidian, Emacs, desktop, mobile — as an AGPL second brain over your notes and the web.
Grounded research notebook — chat your sources, get Audio Overviews.
Google's source-grounded research tool — upload docs, PDFs, and links, then ask questions answered only from your material, with citations and shareable Audio Overviews. Powered by Gemini.
AI insight: Answers strictly from your uploaded sources — no open-web drift — and its Audio Overviews turn a doc set into a two-host podcast.
Andrej Karpathy
Personalized arxiv reader by Andrej Karpathy.
Tag-and-track arxiv papers without drowning in the firehose. We track papers across edge inference, multi-agent harnesses, and memory architectures here — the spine of the Blokz Brief sample product.
AI insight: Karpathy's own tool, open-source and self-hostable — a tag-trained recommender that tames the arXiv firehose into a personal feed.
Hugging Face
Models, datasets, papers, spaces. The AI research commons.
Source-of-truth for open-weights models and datasets. Daily-paper feed for tracking research; Spaces for trying ideas without setting up infra. Heavy use at Blokz for any model we don't pay an API for.
AI insight: One account spans model weights, datasets, runnable Spaces, and a daily papers feed — the closest thing to a commons for open AI.