AI tools for researchers
Research is where AI is most tempting and most dangerous. A model can summarise fifty papers in a minute, and it can also invent a citation that looks exactly like a real one. The tools on this page are built around sources: they search the literature, read the papers you give them, answer with citations you can follow, and keep the evidence next to the claim.
Deep research agents
A deep research agent breaks a question into searches, reads the results and writes a report with references. They save hours on a first pass through an unfamiliar field. Their weak point is source quality: they read what search returns, so check where each claim comes from before it goes into your own work.
Papers, notes and references
For academic work, the tools that matter connect to the places papers live, such as arXiv and Semantic Scholar, or to the reference manager you already use. Question answering over your own PDFs, with the page each answer came from, is the most reliable use of a model in this list.
Science skills for agents package methods: statistics, lab protocols, literature review steps. They help most when you already know the method and want the assistant to follow it consistently.
Keep unpublished data and participant information out of hosted models unless your ethics approval allows it. Several tools here run on local models for that reason.
The list
From SkillScout's catalogue, counted on 27 October 2026: 131 entries matched this topic, and these are the 12 with the most GitHub stars, one per project, after a review for false matches. Descriptions are each project's own. Stars show popularity, not fit.
-
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into...
Get the code, then follow its README:
git clone https://github.com/khoj-ai/khoj -
scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific...
Get the code, then follow its README to add the skill:
git clone https://github.com/K-Dense-AI/scientific-agent-skills -
gpt-researcher
An autonomous agent that conducts deep research on any data using any LLM providers
Get the code, then follow its README:
git clone https://github.com/assafelovic/gpt-researcher -
RD-Agent
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on...
Get the code, then follow its README:
git clone https://github.com/microsoft/RD-Agent -
paper-qa
High accuracy RAG for answering questions from scientific documents with citations
Get the code, then follow its README:
git clone https://github.com/Future-House/paper-qa -
Auto-claude-code-research-in-sleep
ARIS (Auto-Research-In-Sleep), Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No...
Get the code, then follow its README to add the skill:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep -
local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private...
Get the code, then follow its README:
git clone https://github.com/LearningCircuit/local-deep-research -
transformerlab-app
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
Get the code, then follow its README:
git clone https://github.com/transformerlab/transformerlab-app -
zotero-mcp
Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations...
Get the code, then follow its README:
git clone https://github.com/54yyyu/zotero-mcp -
claude-scholar
Semi-automated research assistant for academic research and software development. Supports Claude Code, OpenCode, and Codex CLI across ideation, coding, experiments...
Get the code, then follow its README:
git clone https://github.com/Galaxy-Dawn/claude-scholar -
arxiv-mcp-server
A Model Context Protocol server for searching and analyzing arXiv papers
Get the code, then follow its README:
git clone https://github.com/blazickjp/arxiv-mcp-server -
papersgpt-for-zotero
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.5, Claude Fable 5, Claude Sonnet 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.2, SiliconFlow, GPT-oss...
Get the code, then follow its README:
git clone https://github.com/papersgpt/papersgpt-for-zotero
Questions
Can AI find real academic papers?
Tools that search a paper index return real papers with links. A chat model answering from memory can invent references, so use a tool that cites sources you can open.
Is there an AI tool that works with Zotero?
Yes. The catalogue includes Zotero plugins and MCP servers that let an assistant search and read your library. Check the list for the current ones.
Related
- Best AI tools, sorted by role and task
- AI tools for data analystsText-to-SQL, AI notebooks and spreadsheets, and database servers.
- Best AI tools for writersGrammar checkers, AI editors and writing skills that keep your voice.
- Best AI productivity toolsSecond brains, notes, workflow automation and meeting tools.
Your own list
This page ranks by popularity. SkillScout's scan ranks by fit: the AI you already use writes a short profile of how you work, and SkillScout scores about 22,000 AI tools against your gaps and hands back a short list with install steps. It is free, and the server never saves your profile.