Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review โ searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDFโMarkdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Also answers direct literature lookups โ find papers on a topic, resolve a DOI, get an open-access PDF, check a citation, search PubMed / OpenAlex / Crossref / Semantic Scholar / Europe PMC / arXiv โ with no install and no API key. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it, plus keyless bundled scripts for multi-source search and
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review โ searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDFโMarkdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Also answers direct literature lookups โ find papers on a topic, resolve a DOI, get an open-access PDF, check a citation, search PubMed / OpenAlex / Crossref / Semantic Scholar / Europe PMC / arXiv โ with no install and no API key. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it, plus keyless bundled scripts for multi-source search and open-access full-text retrieval. Curated catalog of 70+ vetted projects. ๆฏๆไธญ่ฑๆ๏ผ็จไบใๆ็ฎ็ปผ่ฟฐๅทฅๅ ท้ๅใใๆ็ฎๆฃ็ดขใไธใไธ้ฎๅฎ่ฃ /่ฟ่กใ๏ผใ
Literature Review Tools โ Select & Run
A curated, use-case-organized catalog of the strongest open-source AI tools for
literature review โ plus a launcher that actually installs and runs the top ones.
Covers: end-to-end research agents, deep-research / auto-survey generators, autonomous
"ideaโpaper" systems, citation-backed RAG over PDFs, PRISMA screening, MCP servers,
Zotero/Obsidian integrations, PDFโstructured extraction, citation graphs, and
paper-writing / peer-review assistants.
Look up โ user wants the literature itself: "find papers on X", "get me the PDF for this DOI", "does this citation exist", "what does PubMed have since 2022". Answer it directly โ no install, no key. Start with for one-off lookups, or run the bundled / scripts for anything corpus-sized.
reference/apis/README.md
papers-fetch
oa-resolve
Recommend โ user asks "what should I use to โฆ". Route with the tables below; cite the catalog for details.
Run โ user asks to install / run / use a specific tool ("turn this PDF into Markdown with MinerU", "ask PaperQA2 about these papers", "set up the arXiv MCP server"). Drive scripts/litrun.py via Bash โ do not hand the user raw pip commands to copy.
Mode 1 is the cheap default. Do not send someone to install PyTorch when they asked
for five papers and a PDF.
Look up mode โ search without installing anything
Two bundled scripts, both standard-library only: no venv, no pip, no API key.
Run them straight (python3 scripts/fetch_papers.py โฆ) or through the launcher.
# 1. search six indexes at once, deduplicated by DOI
python3 scripts/fetch_papers.py --query "active learning for screening" \
--sources openalex,crossref,semanticscholar,pubmed,europepmc,arxiv \
--max 15 --dedup-titles --outdir ./corpus
# 2. turn those DOIs into full text you may legally read
python3 scripts/resolve_oa.py --from-json ./corpus/results.json --outdir ./corpus
fetch_papers.py writes results.json (normalised records, per-source counts, and the
errors of any source that failed) plus one .txt per paper. resolve_oa.py walks
Unpaywall โ OpenAlex โ Europe PMC โ arXiv โ CORE and writes oa_report.json recording
how every DOI resolved โ including the ones that stayed closed, and separating those
from DOIs Crossref has never registered (usually an invented citation). On a 47-paper
corpus with zero keys it recovered 33 full texts; nothing in it bypasses a paywall, and
you should not offer to.
For a single lookup โ one DOI, one author, one citation check โ skip the scripts and
call the API directly (WebFetch/curl). reference/apis/ has a
routing table, the identifier formats, and one page per API with the endpoints and the
failure modes that waste time (Crossref's select 400, OpenAlex's inverted abstracts,
Semantic Scholar's exhausted keyless pool, PubMed's multi-part AbstractText).
Report which indexes you queried and which came back empty. "OpenAlex had no match" is
a fact; "that paper doesn't exist" is a much bigger claim than one API can support.
Run mode โ how to drive scripts/litrun.py
The launcher installs each supported tool into its own venv under ~/.lit-review-tools/
(uses uv if present, else python -m venv) and reads API keys from one shared
~/.lit-review-tools/.env. Machine-readable recipes: recipes/recipes.json.
Typical flow when the user wants to use a tool:
python3 scripts/litrun.py doctor โ check toolchain + which API keys are already set.
python3 scripts/litrun.py info <id> โ confirm what the tool needs (entry, required env).
If a required key is missing, ask the user for it, then litrun.py env --set KEY=VALUE (never echo the value back in full).
python3 scripts/litrun.py run <id> -- <tool args> โ installs on first use, then runs. For PDF tools pass the real file path; e.g. run mineru -- -p paper.pdf -o ./out -b pipeline.
For MCP servers, don't "run" them โ litrun.py mcp <id> prints the client config block to register in Claude Code / Cursor.
Commands: list [--category C] [--kind K] ยท info <id> ยท doctor ยท env [--set K=V] ยท install <id> ยท run <id> -- <args> ยท mcp <id> [--storage PATH] [--client claude|cursor] ยท ui <id>.
python-script, zero install (stdlib only):papers-fetch (6-source deduplicated search) ยท oa-resolve (DOI โ open-access full text)
python-script (bundled, auto install+run):arxiv-fetch (arXiv PDFs) ยท openalex-fetch (OpenAlex; PDF or abstract .txt) ยท pubmed-fetch (PubMed abstracts) โ all keyless for light use. papers-fetch supersedes all three when you want coverage rather than one index.
python-lib (install + run example):gpt-researcher, storm (deep research; need API keys) ยท scholarly, pyalex (API clients)
For gpt-researcher and storm, litrun.py ui <id> clones the repo and launches the full web UI (GPT Researcher โ FastAPI at :8000; STORM โ Streamlit at :8501). These are long-running servers โ launch them with a background Bash call and tell the user the URL. gpt-researcher's UI needs OPENAI_API_KEY + TAVILY_API_KEY set first (litrun writes them into the repo's .env); STORM takes its keys in the app sidebar.
Chained pipelines
For multi-tool tasks, prefer a named workflow over hand-wiring steps: litrun.py workflow list then litrun.py workflow run <id> [--input PATH] [--query "..."] [--question "..."] [--max N]. Built-ins:
pdf-to-markdown โ a PDF/folder โ clean Markdown (MinerU)
pdf-corpus-qa โ a folder of PDFs โ citation-backed answer (PaperQA2)
pdf-md-then-qa โ convert to Markdown and answer a question over the corpus
topic-to-review โ arXiv query โ download PDFs โ citation-backed answer (PaperQA2). The end-to-end "retrieve then review" pipeline; no MCP client needed. Needs OPENAI_API_KEY for the QA step.
topic-to-review-multi โ retrieve from arXiv + OpenAlex into one corpus โ citation-backed answer. Broader coverage; resilient if one source is rate-limited.
topic-to-corpus โ six-source search โ deduplicated corpus. Keyless, no install โ the default first step for any review.
topic-to-fulltext โ six-source search โ open-access full text for every DOI it can legally get. Keyless.
topic-to-fulltext-review โ the strongest path: search โ dedup โ full text โ PaperQA2 answers over full texts, not abstracts. OPENAI_API_KEY for the last step only.
Prefer the topic-to-fulltext* workflows over topic-to-review-multi: same idea, six
sources instead of two, DOI-level deduplication, and it retrieves the papers rather
than the abstracts. Biomedical topics need no special casing โ PubMed and Europe PMC
are already in the source set.
Add --dry-run first to show the exact resolved step commands without executing โ good for confirming paths with the user before a heavy run. Workflows fail fast if a required API key is missing.
Guardrails: installs and downloads happen under the user's home and hit the network โ for a heavy first install (marker/docling pull in PyTorch) say so before running. Never fabricate API keys. If a run fails, show the real error rather than claiming success. Paths in this file (scripts/โฆ, recipes/โฆ) are relative to this skill's directory.
Recommend mode โ how to route
Identify which stage of the lit-review workflow the user is on (search โ read โ extract โ synthesize โ screen โ cite-check โ write/review).
Match it to a category below and recommend the โญ editor's pick first, then 1โ2 alternatives.
For anything beyond the top pick โ full star counts, every project in a category, or a category not summarized here โ read reference/catalog.md. Do not guess project names or URLs; pull them from the catalog.
Give a one-line "why this one" tied to the user's constraint (Claude Code vs. standalone, open vs. commercial, privacy/local, medical, etc.). If the pick is a runnable id above, offer to install/run it.
โก 30-second picker
Just need the papers themselves (topic / DOI / OA PDF) โโโถ Look up mode โ no install โญ
Use Claude Code, want end-to-end researchโpaper โโโโโโโโโโโถ academic-research-skills โญ
Want AI to research a topic โ cited report โโโโโโโโโโโโโโโโถ GPT Researcher / STORM
Want fully autonomous "idea โ submittable paper" โโโโโโโโโถ AI-Scientist-v2 / AutoResearchClaw
Citation-backed Q&A over a pile of PDFs โโโโโโโโโโโโโโโโโโโถ PaperQA2
Rigorous PRISMA review (thousands of abstracts) โโโโโโโโโโถ ASReview / prismAId
Clean Markdown from PDFs to feed an LLM โโโโโโโโโโโโโโโโโโถ MinerU / Docling / marker
Lit capabilities inside Claude / Cursor (MCP) โโโโโโโโโโโโถ paper-search-mcp / zotero-mcp
Chat with your library inside Zotero โโโโโโโโโโโโโโโโโโโโโถ zotero-gpt / PapersGPT
Pre-submission AI peer review โโโโโโโโโโโโโโโโโโโโโโโโโโโโถ open_reviewer / ai-peer-review
Categories (top pick per category)
Category
Editor's pick โญ
When
All-in-one research agents & skills
academic-research-skills
Claude Code user wanting researchโwriteโreviewโrevise, with integrity/citation gates
Active-learning screening of thousands of abstracts (PRISMA)
MCP servers
zotero-mcp / arxiv-mcp-server
Wire papers into Claude / Cursor / Cline
Zotero / Obsidian integration
zotero-gpt
Chat with your library inside your reference manager
PDF โ structured extraction
MinerU / docling / marker
Turn PDFs into clean Markdown/JSON for LLMs
Citation graphs & API clients
scholarly / pyalex
Citation-network analysis; scripting academic DBs
Writing & peer-review assistants
open_reviewer / ai-peer-review
Draft, polish, and pre-submission review
Awesome lists
Awesome-Auto-Research-Tools
Browse the whole landscape
Decision table (map need โ recommendation)
User's need
Recommend
Claude Code, end-to-end researchโpaper
academic-research-skills (most complete, #1 in space)
Generic "research this topic for me" agent
GPT Researcher / STORM
Wiki/survey-style long-form with citations
STORM / Co-STORM
Fully autonomous "idea โ submittable paper"
AI-Scientist-v2 / AutoResearchClaw
Cited Q&A over many PDFs
PaperQA / PaperQA2
Rigorous PRISMA systematic review
ASReview or prismAId
PDF โ clean Markdown for an LLM
MinerU / Docling / marker
Lit capabilities in an MCP client
paper-search-mcp / zotero-mcp
Chat with library inside Zotero
zotero-gpt / PapersGPT
AI pre-review before submission
open_reviewer / ai-peer-review
Just want to browse the landscape
The Awesome lists section
Notes & caveats
Open-source is prioritized. Commercial/closed tools (Elicit, Consensus, Scite, SciSpace, Research Rabbit, Connected Papers) are listed for reference only โ see the catalog's commercial section.
Star counts drift. The catalog's numbers are periodic GitHub-API snapshots โ treat as rough popularity signals, not exact. For live numbers, point the user at the repo.
Match the constraint, not just the task. Privacy/local โ local-deep-research; medical โ medsci-skills / paperai; Codex instead of Claude โ academic-research-skills-codex.
Full catalog with every project, star count, and one-line description: reference/catalog.md.
