paperloom
Karpathy-style LLM wiki for research papers. Ingest a URL / arXiv ID / DOI / PDF, write a structured summary into a local Obsidian vault, and maintain a finding-level knowledge graph via wikilinks + Dataview.
pinned to #b94a893updated 3 weeks ago
Ask your AI client: “install plugins/paperloom”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install plugins/paperloommetahub onboarded this repo on the author's behalf.
If you own github.com/trapoom555/claude-paperloom on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
92
Last commit
3 weeks ago
Latest release
published
- #claude-code
- #claude-code-plugin
- #knowledge-graph
- #obsidian
- #research-data-management
- #research-tool
What's bundled
Items extracted from this plugin's manifest + directory tree.
Commands (4)
/ingestFast, triage-grade ingest. `$ARGUMENTS` is the paper reference./initScaffold the Obsidian vault that PaperLoom uses. All filesystem work is done by `scripts/init_vault.py` — this command just resolves the path and shells out./lintRead-only health check of the vault. All six checks run in `scripts/lint.py`./query`$ARGUMENTS` is a natural-language question about the vault's contents.
Subagents (4)
finding-extractorExtracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-extractor during /paperloom:ingest.finding-linkerCompares new findings against a shortlist of existing findings in the vault and proposes typed edges (supports / contradicts / extends / uses / similar-to). Invoked by /paperloom:ingest.lite-drafterProduces a short, triage-grade paper summary — Key Takeaways, Background, Main Idea & Summary, Critique. Invoked alongside metadata-extractor and finding-extractor during /paperloom:ingest. Returns…metadata-extractorExtracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibility, experimental rigor, reproducibility) from a paper's plain text. Invoked alongside l…
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.b94a893· 3 weeks ago
Kind-specific
31Plugin: manifest fields complete
Plugin: bundled artifacts presentwarn
Couldn't find a skills/ subdir or an MCP server config inside the plugin
A plugin is most useful when it bundles ≥ 1 skill or an MCP server.
Plugin: bundle shape
4 commands · 4 subagents
Plugin: manifest location
manifest at .claude-plugin/plugin.json (modern convention)
Release history
1- releasecurrentb94a893warn3 weeks ago
Contents
Keep every paper you care about. See how they connect. Drop in a URL, arXiv ID, DOI, or PDF — Claude files it into an Obsidian vault, extracts the atomic claims, and wires them to everything you've read before with typed edges: supports, contradicts, extends, uses, similar-to.
Based on Andrej Karpathy's LLM Wiki pattern, tuned for research papers. 4 LLM calls per paper. Zero manual filing. Linking cost stays constant as the graph grows.
Features
- 4-section triage summary per paper — Key Takeaways → Background → Main Idea & Summary → Critique. The critique is generated by a reasoning model, so you get critical thinking, not a polite restatement of the abstract.
- Structured metadata + quality scores — authors, venue, date, fields, and a quality assessment (credibility, experimental rigor, reproducibility) on every paper.
- Atomic findings as graph nodes — one claim per file, with frontmatter and backlinks.
- Typed edges —
supports,contradicts,extends,uses,similar-to; auto-aggregated to paper-level (cites,builds-on, …). - Deterministic citation matching — arXiv ID → DOI → fuzzy title → first-author+year. The LLM never sees the reference list.
- Constant-cost linking — pre-filter caps the LLM at ≤30 candidate findings, so the 100th paper costs the same as the 10th.
- Cross-paper contradiction surfacing — bidirectional, with a pre-built Dataview view.
- Pre-built Dataview views — by-author, by-field, contradictions, high-credibility, recent-papers.
- Obsidian-native — plain wikilinks + YAML frontmatter, no custom app, no lock-in.
Quick Start
# 1. Install the plugin
claude --plugin-dir /path/to/claude-paperloom
# 2. Scaffold your vault (default ~/PaperLoom)
# On first run, this creates `.venv` at the plugin root and installs
# dependencies from `requirements.txt` automatically.
/paperloom:init
# 3. Ingest your first paper
/paperloom:ingest https://arxiv.org/abs/1706.03762
Open the vault folder in Obsidian and turn off Restricted Mode once to activate Dataview.
Commands
| You run | Claude does |
|---|---|
/paperloom:init [path] | Scaffold the vault. Idempotent. Seeds Dataview. |
/paperloom:ingest <url|arxiv-id|doi|pdf> | Fetch, summarize, extract findings, link. Skips if already in vault. |
/paperloom:query <question> | Search + synthesize across the vault with wikilink citations. |
/paperloom:lint | Health check. Auto-wires near-duplicate findings with bidirectional similar-to. |
Docs
- Pipeline — the 4-LLM-call ingest pipeline, section detection, models, token cost.
- Linking — five-layer linking, relation types, paper-level aggregation.
- Architecture — vault layout, plugin structure, design principles, out-of-scope.
Reviews
No reviews yet. Be the first.
Related
mega-brain
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session
cc10x
The Loop Engine — harness and loop engineering plugin for Claude Code. Router-kernel orchestration, workflow artifacts, sub-agent delegation, hook enforcement, Test Honesty Gates, fresh-context verification, and memory that persists. 73% leaner than v11, zero quality regression.
manifest-dev-tools
Tools for working with prompts and PRs alongside the manifest workflow. Collaborative PR walkthroughs, autonomous PR review with per-comment verification, author-side PR babysitting via manifest-dev, gap-calibrated prompt engineering, cross-boundary context handoff, and incremental teaching for session work.
mh install plugins/paperloom