paperloom
By trapoom555
Ingest research papers from URLs, arXiv IDs, DOIs, or PDFs into a local Obsidian vault. Auto-generate 4-section summaries, extract atomic findings with metadata, propose typed knowledge graph edges (supports/contradicts/etc.), query the graph for cited answers, and audit vault for orphans/duplicates/staleness.
npx claudepluginhub trapoom555/claude-paperloomComponent Overview
Setup Configuration
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
vault_pathLocal directory for the research vault. Created by /paperloom:init if it does not exist.
${user_config.vault_path}open_in_obsidianIf true, ingest opens the new paper page via the obsidian:// URI scheme.
${user_config.open_in_obsidian}Component Details
Commands (4)
Lite ingest — fetch a paper and write a short 4-section triage summary (Key Takeaways, Background, Main Idea & Summary, Critique). No figures, fast.
Scaffold a new PaperLoom at the configured path (or at an optional path argument). Idempotent — fills missing files without clobbering existing ones.
Scan the vault for orphan pages, frontmatter schema drift, duplicate findings, unmarked contradictions, and stale wikilinks. Reports issues without auto-fixing.
Ask a question of the research vault. Searches papers and findings, synthesizes an answer with wikilink citations.
Agents (4)
Extracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-extractor during /paperloom:ingest.
Compares 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.
Produces a short, triage-grade paper summary — Key Takeaways, Background, Main Idea & Summary, Critique. Invoked alongside metadata-extractor and finding-extractor during /paperloom:ingest. Returns JSON only; page assembly is handled by scripts/assemble_paper.py.
Extracts 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 lite-drafter and finding-extractor during /paperloom:ingest.
README
A Claude Code Plugin for Self-maintaining research knowledge graph for Claude Code + Obsidian.
|
|
| Knowledge graph view — 🟡 papers · 🟢 findings · 🟣 fields · 🔴 authors. Example shown: Typhoon.AI research papers. | Per-paper info page — 4-section summary (incl. critique), atomic findings, metadata + quality scores, and typed edges to related work. |
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.
Similar Plugins
autowiki
LLM-maintained knowledge base skill — structured wiki with Obsidian, milestone-based source clustering, proactive write-back, and autonomous lint
Uses power tools
Uses Bash, Write, or Edit tools
Help us improve
Share bugs, ideas, or general feedback.