Documents and notes decision
Glasp
A capable developer can build a narrower self-hosted replacement for highlight + summarization and basic chat, but reproducing Glasp’s community-driven discovery, polished cross-platform extensions, integrations catalog, and scale would be expensive and time-consuming—so keep paying if you rely on those.
Visit website↗Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need — the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship.
What a replacement has to do
- Capture highlights from web/PDF/YouTube → store and index highlights → generate AI summaries / chat against saved highlights → present in reader UI and export to external note apps.
What it still won’t have
- Large active community and social discovery features
- Polished cross-browser extensions and native mobile apps
- Extensive integrations catalog and daily sync reliability
- Priority support and usage scale optimizations
What remains hard
- Network effects
A knowledge graph maps what you read, and follows people who highlight the things you care about.
- Brand trust
2,000,000+ researchers, students, and lifelong learners highlight with Glasp.
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 17 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted Glasp-like service using: React frontend, Chrome/Firefox content script extensions, Node.js + Express backend, Postgres for metadata, S3-compatible storage for files, Tesseract or pdf.js for PDF text extraction, Meilisearch or OpenSearch for search, and OpenAI-compatible LLM+embedding API for summarization. In scope: highlight capture (browser extension), backend storage API, PDF ingestion + OCR, semantic search and embeddings, LLM-driven article/video/PDF summarization and a simple chat UI, and export to Markdown/Notion/Obsidian. Out of scope: native iOS/Android apps, large-scale multi-tenant optimizations, social feed/ranking, and advanced analytics. Include error handling, retry/backoff for API calls, per-user usage limits, basic auth, and unit/integration tests for core flows.
How we checked
How the score was reached
- Pay verdict base20
- An open-source build was found+5
- 5 cited sources+3
- Price verified on pricing page+3
- Hard moats found in the evidence-3
- Evidence score28
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time — so the same evidence always produces the same number.
How scoring works →Cited sources · 5
Every page the run actually retrieved.
- official productGlasp: PDF & Web Highlighter for Researchers & Learners
- official pricingGlasp Pricing
- official docsGlasp Documentation
- open sourcenashsu/llm_wiki
- open sourcelabring/FastGPT
Integrity checks
What held up, and what did not.
