Documents and notes decision
Recall
A capable developer can build a useful subset (save, summarize, search, chat) in about a week, but many polished features (extensions, augmented browsing, TTS, bulk workflows and premium support) and product polish would be costly to match; keep paying if you need the full integrated experience.
Visit website↗$10/mo
$120/yr
Read off the official pricing page.
$50one-off30 h to build
$50/mo8 h/mo upkeep
On cash alone, building overtakes the subscription at 6 seats.
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. All Recall alternatives, with the arithmetic →
What a replacement has to do
- Ingest content (URL/PDF/audio), extract text/transcript, generate summaries via an LLM, index content and summaries into a vector/relational store, provide retrieval + chat over user's corpus.
What it still won’t have
- Browser extensions and mobile apps (unless rebuilt separately)
- Automated augmented browsing overlays
- Built-in text-to-speech with custom voices (Listen Mode)
- 1:1 onboarding and premium support
- Bulk actions / high-volume tooling and chosen-model routing
What remains hard
- Brand trust
Trusted by 500,000+ professionals
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 6 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 personal AI knowledge base web app using Next.js (React), a Postgres DB, and an open-source vector DB (e.g., Milvus or Weaviate). Implement: (1) endpoints to ingest URLs and PDFs and extract text/transcripts (use youtube-dl/yt-dlp and pdf parsing libs), (2) an LLM summarization worker calling OpenAI/other API to produce concise summaries with timestamps, (3) embedding generation and indexing into the vector DB, (4) a retrieval+chat endpoint that constructs prompts from retrieved snippets and calls the LLM, (5) metadata storage (title, URL, tags) in Postgres and a simple React UI to save, view, search, and export items. Out of scope: mobile apps, browser extensions, custom TTS voice models, multi-tenant billing. Include error handling for network/LLM failures, rate limits, and unit tests for ingestion, summarization, and retrieval components.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 5 cited sources+3
- Price verified on pricing page+3
- Evidence score63
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 productRecall - Your AI Knowledge Base
- official pricingRecall Pricing | Free, Plus & Max Plans | Recall
- official docsRecall Documentation
- open sourcelabring/FastGPT
- open sourcenashsu/llm_wiki
Integrity checks
What held up, and what did not.
