Paste a URL, get clean text
The server fetches the page and extracts readable text — scripts, nav, and footers stripped — with no browser or scraping stack required. Failed fetches keep the row with the error so a human can fix it.
Ingest once. Every employee studies it. URLs, PDFs, ebooks, and transcripts your AI can search and cite.
Resources is the knowledge-ingestion surface: external material your team didn't write — articles, ebooks, PDFs, transcripts — ingested once, extracted to searchable plain text, and served to AI employees on demand. It replaces the copy-paste-into-the-prompt ritual and the shared-drive folder no AI can actually read.
- URL, PDF, EPUB, text, and markdown
- Full-text search over extracted bodies
- read < edit < delete Grant levels
- Attach to outgoing Gmail by slug
genosyn.com / resources
usage-based billing
2 matchesURL
stripe.com/docs/billing
extracted · 41k chars
PDF
SOC 2 readiness guide.pdf
18 pages
EPUB
The Mom Test
12 chapters
Transcript
All-hands · Q1 retro
48 min
Alex (AI) cited the Stripe docs in today's pricing brief — every employee holds a read Grant
What ships in the box
Resources, in detail.
Real document formats
PDFs extract via pdf-parse, EPUBs unzip chapter by chapter, and TXT, Markdown, and HTML upload directly — 25 MB per file, with up to 1 MiB of extracted text each.
One search across it all
Full-text search over titles, summaries, tags, and extracted bodies — search-as-you-type for humans, the same query surface as a tool for AI employees.
Readable in place
Type-aware detail pages: editable markdown for text, the native viewer for PDFs, an in-app EPUB reader with table of contents and progress, and an open-original card for URLs.
Exports that look right
Export any Resource as PDF, HTML, Markdown, or plain text. PDFs render through Chromium, so headings, tables, and code blocks come out styled — ready for a chat reply or a Base record.
Attach to real email
Gmail send and draft tools accept attachments by Resource slug — the server checks the Grant and resolves the bytes, so no base64 ever crosses the model's context window.
With AI employees
Study before answering
AI employees reach the library through built-in tools gated by three Grant levels — read, edit, delete. The tool descriptions coach them to check whether the team already ingested a primer before improvising.
They curate it too
An employee can file a URL or a pasted transcript itself with create_resource — it gets full control of rows it authored, while teammates start at read.
Levels, not switches
read covers list, search, and get; edit adds re-titling, tagging, and body updates; delete allows permanent removal. Humans promote employees between levels from the share modal.
New material is instantly usable
Every new Resource is automatically granted read to all AI employees, so the primer you drop in at 9:00 informs the Routine that runs at 9:05.
Questions
Frequently asked.
How is a Resource different from a Note or a Memory?
A Resource is content the team did not write — an article, ebook, or transcript ingested once and queried on demand. A Note is a page the team authors together, and a Memory is a durable fact auto-injected into an AI employee's prompt.
What formats can I ingest?
Web pages by URL (fetched and extracted to plain text), PDF, EPUB, TXT, Markdown, and HTML uploads up to 25 MB per file, and pasted raw text. Video files are accepted but transcripts aren't extracted yet — upload the transcript as text in the meantime.
Can AI employees add their own Resources?
Yes. The create_resource tool lets an employee index a URL or file a pasted transcript or research summary. The authoring employee automatically gets full control of its own row; teammates start at read-only. File uploads stay human-only.
Can an AI employee email a Resource to someone?
Yes. The Gmail send and draft tools accept attachments by Resource slug and format — the server checks the employee's Grant, resolves the bytes, and attaches the original file or the text rendered as PDF, HTML, Markdown, or plain text.
Does it use embeddings or RAG?
v1 retrieval is deliberately simple: case-insensitive substring matching over titles, summaries, tags, and the full extracted text. Embeddings and vector search are planned once real query patterns are known.
More in the box
All productsBases
Multi-table workspaces with typed fields, saved views, comments, and attachments — and 21 built-in tools for granted AI employees.
Learn moreNotes
Notion-style markdown pages in nested notebooks — read, written, and searched by humans and AI employees under cascading Grants.
Learn moreAI Employees
Persistent AI teammates with a written constitution, markdown playbooks, and cron-scheduled work — every execution captured as a readable Run.
Learn moreWorkspace
Slack-style channels and DMs where AI employees are real members — @mention one and it joins, replies, and reports back from its Routines.
Learn moreMeet your first AI employee.
One command pulls the image and starts Genosyn on localhost:8471. Write their soul. Schedule their first routine.
$curl -fsSL genosyn.com/install.sh | bash