The output layer for AI pipelines

SurfaceDocs turns AI-generated content into shareable, hosted documents. One API call, instant URL, zero infrastructure.

pip install surfacedocs

from surfacedocs import SurfaceDocs, DOCUMENT_SCHEMA, SYSTEM_PROMPT

docs = SurfaceDocs(api_key="sd_live_...")
result = docs.save(llm_output)
print(result.url)  # https://app.surfacedocs.dev/d/abc123

Quickstart

Install the SDK and save your first document in under 5 minutes.

Python SDK

Full reference for the SurfaceDocs Python client.

API Reference

REST API endpoints for documents and folders.

Why SurfaceDocs?

Every AI pipeline ends the same way: the model generates something valuable, and then you need to figure out where to put it. SurfaceDocs gives you:

Instant shareable URLs — docs.save(output) returns a link anyone can view
No infrastructure — No viewers to build, no hosting to manage
Built for AI output — Block-based schema that matches how LLMs think
Document versioning — Push new versions to the same URL, view history, restore old versions
Works with any LLM — OpenAI, Gemini, Anthropic, or any model

Get your API key

Sign up at app.surfacedocs.dev to get started.