The fastest path is hosted: Agent Relay runs the integration stack for you — OAuth, sync workers, writeback — so you only run a local mount. One command and you have provider-backed files in an ordinary directory.
Want to run the whole stack yourself instead? See Run locally for the self-hosted Docker path. The source lives at github.com/AgentWorkforce/relayfile — clone it first.
One command
If you want Notion, Slack, Linear, GitHub, or other provider-backed files without running infrastructure, use Hosted Agent Relay. The CLI logs you in, creates or joins a cloud workspace, completes provider auth, waits for sync, and mounts the result.
relayfile setup \
--provider notion \
--workspace my-agent \
--local-dir ./relayfile-mount \
--no-open--no-open prints the hosted login and connect URLs instead of opening a browser — useful inside agents and headless environments. The command connects to agentrelay.com, completes the Nango connect flow, blocks until the provider reports ready, and starts the mount sync loop.
When it returns, ./relayfile-mount is a live mirror of your workspace:
ls ./relayfile-mount/notion
cat ./relayfile-mount/LAYOUT.mdSee Relayfile Cloud for what the hosted plane manages, and Mounting to do the same thing programmatically from a sandbox.
Read and write
Once mounted, the interface is the filesystem you already know:
# read
cat ./relayfile-mount/linear/issues/AGE-12__fix-login-bug.json
# patch back to the provider by writing the canonical path
echo '{"state":"In Review"}' \
> ./relayfile-mount/linear/issues/AGE-12__fix-login-bug.json
# find across providers
grep -rl '"state":"Todo"' ./relayfile-mount/linear/issues/See Reads and writes for the full PATCH / CREATE / DELETE model.
Next steps
Mount layout
Learn the tree shape: LAYOUT.md, _index.json, canonical naming, and alias views.
Reads and writes
How file ops map to PATCH, CREATE, and DELETE — and where schemas live.
The SDK
Use RelayFileClient from any agent runtime, with the built-in read cache.
Agents
One connect() call for Vercel AI SDK, OpenAI Agents SDK, and LangChain.