Clarify deployment setup options in docs

Author: marcusschiesser

.changeset/clear-provider-positioning.md

@@ -0,0 +1,5 @@
+---
+"agentpond": patch
+---
+
+Clarify that AgentPond supports multiple object stores while Firebase provides the automated one-command setup path.

AGENTS.md

@@ -5,7 +5,8 @@
 This repository uses Changesets to generate package changelogs.
 
 - Add a changeset in `.changeset/` for every user-facing change, package dependency change, CLI behavior change, or release-worthy bug fix.
-- Use `patch` for fixes and dependency maintenance, `minor` for new features, and `major` for breaking changes.
+- Use `patch` for fixes and dependency maintenance, and `minor` for new features or pre-1.0 breaking changes.
+- Do not add `major` changesets for now. A major changeset would trigger the 1.0 release and requires explicit approval.
 - Keep changeset summaries concise and written for AgentPond users.
 - Do not manually edit generated changelog output unless the release process has already run `pnpm changeset version`.
 

README.md

@@ -14,15 +14,15 @@
   <a href="https://www.npmjs.com/package/agentpond"><img src="https://img.shields.io/node/v/agentpond.svg" alt="Node.js version"></a>
 </p>
 
-AgentPond is a lightweight trace backend and CLI for AI applications. It keeps raw traces in object storage you control and syncs them into a local DuckDB cache for fast analysis by developers and coding agents.
+AgentPond is a lightweight trace backend and CLI for AI applications. It keeps raw traces in object storage you control and syncs them into a local DuckDB cache for fast analysis by developers and coding agents. Use it with Firebase Storage, Amazon S3, Google Cloud Storage, Vercel Blob, or custom infrastructure. Firebase includes an automated one-command setup; other deployments use the manual setup path.
 
 ## How it works
 
 ![AgentPond data flow from agent traces through object storage and local CLI analysis](https://raw.githubusercontent.com/marcusschiesser/agentpond/main/docs/assets/agentpond-how-it-works.png)
 
 Object storage is the durable source of truth. The local DuckDB database is a rebuildable analytical cache, so production traces stay in your infrastructure without requiring an always-on analytics database.
 
-## Get started with Firebase
+## Quick start: Firebase in one command
 
 You need Node.js 22 or newer and an initialized Firebase project with an active project selected through `firebase use`.
 
@@ -48,7 +48,7 @@ npx agentpond traces list --limit 10
 
 See [Firebase setup](./docs/getting-started/firebase.md) for prerequisites and troubleshooting.
 
-> Not using Firebase? See [Manual deployment setup](./docs/getting-started/manual-setup.md) for AWS, Google Cloud, Vercel, and custom infrastructure.
+> For Amazon S3, Google Cloud Storage, Vercel Blob, or custom infrastructure, see [Manual deployment setup](./docs/getting-started/manual-setup.md).
 
 ## Analyze traces