## Summary Rename Mastra’s first-party built-in gateway from **“Memory Gateway”** to **“Gateway”** across live product surfaces, docs, templates, and Mastra Code. This is primarily a naming change. Gateway still handles model routing, while Observational Memory remains a separate capability available through the hosted service. ## What changed - **Core:** `MastraGateway.name` and its provider-catalog display name now use **Gateway**. - **Playground:** the remote-memory panel uses **Gateway** as the product name and **Remote** as the status label. - **Mastra Code:** setup messages, internal symbol names, tests, and filenames use the current Gateway terminology. - **Docs and templates:** current product prose uses **Gateway** consistently. - **Tests and changesets:** assertions and release notes match the final naming. ## Compatibility The rename preserves existing identifiers and contracts: - `MastraGateway`, gateway id `mastra`, the `mastra/` model prefix, and `MASTRA_GATEWAY_*` environment variables are unchanged. - The `X-Memory-Gateway-Authorization` header remains unchanged because it is a wire contract. - Persisted `settings.memoryGateway` remains unchanged to avoid a settings migration. - Auth-storage keys and default URL string values are unchanged. - `MEMORY_GATEWAY_PROVIDER` and `MEMORY_GATEWAY_DEFAULT_URL` remain exported as deprecated aliases of the new `MASTRA_GATEWAY_*` constants. - `MastraCodeGateway.getMemoryGatewayApiKey()` remains a deprecated alias and is covered for both normal and detached static calls. - `/gateway` is the current hidden setup command; legacy `/memory-gateway` remains accepted as an alias. This lets current code adopt the Gateway name without breaking existing consumers, stored configuration, commands, or network integrations. ## Deliberately out of scope This PR does not change Gateway memory behavior or infer new capabilities from its display name. It also does not include unrelated CI hardening or review fixes. The following accidental branch changes were restored exactly to `main`: - client-js observability/memory E2E reset and seeding changes - MongoDB vector metadata validation and its changeset - generated Temporal fixture formatting drift ## Changesets - `@mastra/core` — patch: display-name rename - `mastracode` — patch: setup naming and `/gateway` alias - `@mastra/code-sdk` — minor: new canonical exports/accessor with deprecated compatibility aliases ## Validation Synced normally with `main` through ` |
History
|
|
|---|---|---|
| .. | ||
| src/mastra | ||
| .env.example | ||
| .gitignore | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
Meeting Notes (with Zoom)
Turns a Zoom cloud recording into structured meeting notes — attendees, decisions, action items, topics — and optionally ships them to Notion or Linear via MCP.
- Zoom Server-to-Server OAuth — one-time setup, no per-user OAuth dance.
ingest-meetingworkflow — pulls the Zoom-generated VTT transcript, summarizes it withgpt-5.4via Mastra's Gateway, returns structured JSON.- Optional exports to Notion and Linear via MCP, gated on env vars.
POST /meetings/upload— API route for non-Zoom sources (Google Meet, Riverside, Loom, plain text).
Demo
This demo runs in Mastra Studio. Open the meetingNotesAgent and ask it to summarize a transcript, or run the ingest-meeting workflow with a Zoom meeting id.
Prerequisites
- A Gateway API key.
- A Turso database URL + auth token.
- A Zoom Server-to-Server OAuth app. See setup below.
- (Optional) A Linear API key to create issues from action items.
- (Optional) A Notion integration token to push notes via the Notion MCP server.
Quickstart 🚀
- Set up a Zoom Server-to-Server OAuth app
- At https://marketplace.zoom.us → "Develop" → "Build App" → choose "Server-to-Server OAuth".
- Add these scopes:
cloud_recording:read:list_user_recordings:admincloud_recording:read:recording:adminuser:read:user:admin
- Activate the app and copy the Account ID, Client ID, and Client Secret into
.env.
- Add your API keys
- Copy
.env.exampleto.envand fill it in.
- Copy
- Start the dev server
- Run
npm run devand open localhost:4111.
- Run
Then try:
- In Studio, run the
ingest-meetingworkflow with a ZoommeetingId. - Or chat with the
meetingNotesAgent: "List my recent Zoom recordings", then "Summarize the one from Tuesday".
Zoom transcripts
This template uses Zoom's built-in transcript (generated by Zoom AI Companion). Make sure the cloud-recording setting "Audio transcript" is enabled for the user whose meetings you're ingesting. If a meeting has no Zoom transcript, fetchZoomTranscript will throw — wire in your own STT service (e.g. Whisper, Deepgram, AssemblyAI) as a fallback.
Manual upload endpoint
POST /meetings/upload
Content-Type: application/json
{
"title": "Q3 planning sync",
"transcript": "Alice: Let's start with..."
}
Returns the structured notes JSON. Useful for Google Meet / Riverside / Loom / plain text sources.
Making it yours
- Add Whisper fallback. Drop a
transcribeAudiotool that downloads the recording's audio file and runs it through Whisper, so meetings without Zoom AI still work. - Tighten the output schema. Edit
meetingNotesOutputSchemato capture the fields your team actually uses (e.g. risks, blockers, follow-up meetings). - Auto-create Linear issues. Add a workflow step that loops over
actionItemsand uses the Linear MCP tools to create issues for each one. - Trigger on Zoom webhooks. Add an API route at
/zoom/webhookthat listens for therecording.completedevent and kicks off theingest-meetingworkflow automatically.
Agent Editor
This template enables the code-backed Agent Editor with new MastraEditor({ source: 'code', codePath: 'mastra/editor' }). Edits made in Studio are written as deterministic JSON overrides under mastra/editor/agents/, so Mastra Platform can open GitHub pull requests for agent changes instead of only saving them to the database.
About Mastra templates
Mastra templates are ready-to-use projects that show what you can build. Use the platform-created repository as your starting point, then customize it for your app.
Want to contribute? See the Mastra contributing guide.