Shortwave
Group Gmail conversations, add bundles and todos, and index mail locally
The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Shortwave, group Gmail conversations, add bundles and todos, and index mail locally. The hard boundary is deep gmail semantics, cloud search, ai, team features, and mobile sync, plus mail infrastructure, integrations, and client polish.
Build verification: not recorded. How we judge buildability
What you give up
- deep Gmail semantics, cloud search, AI, team features, and mobile sync
- mail hosting and deliverability
- push on every platform
- advanced team collaboration
- provider-specific AI and search
Why people still pay
People still pay for Shortwave because an email client can be rebuilt; operating a trusted mail service with excellent deliverability cannot. The recurring cost buys IMAP quirks, OAuth, MIME, threading, search, attachments, offline sync, notifications, secure storage, and provider changes, not just the visible interface.
Your build guide
The stack, security requirements, and agent rules for a focused replacement.
Before you start
- Node and the Rust toolchain, a supported desktop build environment and an explicitly selected data folder. Remote sync is outside the initial scope. A Gmail account, registered OAuth application and appropriate provider scopes/verification for the intended deployment.
- Implementation components: Tauri, React and TypeScript for the desktop interface with a narrowly scoped Rust filesystem bridge. SQLite for structured state and search; user-owned files for original documents and attachments. Gmail API OAuth adapter with history-cursor reconciliation; a sanitized message viewer and optional reviewed summary provider.
- Scope boundary: deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability
Use these project rules and optional skill references alongside the prompt. Review each skill before adding it to your agent; the AGENTS.md export includes the same guidance.
Optional external skill: vercel-react-best-practices — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: web-design-guidelines — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: sharp-edges — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: Gmail message/thread IDs, sync cursors, user bundles, todo links, draft revisions and send receipts
Project rule — preserve this invariant: Labels and archive actions are conditional on the latest sync state; private messages cannot become prompts without explicit user selection.
Project rule — acceptance evidence: Expire the sync cursor and rebuild safely without deleting mail; completing a linked todo does not silently archive its source thread.
Implementation plan
Phase 1
Scope and fixtures. Implement this bounded workflow: Connect one Gmail account through its supported API, group threads into user-defined bundles and turn selected messages into todos. Search a bounded local cache and preview any optional AI summary before sending content to a provider. Record prerequisites, select representative user-owned fixtures and document the unsupported features: deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability
Phase 2
Durable model. Model Gmail message/thread IDs, sync cursors, user bundles, todo links, draft revisions and send receipts Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Labels and archive actions are conditional on the latest sync state; private messages cannot become prompts without explicit user selection.
Phase 3
Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss.
Phase 4
Permissions and integration failure. Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
Phase 5
Portable handoff. Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
Phase 6
Acceptance scenarios. Expire the sync cursor and rebuild safely without deleting mail; completing a linked todo does not silently archive its source thread. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.
WORKING SLICE Connect one Gmail account through its supported API, group threads into user-defined bundles and turn selected messages into todos. Search a bounded local cache and preview any optional AI summary before sending content to a provider. Build this scoped Shortwave-inspired workflow with a documented data model and visible failure states. Architecture - Tauri, React and TypeScript for the desktop interface with a narrowly scoped Rust filesystem bridge. - SQLite for structured state and search; user-owned files for original documents and attachments. - Gmail API OAuth adapter with history-cursor reconciliation; a sanitized message viewer and optional reviewed summary provider. Prerequisites and limits Node and the Rust toolchain, a supported desktop build environment and an explicitly selected data folder. Remote sync is outside the initial scope. A Gmail account, registered OAuth application and appropriate provider scopes/verification for the intended deployment. Outside this release: deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability Data model and correctness Gmail message/thread IDs, sync cursors, user bundles, todo links, draft revisions and send receipts Invariant: Labels and archive actions are conditional on the latest sync state; private messages cannot become prompts without explicit user selection. Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss. Security and privacy Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview. Recovery and export Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources. Implementation order 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Connect one Gmail account through its supported API, group threads into user-defined bundles and turn selected messages into todos. Search a bounded local cache and preview any optional AI summary before sending content to a provider. Record prerequisites, select representative user-owned fixtures and document the unsupported features: deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability 2. Phase 2 — Durable model. Model Gmail message/thread IDs, sync cursors, user bundles, todo links, draft revisions and send receipts Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Labels and archive actions are conditional on the latest sync state; private messages cannot become prompts without explicit user selection. 3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Save edits atomically with stable IDs and revision history. Detect external file changes and offer a conflict copy instead of last-write-wins data loss. 4. Phase 4 — Permissions and integration failure. Limit Tauri capabilities to selected folders and commands. Render imported content without executable HTML, and never expose arbitrary shell execution to the webview. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Provide a portable folder export with a JSON manifest and original files. Restore to a separate folder; rebuild disposable indexes from sources. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. Expire the sync cursor and rebuild safely without deleting mail; completing a linked todo does not silently archive its source thread. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance Expire the sync cursor and rebuild safely without deleting mail; completing a linked todo does not silently archive its source thread. Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees. Optional agent guidance Optional external skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Project rule — data model: Gmail message/thread IDs, sync cursors, user bundles, todo links, draft revisions and send receipts Project rule — preserve this invariant: Labels and archive actions are conditional on the latest sync state; private messages cannot become prompts without explicit user selection. Project rule — acceptance evidence: Expire the sync cursor and rebuild safely without deleting mail; completing a linked todo does not silently archive its source thread.
$ open in your agent (prompt prefilled, you press enter), copy the prompt or copy or download AGENTS.md · generated from this app's build plan
prompt copied. want to know what dies next week?
new verdicts + top votes, weekly. free. one-click out.
Alternatives to building your own
no votes, no pay-to-list · just what's real
Shortwave pricing
| plan | monthly | annual (per mo) | what you get |
|---|---|---|---|
| free | $0/user | $0/user | 90 days of standard and AI search history; max 15 threads per AI search; 0 AI filters; limited AI quota; mandatory 'Sent with Shortwave' signature. |
| pro | $18/user | — | 3 years of AI search history; max 50 threads per AI search; 0 AI filters; standard AI quota. |
| business | $30/user | — | 5 years of AI search history; max 50 threads per AI search; 3 AI filters; roughly 150-300 Standard-intelligence AI requests/day. |
| premier | $45/user | — | Unlimited AI search history; max 100 threads per AI search; 10 AI filters; 2x Business AI usage and 2x context. |
| max | $120/user | — | Unlimited AI search history; max 150 threads per AI search; 50 AI filters; 6x Business AI usage and 3x context. |
free tier90 days of standard and AI search history; max 15 threads per AI search; 0 AI filters; limited AI quota; mandatory 'Sent with Shortwave' signature
billingmonthly only for new subscriptions; no annual plan; billed upfront; 14-day free trial and 14-day refund window
hidden costsEvery teammate must use the same paid tier and is billed per seat. AI capacity, search depth and filter count require tier upgrades rather than overage purchases. One paid seat covers all of that person's signed-in accounts; Tasklet 24/7 automation is a separate subscription.
price historyPro: $14 → $18 (2026-06) · Business: $24 → $30 (2026-06) · Premier: $36 → $45 (2026-06) · Max: $100 → $120 (2026-06)
pricing sources checked 2026-08-12 · pricing source ↗
Questions about Shortwave
Can you build your own Shortwave with AI?
Partly. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Shortwave, group Gmail conversations, add bundles and todos, and index mail locally. The hard boundary is deep gmail semantics, cloud search, ai, team features, and mobile sync, plus mail infrastructure, integrations, and client polish.
What does the Shortwave build prompt cover?
The prompt starts with this scope: Connect one Gmail account through its supported API, group threads into user-defined bundles and turn selected messages into todos. Search a bounded local cache and preview any optional AI summary before sending content to a provider. Full-product capabilities excluded from the comparison include: deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability; push on every platform. Follow the implementation plan and its prerequisites before expanding the build.
How do I use the prompt, AGENTS.md and agent skills?
Start with the Shortwave prerequisites and stack, then copy the prompt into your coding agent. Save the project rules as AGENTS.md in the project root. Linked skills are optional packages or source instructions for specific tasks; review their current contents and install only those matching the chosen stack. A skill does not supply API credentials or verify the finished app.
How long will this Shortwave project take?
The catalogue estimate is multi-day for the limited scope. Setup, integration approvals, debugging, deployment and ongoing maintenance can add time. This is an estimate, not a delivery guarantee.
What would I give up by replacing Shortwave?
deep Gmail semantics, cloud search, AI, team features, and mobile sync; mail hosting and deliverability; push on every platform; advanced team collaboration; provider-specific AI and search. People still pay for Shortwave because an email client can be rebuilt; operating a trusted mail service with excellent deliverability cannot. The recurring cost buys IMAP quirks, OAuth, MIME, threading, search, attachments, offline sync, notifications, secure storage, and provider changes, not just the visible interface.
What price is this guide comparing against?
The recorded Pro plan is $18/mo per seat (monthly per user), checked 2026-08-12. Check the linked pricing source before buying. Building your own also has hosting, API and maintenance costs; the recorded amount is not a guaranteed saving.
What can I use instead of building Shortwave?
BlueMail Personal: Clusters group related mail and the Later Board turns messages into tasks; Gmail-specific bundles are less clever. Spark Free: Smart Inbox, Set Aside and Done reproduce the focused workflow; conversation bundling is simpler. Check each option's license, hosting needs and feature limits.