InboxMinder: open-source Mac agent scores every Gmail, only 6 of 127 emails need you
ayushtweetshere · x · 2026-09-07
Developer Sachin Neravath open-sourced InboxMinder, a Mac-native email triage agent: it polls Gmail every 45 seconds with a durable queue (crashes and rate limits lose nothing), makes exactly one LLM call per email for reply-worthiness, category, and importance, then writes results to Gmail labels. Output failures fail open to "needs you". Runs locally with your own Anthropic/OpenAI key — nothing hosted.
- Demo: 127 emails a day, only 6 deserved a human
- Setup in 5 minutes via app download or npm i -g inboxminder; Apple Silicon, macOS 13+, v0.10.4, free and open source
A good fit for people drowning in cold pitches and newsletters who want to stay in Gmail.
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26