I built AI agents with CrewAI to automate my entire Gmail workflow
I created a crew of AI agents using CrewAI to automate my old Gmail account that had a lot of unread emails. This is what I had it do: - Categorizing emails and assigning priority levels - Applying labels and stars based on content analysis - Creating draft responses for important emails only + saving it in Drafts folder - Sending Slack notifications for high-priority messages (I use Slack a lot) - Cleaning up low-priority emails based on configurable rules (delete low quality emails + empty trash afterwards) It works with most of the models so long as they're good at tool calling (most OSS…
In plain words
This project uses CrewAI to deploy a team of AI agents that automate Gmail inbox management. The system categorizes emails by priority, applies labels and stars, drafts responses to important messages, sends Slack notifications for urgent items, and deletes low-quality emails based on configurable rules. It connects via IMAP and works with most language models that support tool calling, with documentation and a video tutorial provided on GitHub.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I created a crew of AI agents using CrewAI to automate my old Gmail account that had a lot of unread emails. This is what I had it do: - Categorizing emails and assigning priority levels - Applying labels and stars based on content analysis - Creating draft responses for important emails only + saving it in Drafts folder - Sending Slack notifications for high-priority messages (I use Slack a lot) - Cleaning up low-priority emails based on configurable rules (delete low quality emails + empty trash afterwards) It works with most of the models so long as they're good at tool calling (most OSS Ollama models struggle) and connects via IMAP for easy setup. The project is well-documented with clear installation instructions in my repo above. I also have a YouTube tutorial walking through the project here: https://www.youtube.com/watch?v=zz0SA8xMBCo I built this to solve my own email overload problem and thought others might find it useful too. Would appreciate any feedback or suggestions for improvement. NOTE: I work at CrewAI. This is a side project I built to help solve my old email with a lot of unread emails that was running out of storage. I though to share here in case someone find it useful.
Does the same job
all alternatives →
- AEAgentMail – Email infra for AI agents2025 · chat.agentmail.to · ▲121
Hey HN, we're Haakam, Michael, and Adi. We're building AgentMail (https://agentmail.to/), an API to give AI agents their own email inboxes. We’re not talking about AI for your email, this is email for your AI. We started building email agents because they can converse with users in their inboxes, automate email-based workflows, and authenticate with third-party applications. Given these unique capabilities, we think email will be a core interface for agents. But we were building on top of Gmail, which was a struggle: poor API support, expensive subscriptions, rate limits,…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
