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 \nrules (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."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Show HN: I built AI agents with CrewAI to automate my entire Gmail workflow"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://github.com/tonykipkemboi/crewai-gmail-automation"}},"_tags":["story","author_Tonykip","story_43354219","show_hn"],"author":"Tonykip","children":[43354231,43354464,43354513,43354520,43354557,43354562,43354682,43354775],"created_at":"2025-03-13T15:18:52Z","created_at_i":1741879132,"num_comments":25,"objectID":"43354219","points":26,"story_id":43354219,"story_text":"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 \nrules (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.","title":"Show HN: I built AI agents with CrewAI to automate my entire Gmail workflow","updated_at":"2026-01-05T20:52:39Z","url":"https://github.com/tonykipkemboi/crewai-gmail-automation"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mounir-portia"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Show HN: Portia \u2013 A stateful Crew AI alternative, with auth and 1000 tools"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/portiaAI/portia-sdk-python"}},"_tags":["story","author_mounir-portia","story_44561985","show_hn"],"author":"mounir-portia","children":[44562021,44562271,44565542,44568199,44570139,44574605],"created_at":"2025-07-14T16:24:10Z","created_at_i":1752510250,"num_comments":10,"objectID":"44561985","points":19,"story_id":44561985,"title":"Show HN: Portia \u2013 A stateful Crew AI alternative, with auth and 1000 tools","updated_at":"2025-07-18T22:50:09Z","url":"https://github.com/portiaAI/portia-sdk-python"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tizkte"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"CrewAI vs. AutoGen for runnning LLM-generated code"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://e2b.dev/blog/crewai-vs-autogen-for-code-execution-ai-agents"}},"_tags":["story","author_tizkte","story_39399490"],"author":"tizkte","created_at":"2024-02-16T16:46:34Z","created_at_i":1708101994,"num_comments":0,"objectID":"39399490","points":14,"story_id":39399490,"title":"CrewAI vs. AutoGen for runnning LLM-generated code","updated_at":"2024-09-20T16:31:29Z","url":"https://e2b.dev/blog/crewai-vs-autogen-for-code-execution-ai-agents"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jonkrohn"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Agentic AI Engineering: Full 4-Hour Workshop feat. MCP, CrewAI, OpenAI Agent SDK"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.youtube.com/watch?v=LSk5KaEGVk4"}},"_tags":["story","author_jonkrohn","story_44600832"],"author":"jonkrohn","children":[44600833,44602660,44607915,44615986,44665499],"created_at":"2025-07-18T03:10:20Z","created_at_i":1752808220,"num_comments":8,"objectID":"44600832","points":12,"story_id":44600832,"title":"Agentic AI Engineering: Full 4-Hour Workshop feat. MCP, CrewAI, OpenAI Agent SDK","updated_at":"2025-07-28T04:01:15Z","url":"https://www.youtube.com/watch?v=LSk5KaEGVk4"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mtrofficus"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"CrewAI Meets Suno AI"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/neural-maze/melody_agents"}},"_tags":["story","author_mtrofficus","story_40686406"],"author":"mtrofficus","created_at":"2024-06-15T00:14:12Z","created_at_i":1718410452,"num_comments":0,"objectID":"40686406","points":12,"story_id":40686406,"title":"CrewAI Meets Suno AI","updated_at":"2024-09-20T17:18:56Z","url":"https://github.com/neural-maze/melody_agents"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"rakan1"},"story_text":{"matchLevel":"none","matchedWords":[],"value":"Curious."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Does anyone use CrewAI or LangChain anymore?"}},"_tags":["story","author_rakan1","story_47132187","ask_hn"],"author":"rakan1","children":[47132417,47133102,47136397,47146042,47157075],"created_at":"2026-02-24T02:40:13Z","created_at_i":1771900813,"num_comments":5,"objectID":"47132187","points":11,"story_id":47132187,"story_text":"Curious.","title":"Does anyone use CrewAI or LangChain anymore?","updated_at":"2026-07-14T10:03:47Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"thinkagenticai"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"We\u2019ve published a set of open-source reference implementations on how to build production-grade Agentic AI applications on AWS.
What\u2019s in the repo:\n \u2022 Agentic RAG, memory, and planning workflows with LangGraph & CrewAI\n \u2022 Strands-based flows with observability using OTEL & Arize\n \u2022 Evaluation with LLM-as-judge and cost/performance regressions\n \u2022 Built with Bedrock, S3, Step Functions, and more
GitHub: https://github.com/aws-samples/sample-agentic-frameworks-on-...
Would love your thoughts \u2014 feedback, issues, and stars welcome!"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Show HN: Agentic AI Frameworks on AWS (LangGraph,Strands,CrewAI,Arize,Mem0)"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/aws-samples/sample-agentic-frameworks-on-aws"}},"_tags":["story","author_thinkagenticai","story_44763850","show_hn"],"author":"thinkagenticai","created_at":"2025-08-02T00:20:11Z","created_at_i":1754094011,"num_comments":0,"objectID":"44763850","points":7,"story_id":44763850,"story_text":"We\u2019ve published a set of open-source reference implementations on how to build production-grade Agentic AI applications on AWS.
What\u2019s in the repo:\n \u2022 Agentic RAG, memory, and planning workflows with LangGraph & CrewAI\n \u2022 Strands-based flows with observability using OTEL & Arize\n \u2022 Evaluation with LLM-as-judge and cost/performance regressions\n \u2022 Built with Bedrock, S3, Step Functions, and more
GitHub: https://github.com/aws-samples/sample-agentic-frameworks-on-...
Would love your thoughts \u2014 feedback, issues, and stars welcome!","title":"Show HN: Agentic AI Frameworks on AWS (LangGraph,Strands,CrewAI,Arize,Mem0)","updated_at":"2025-08-11T19:31:12Z","url":"https://github.com/aws-samples/sample-agentic-frameworks-on-aws"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ulrischa"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"CrewAI: Framework for orchestrating role-playing, autonomous AI agents"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://github.com/joaomdmoura/crewAI"}},"_tags":["story","author_ulrischa","story_38904970"],"author":"ulrischa","created_at":"2024-01-07T20:45:51Z","created_at_i":1704660351,"num_comments":0,"objectID":"38904970","points":5,"story_id":38904970,"title":"CrewAI: Framework for orchestrating role-playing, autonomous AI agents","updated_at":"2024-09-20T15:59:33Z","url":"https://github.com/joaomdmoura/crewAI"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fsndz"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Crewai Raises $18M\u2013But Are AI Agents Ready for Prime Time?"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://finance.yahoo.com/news/crewai-launches-multi-agentic-platform-120000686.html"}},"_tags":["story","author_fsndz","story_41918658"],"author":"fsndz","children":[41918659],"created_at":"2024-10-22T21:01:30Z","created_at_i":1729630890,"num_comments":3,"objectID":"41918658","points":4,"story_id":41918658,"title":"Crewai Raises $18M\u2013But Are AI Agents Ready for Prime Time?","updated_at":"2024-10-25T11:16:57Z","url":"https://finance.yahoo.com/news/crewai-launches-multi-agentic-platform-120000686.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"HomunMage"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"GUI for CrewAI, node based ai-agent visualized editor"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://github.com/HomunMage/CrewAI-GUI"}},"_tags":["story","author_HomunMage","story_40414454"],"author":"HomunMage","children":[40414455],"created_at":"2024-05-20T11:52:25Z","created_at_i":1716205945,"num_comments":1,"objectID":"40414454","points":3,"story_id":40414454,"title":"GUI for CrewAI, node based ai-agent visualized editor","updated_at":"2024-09-20T17:00:44Z","url":"https://github.com/HomunMage/CrewAI-GUI"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"joaomdmoura"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"AI Role Playing Agents Framework \u2013 CrewAI"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://github.com/joaomdmoura/crewAI"}},"_tags":["story","author_joaomdmoura","story_38847595"],"author":"joaomdmoura","children":[38847596],"created_at":"2024-01-02T21:52:40Z","created_at_i":1704232360,"num_comments":1,"objectID":"38847595","points":3,"story_id":38847595,"title":"AI Role Playing Agents Framework \u2013 CrewAI","updated_at":"2024-09-20T16:02:53Z","url":"https://github.com/joaomdmoura/crewAI"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"antonap"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Building the same AI agents with 3 frameworks: LangGraph vs. CrewAI vs. Swarm"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://www.relari.ai/blog/ai-agent-framework-comparison-langgraph-crewai-openai-swarm"}},"_tags":["story","author_antonap","story_42246897"],"author":"antonap","children":[42247098],"created_at":"2024-11-26T16:06:55Z","created_at_i":1732637215,"num_comments":0,"objectID":"42246897","points":3,"story_id":42246897,"title":"Building the same AI agents with 3 frameworks: LangGraph vs. CrewAI vs. Swarm","updated_at":"2024-11-26T17:01:19Z","url":"https://www.relari.ai/blog/ai-agent-framework-comparison-langgraph-crewai-openai-swarm"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"danfuya"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Learnings Comparing AI Agent Frameworks LangGraph, CrewAI, AG, Semantic Kernel"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://bestaiagents.ai/blog/best-4-ai-agent-frameworks-2025"}},"_tags":["story","author_danfuya","story_42449741"],"author":"danfuya","children":[42449742,42449747],"created_at":"2024-12-18T11:47:56Z","created_at_i":1734522476,"num_comments":2,"objectID":"42449741","points":2,"story_id":42449741,"title":"Learnings Comparing AI Agent Frameworks LangGraph, CrewAI, AG, Semantic Kernel","updated_at":"2025-02-07T12:29:02Z","url":"https://bestaiagents.ai/blog/best-4-ai-agent-frameworks-2025"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Ross00781"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"CrewAI Reaches 44K GitHub Stars as Multi-Agent Orchestration Gains Momentum"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://theagenttimes.com/articles/44335-stars-and-counting-crewais-github-surge-maps-the-rise-of-the-multi-agent-e"}},"_tags":["story","author_Ross00781","story_47117537"],"author":"Ross00781","children":[47117653],"created_at":"2026-02-23T03:00:38Z","created_at_i":1771815638,"num_comments":1,"objectID":"47117537","points":2,"story_id":47117537,"title":"CrewAI Reaches 44K GitHub Stars as Multi-Agent Orchestration Gains Momentum","updated_at":"2026-03-05T23:35:16Z","url":"https://theagenttimes.com/articles/44335-stars-and-counting-crewais-github-surge-maps-the-rise-of-the-multi-agent-e"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"snasan"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"An Open Protocol Uniting LangGraph, CrewAI, and Pydantic AI Agents"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://openagents.org/blog/posts/2025-12-28-a2a-protocol-integration"}},"_tags":["story","author_snasan","story_46692495"],"author":"snasan","children":[46692496],"created_at":"2026-01-20T15:02:53Z","created_at_i":1768921373,"num_comments":1,"objectID":"46692495","points":2,"story_id":46692495,"title":"An Open Protocol Uniting LangGraph, CrewAI, and Pydantic AI Agents","updated_at":"2026-03-05T23:29:02Z","url":"https://openagents.org/blog/posts/2025-12-28-a2a-protocol-integration"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gardnr"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"CrewAI collects prompts via telemetry, can't be disabled"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://github.com/joaomdmoura/crewAI/issues/372"}},"_tags":["story","author_gardnr","story_40923115"],"author":"gardnr","children":[40923121],"created_at":"2024-07-10T02:07:54Z","created_at_i":1720577274,"num_comments":1,"objectID":"40923115","points":2,"story_id":40923115,"title":"CrewAI collects prompts via telemetry, can't be disabled","updated_at":"2024-09-20T17:23:55Z","url":"https://github.com/joaomdmoura/crewAI/issues/372"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"DeadlyPretzel"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Atomic AI Agents Framework \u2013 A Better Autogen / CrewAI Alternative"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/KennyVaneetvelde/atomic_agents"}},"_tags":["story","author_DeadlyPretzel","story_40589656"],"author":"DeadlyPretzel","children":[40589657],"created_at":"2024-06-05T19:47:56Z","created_at_i":1717616876,"num_comments":1,"objectID":"40589656","points":2,"story_id":40589656,"title":"Atomic AI Agents Framework \u2013 A Better Autogen / CrewAI Alternative","updated_at":"2026-06-19T13:27:45Z","url":"https://github.com/KennyVaneetvelde/atomic_agents"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"TheAnkurTyagi"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Show HN: Agent Cloud vs. CrewAI"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"https://www.agentcloud.dev/blog/agent-cloud-vs-crewai-a-comparison"}},"_tags":["story","author_TheAnkurTyagi","story_39939998","show_hn"],"author":"TheAnkurTyagi","children":[39939999],"created_at":"2024-04-05T08:33:22Z","created_at_i":1712306002,"num_comments":1,"objectID":"39939998","points":2,"story_id":39939998,"title":"Show HN: Agent Cloud vs. CrewAI","updated_at":"2024-09-20T16:49:00Z","url":"https://www.agentcloud.dev/blog/agent-cloud-vs-crewai-a-comparison"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"oabolade"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"I have been running into the same problems recently instrumenting my LangChain and CrewAI agent pipelines. If something goes wrong with a tool call, there was no way to way to prove what the agent did, in what order, and whether the logs have been modified. Observability platforms like LangSmith and Langfuse are great at optimizing for agent behavior, tokens and costs but they do not produce legally defensible and auditable artifacts. That's the reason why I decided to build RootSign, an SDK that instruments your CrewAI and LangGraph agents and produces cryptographic audit logs for CrewAI and LangGraph agents. RootSign adds a cryptographic hash chain to every tool call. If any record is modified after the fact, "rootsign verify" detects it.
What it does:
- SHA-256 hash chain across every Action record in a session \n- Human-in-the-loop checkpoints with Approval records for certain agent actions \n- PII redacted before hashing (StandardPIIConfig out of the box)\n- Works with LangGraph and CrewAI \u2014 AutoGen coming soon\n- Local first (Postgres + Timescale) \u2014 no cloud dependency
What it doesn't do (yet): compliance dashboard, cloud backend, policy engine, all on the roadmap.
Please try it out on the Github repo, contributions and feedback are always welcome."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Show HN: Tamper-evident audit logs for LangChain/Crew AI agents"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/Providex-AI/rootsign"}},"_tags":["story","author_oabolade","story_48588177","show_hn"],"author":"oabolade","created_at":"2026-06-18T16:52:51Z","created_at_i":1781801571,"num_comments":0,"objectID":"48588177","points":2,"story_id":48588177,"story_text":"I have been running into the same problems recently instrumenting my LangChain and CrewAI agent pipelines. If something goes wrong with a tool call, there was no way to way to prove what the agent did, in what order, and whether the logs have been modified. Observability platforms like LangSmith and Langfuse are great at optimizing for agent behavior, tokens and costs but they do not produce legally defensible and auditable artifacts. That's the reason why I decided to build RootSign, an SDK that instruments your CrewAI and LangGraph agents and produces cryptographic audit logs for CrewAI and LangGraph agents. RootSign adds a cryptographic hash chain to every tool call. If any record is modified after the fact, "rootsign verify" detects it.
What it does:
- SHA-256 hash chain across every Action record in a session \n- Human-in-the-loop checkpoints with Approval records for certain agent actions \n- PII redacted before hashing (StandardPIIConfig out of the box)\n- Works with LangGraph and CrewAI \u2014 AutoGen coming soon\n- Local first (Postgres + Timescale) \u2014 no cloud dependency
What it doesn't do (yet): compliance dashboard, cloud backend, policy engine, all on the roadmap.
Please try it out on the Github repo, contributions and feedback are always welcome.","title":"Show HN: Tamper-evident audit logs for LangChain/Crew AI agents","updated_at":"2026-06-18T17:53:57Z","url":"https://github.com/Providex-AI/rootsign"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Cherie91"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["crewai"],"value":"Why Choose OpenAgents Instead of CrewAI, LangGraph, AutoGen?"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://openagents.org/blog/posts/2026-02-23-open-source-ai-agent-frameworks-compared"}},"_tags":["story","author_Cherie91","story_47228116"],"author":"Cherie91","created_at":"2026-03-03T04:37:58Z","created_at_i":1772512678,"num_comments":0,"objectID":"47228116","points":2,"story_id":47228116,"title":"Why Choose OpenAgents Instead of CrewAI, LangGraph, AutoGen?","updated_at":"2026-03-05T23:40:22Z","url":"https://openagents.org/blog/posts/2026-02-23-open-source-ai-agent-frameworks-compared"}],"hitsPerPage":20,"nbHits":645,"nbPages":33,"page":0,"params":"query=crewai&advancedSyntax=true&analyticsTags=backend","processingTimeMS":5,"processingTimingsMS":{"_request":{"roundTrip":21},"fetch":{"query":2,"scanning":1,"total":4},"total":5},"query":"crewai","serverTimeMS":7}