Run email-driven agents that pick up Redmine tasks
The author built custom agents that take instructions by email, one of which picks up and completes tasks from a Redmine board using a sandbox container for development. ·
Done with a custom-built or unnamed agent
- What they did
- The author built custom agents on top of RubyLLM and mostly gives them instructions by email. One agent has access to a Redmine project board, where it picks up tasks and completes assignments. It also gets non-sudo access to a sandbox container, which it uses for development work.
- How it went
- The source gives no results or numbers. It only describes the setup, running on a locally hosted Qwen model, so how well the agent completes tasks is not stated.
- Worth knowing
- Giving the agent only non-sudo access to a sandbox container limits what it can change while it does development work.
Try it yourself with n8n
Build a workflow that triggers when I get an email at [dedicated address] from [allowed sender], reads the instructions, and creates or updates a task in [Redmine/project board] accordingly. Add a step that has an AI agent work on the task, then replies by email with a summary of what it did. Before the workflow sends any reply or changes a task, have it hold the action for my approval, and finish by showing me a test run on a sample email.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: HN · Nov 5, 2026
Related use cases
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build a searchable map of funded companies
A software engineer had Replit Agent build a searchable map of Wefunder brick-and-mortar companies in about 3 hours for about $22.
Review GitHub pull requests automatically
An n8n AI agent triggers on each new PR, fetches diffs, calls an LLM for a review, and posts comments and labels back on the PR.
Build a multi-tenant SaaS with an agent
The poster built a production multi-tenant SaaS in 15 days with Replit Agent, but hit issues like RLS bypasses and production pointing at the dev database, so checking its work was essential.
Plan with PRDs and delegate tasks to cheaper agents
A developer uses a high-level agent to write a PRD, splits it into a task list, and hands the work to cheaper agents in a production workflow.
Review agent work plans and track user intent logs
A developer logs every user message to distill intent and has agents review saved plan files against project constraints before executing work.
Custom agent
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.