Launching today

Hiro Task Manager

Launching today

Task manager for solo builders and their AI agents

3 followers

Task manager for solo builders and their AI agents

3 followers

Visit website

Issue tracking software

•

AI Workflow Automation

A task manager that is deeply and securely connected to AI agents. Create your tasks, organize them in lists and boards, in a Trello-inspired Web UI. Discuss them seamlessly with your AI agent. Allow the agent to create, update and review your tasks. Enrich them with Markdown and mermaid diagrams, the language that AI agents understand. Use it locally or on a VPS, use any LLM Model, any AI Agent, controlled access, works on macOS, Windows, *nix. Setup in 60 seconds. Detailed, up-to-date docs.

Free

Launch tags:Task Management•Developer Tools•Artificial Intelligence

Launch Team / Built With

Pioneer — Fine-tune any LLM in minutes, with one prompt

Fine-tune any LLM in minutes, with one prompt

Promoted

Maker

📌

I had a bottleneck in managing and organizing my tasks as a solo builder. Building at the speed of coding agents, I had new features flowing in and releases flowing out. I needed a task manager as simple as Trello; quick to add boards and tasks. I also needed it to be deeply connected to my coding agent. So, I built Hiro Task Manager, an open source project, that does just that. Then, I used it to build itself in the past 4 releases and It's ready to get tested. Now, I can prompt my coding agent: - Convert this plan into 5 tasks with detailed markdown description, add them to the board. - Review task #54 and update its status, in markdown format. - Check tasks marked critical, fix them all and set their status to in-progress - List open tasks in release 0.0.8 - Do we have Open Bugs in "CLI Module" list? - Make a Changelog document for release 0.0.7 What Hiro Task Manager is NOT: - a full project management suite - a cloud-first collaboration tool for teams The ability to share my tasks, releases and the flow of execution is very powerful. It enhances the AI Agent's episodic memory. It sort of becomes the glue that holds together all these endless conversations (tabs in cursor, sessions in claude code) In addition, it comes with the following: - Works locally or on a VPS. - Local agents and local models are welcome (tested on opencode+Gemma4) Available on macOS 12+, Win10+, *nix - Controlled Access for Agents (What can agent access? Level of control?) - Works with any AI Agent supported by skills package (45+ agents) - Easy to read documentation - written mostly by a Human :) Today, I released a stable version 0.1.0, and I'm starting to use it in my other projects. I am inviting you to do the same and I'd like feedback: Did you have the same problem I had? Would that project help, would you use it? What is it missing? Issues?

Report

1d ago