Beans by hmans
Shares rank 12 of 14 task managers by recommenders
Recommended as a simple, pragmatic Markdown-based task tracker that agents can read and edit directly. Critics say its codebase is large and setup in a repo can be messy.
Recommended as a simple, pragmatic Markdown-based task tracker that agents can read and edit directly. Critics say its codebase is large and setup in a repo can be messy.
7 people gave an opinion
- recommend it
- 5
- criticize it
- 2
- approval share
- 71%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 5 people recommend itNeeds 10 or more, not met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Plain Markdown files agents can edit
“its serdes is markdown files with front matter, in a dot folder”
Comment from 24 Jan 2026 in “Gas Town's Agent Patterns, Design Bottlenecks, and Vibecoding at Scale” “its directly editable by them as its just markdown”
Comment from 20 Jan 2026 in “Ask HN: Do you have any evidence that agentic coding works?” Simpler code and easier use
“for much simpler code and use”
Comment from 4 Jun 2026 in “Claude Code and Codex Can Have Real-Time Conversation via Git” Pragmatic fit with agent workflows
“I find it a refreshingly pragmatic take that works great with my agents use.”
Comment from 25 Mar 2026 in “Thoughts on Slowing the Fuck Down”
What people warn about
Each mark is one comment
Large codebase and messy setup
“It's insane that its measured in the 100s of thousands of LoC and getting that thing setup in a repo is a mess.”
Comment from 31 Jan 2026 in “A Step Behind the Bleeding Edge: A Philosophy on AI in Dev” Weak human auditability
“wanted something with better human auditability”
Comment from 4 Mar 2026 in “Show HN: Beans, a task tracker with verification gates and agent orchestration”
Other task managers people recommend
The four most recommended other task managers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Beads by Steve Yegge | 79 | 55 | 59% | 11 | 3 mo4 owners | — |
| Apple Reminders | 15 | 16 | 48% | 11 | — | — |
| Paca | 14 | 2 | 88% | 2 | — | — |
| Todoist | 13 | 7 | 65% | 7 | — | — |
| Beans by hmansThis page | 5 | 2 | 71% | 3 | — | — |
What people said
6 of the 8 comments that mention it, newest first. Each links to the original comment.
“for much simpler code and use”
“I find it a refreshingly pragmatic take that works great with my agents use.”
“wanted something with better human auditability”
“It's insane that its measured in the 100s of thousands of LoC and getting that thing setup in a repo is a mess.”
“its serdes is markdown files with front matter, in a dot folder”
“its directly editable by them as its just markdown”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.