Show HN: Even Keel – a task queue for coding agents
I was new to developing apps with a coding agent months ago. I was sitting in the terminal and trying to understand how people actually use them. I had a bunch of project ideas and was constantly saying, "Do this, do that." For a while it was ok, but later I didn't have enough time to track what my agent was doing. To find a tracker was not a problem, but to start the agent in a predictable way: in the order of tasks' block links, one at a time per worktree and task, waiting out usage
Read original sourceSource record
Recorded metrics
points · 1 votes
2026-11-18 00:28:50.570Z
cumulative since publication
Research analysis
Project record
Repository: NamerekT/even-keel. Source account: I was new to developing apps with a coding agent months ago. I was sitting in the terminal and trying to understand how people actually use them. I had a bunch of project ideas and was constantly saying, "Do this, do that." For a while it was ok, but later I didn't have enough time to track what my agent was doing. To find a tracker was not a problem, but to start the agent in a predictable way: in the order of tasks' block links, one at a time per worktree and task, waiting out usage
Observed adoption & comparisons
Source votes: 1 votes (Nov 18, 2026 UTC; cumulative since publication) Recent records to compare: “mdiri-ai/SoduWork” (Trendshift, Nov 18, 2026); “mvanhorn/last30days-skill” (Trendshift, Nov 18, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.