claude-eta

# claude-eta


  
  = 18" />
  
  
  


## Claude has no concept of time. claude-eta gives it one.

Claude says "this should take about 2 days." You finish in 12 minutes.

LLMs have zero feedback between what they promise and what actually happens.
claude-eta creates that loop: it times every task, learns your velocity,
and feeds real data back into Claude before it responds.

After 10 tasks of the same type, ETAs appear automatically — calibrated on YOUR project.


  


### How it works

1. You type a prompt
2. claude-eta classifies it, starts a timer, injects your velocity stats
3. Claude works. Tool calls, file ops, errors counted silently.
4. Task completes. Real duration recorded. Next estimate improves.
5. After 10 tasks of the same type, ETAs appear automatically at the start of Claude's responses.

## Eval results

Walk-forward replay over real, single-developer task history.

- **p80 coverage at prompt** typically lands in the **75–80% target range** (target: ~80%, since p80 is by definition the value the real duration should fall at or below 80% of the time).
- **MdAPE** (median absolute % error) sits in the **70–95% range** depending on the evaluator stage (`prompt` / `f…