Automated README summary
Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
typesafe-computer-use (jev) drives a Mac toward a plain-English goal by reading the screen deterministically, asking a small classifier for the next action, and only calling a writing model for free text or final answers. For developers exploring cheap, fast desktop automation.
How it uses Jev
Jev answers three Choice questions per step: which kind of action, which item, which site. State includes OCR text, accessibility tree labels, computed facts like dates and focus, and tried actions. The chosen action runs deterministically; low confidence or a stop hands off to the writer.
Primitives:choice
Technique worth stealing
Compute all reasoning as deterministic state in code, then let a classifier pick from a bounded action list.
Try it
uv run clicker "open the Playground" for a dry run; add --act to drive the machine.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.87
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.32
- Reports measured numbersnot found in the excerpt0.32
- Is a runnable toolunclear0.48
- Top-10 learning shortlist signalunclear0.54
- Is a replica of the modelFound in material0.65
- Solves a common problem (0–2)score on a 0–2 scale0.45 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 28 Sept 2026.