Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Rocky is a voice-controlled computer agent for macOS (Windows written but untested) that lets you say a command and have your computer perform it, built on TypeSafe's Jev decision model.
How it uses Jev
Jev makes routing and goal-loop decisions: the router asks thirteen questions in one request (kind, addressed, compound, needs_screen, app, site, engine, shortcut, scroll, volume, media, system op, text span); the goal loop asks kind, click target and type target together. Jev returns an index and confidence, and code executes the action.
Primitives:choice
Technique worth stealing
Select instead of generate: every free-text value is cut from the utterance in code and offered as candidates for Jev to select.
Try it
uv sync; cp .env.example .env; add TYPESAFE_API_KEY and TEXT_MODEL_API_KEY; uv run rocky --text "open photo booth"
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 material0.94
- Shows a System One patternFound in material0.83
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.89
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalunclear0.49
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale0.70 / 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 20 Sept 2026.