Automated README summary
Automatically summarized from the README on 30 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
SysTorch is a structured decision runtime for people, models, and agents. It routes typed questions through an inspectable DAG to local or cloud decision services, and can hand tasks to a human for persistent answering before returning results to the caller.
How it uses Jev
SysTorch uses the Jev/SystemOne decision protocol for its external service. It sends structured questions (Noul, Choice, Score, Box) to upstream adapters including TypeSafe SystemOne; the returned answers are routed back to the caller. The README does not specify which individual decisions Jev makes or how its probabilities are consumed in code.
Primitives:choicescorenoul
Technique worth stealing
Persistent human-in-the-loop answering: submit, exit, answer at a decision desk, then retrieve results by the same caller.
Try it
Download the v0.12.0 prerelease for Windows/Android, or run the Rust daemon and UI from source.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectnot found in the excerpt0.05
- Shows a System One patternFound in material0.75
- Describes handling uncertaintyFound in material0.63
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.04
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.83 / 2
- About JevFound in material0.94
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 30 Oct 2026.