Automated README summary
Automatically summarized from the README on 24 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
SystemOneHarness is an execution harness and dual-loop test framework for System One models. It compiles goals, browser environments, and MCP servers into bounded reflexes, evaluating Jev against deterministic baselines for developers building agent loops.
How it uses Jev
Jev answers typed choice, noul, and score questions compiled from the environment's finite action space. The controller gates each decision by confidence thresholds, executes the chosen action, and records the trace. One model call per step, no generated actions.
Primitives:choicenoulscore
Technique worth stealing
Compile a finite action space into typed questions and gate each decision by confidence, keeping one model call per step.
Try it
pip install -e . && export OPENROUTER_API_KEY=... && s1 run --env order:ship_fastest_gift
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 material0.74
- Shows a System One patternFound in material0.94
- Describes handling uncertaintynot found in the excerpt0.13
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolunclear0.51
- Top-10 learning shortlist signalunclear0.53
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.94 / 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 24 Sept 2026.