Automated README summary
Automatically summarized from the README on 27 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-governor splits an agent loop so a decision model picks the next action while the generative model only writes. It installs into existing frameworks like LangChain, Hermes, Pydantic AI, OpenClaw, or any OpenAI-compatible loop.
How it uses Jev
On each step, Jev answers three typed questions over a bounded read-only state projection: action (choice over available tools plus finish/clarify/delegate), goal_met (noul), and risk (choice low/medium/high). Seven ordered guards then route the result to a static tool, constrained tool arguments, final response, clarification, risk stop, or delegation.
Primitives:choicenoul
Technique worth stealing
Ask action and goal_met as separate typed questions in one request so the model cannot be its own witness that work is done.
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 projectunclear0.55
- Shows a System One patternunclear0.47
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.12
- Is a replica of the modelnot found in the excerpt0.16
- Solves a common problem (0–2)score on a 0–2 scale1.95 / 2
- About JevFound in material0.91
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 27 Oct 2026.