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
A local HTTP MCP tool for agents using Hermes: the agent gathers its own evidence, defines named questions, and receives structured JEV judgments via OpenRouter. Standalone public version of the workflow, not a live multi-agent installation.
How it uses Jev
The agent defines named questions in noul, choice, or score modes (mixable in one evaluate call) over state it supplies. The broker validates input, logs attempt metadata, calls TypeSafe JEV through OpenRouter, and returns structured judgments; the agent must then check the original evidence and decide itself.
Primitives:choicescorenoul
Technique worth stealing
Broker holds the OpenRouter key; each permitted Hermes profile gets its own revocable bearer token, keeping credentials out of agent configs.
Try it
Clone repo, run go test and python3 scripts/setup.py --profile assistant, then python3 scripts/run.py.
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 projectFound in material0.94
- Shows a System One patternFound in material0.82
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.88
- Top-10 learning shortlist signalunclear0.44
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.99
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.