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
DGP is an open-source protocol by Numerous ApS for building decision-based AI agents. Applications expose evidence, typed decisions, and guarded actions; an agent assesses choices while application code retains control of permissions and effects.
How it uses Jev
Jev is the intended first assessor. The agent reads an immutable frame of evidence and offered decisions, then produces a typed assessment using Jev or another eligible assessor. The application checks state and authorization before committing, then returns a receipt and next frame.
Primitives:choicescorenoul
Technique worth stealing
Immutable evidence frames with typed assessments and application-guarded commits keep permissions and effects under application control.
Try it
Clone repo, run local mock demo with uv, open browser, paste token, connect.
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 material0.76
- Shows a System One patternunclear0.59
- Describes handling uncertaintynot found in the excerpt0.10
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.70
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 2
- About JevFound in material0.95
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.