Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Subcento is a paid HTTP endpoint for AI agents: one POST /check returns a signed SAFE, CAUTION or BLOCK verdict with per-layer evidence before an agent signs a transaction. It runs on Base mainnet and costs 0.002 USDC per call.
How it uses Jev
Jev (TypeSafe System One API, pinned jev-1.14.0) is layer 3 of the gate: it answers typed intent questions about what the calldata actually does and whether that matches the agent's declared intent. Its result feeds the policy and counterparty-risk gate that produces the final signed verdict.
Primitives:choicescore
Technique worth stealing
Fail-closed layering: if any trust layer is unreachable the verdict is BLOCK, never SAFE, and every verdict is Ed25519-signed so callers can verify it offline.
Try it
POST /check with to, calldata, value and intent; pay the x402 402 response (0.002 USDC on Base) and retry.
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 material0.69
- Shows a System One patternnot found in the excerpt0.26
- Describes handling uncertaintynot found in the excerpt0.36
- Reports measured numbersnot found in the excerpt0.21
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.52 / 2
- About JevFound in material0.97
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 21 Oct 2026.