Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
kime is a Rust inference engine and HTTP server that answers typed questions about text (choice, score, yes/no) with calibrated probabilities. It targets developers building classification, routing, or agent-decision systems who want Jev/Laya compatibility.
How it uses Jev
kime speaks Jev's wire format and covers every Jev feature. The server accepts a state plus typed questions (choice, score, noul) and returns calibrated probabilities per answer; Jev's API works unchanged against kime. Native kime models are still to come; today it runs Laya checkpoints.
Primitives:choicescorenoul
Technique worth stealing
Encode the state once, cache its keys and values, and answer each question with a small cross-attention tower; options are permutation equivariant by construction.
Try it
cargo build --release; kime pull laya; kime serve --port 8000, then POST to /v1/systemone.
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 projectunclear0.45
- Shows a System One patternFound in material0.74
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.89
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelFound in material0.93
- Solves a common problem (0–2)score on a 0–2 scale1.51 / 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 Oct 2026.