Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A self-hosted implementation of TypeSafe's System One API, serving typed, calibrated decisions instead of text. Wire-compatible with the official TypeSafe SDKs, n8n node, jevgrep and pg-jev. Defaults to the Clef-Flash decision model, with an optional generative reader for long states and extraction.
How it uses Jev
Clients POST state plus typed questions (noul, choice, score) to /v1/systemone. e-jev routes each question to a backend in the fleet (Clef by default, or a vLLM/OpenAI-logprob reader), renormalizes option scores, and returns calibrated probabilities per (backend, question kind). Failures fall down the configured rows; capacity returns 429/529.
Primitives:choicescorenoul
Technique worth stealing
Route each question kind across a backend fleet by shape and reachability, calibrating thresholds per (backend, kind) rather than transferring them.
Try it
docker run -d -p 45160:45160 ghcr.io/damvolkov/e-jev:latest, then curl /v1/systemone with a state and questions.
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 material0.91
- Shows a System One patternnot found in the excerpt0.07
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersFound in material0.78
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.54
- Is a replica of the modelFound in material0.69
- Solves a common problem (0–2)score on a 0–2 scale1.34 / 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 28 Oct 2026.