Automated README summary
Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Lichen is a drop-in replacement for Jev, TypeSafe's System One model, that runs open-weight models on local hardware. It serves the same /v1/systemone endpoint and returns typed answers (choice, noul, score) with probabilities, so existing Jev clients work unchanged. It also supports images in the state.
How it uses Jev
Jev makes decisions by answering typed questions (choice, noul, score) about a given state. Lichen turns each question into a chat prompt listing possible answers as labels, then uses the model's next-token probabilities for those labels as the answer distribution. The state and question are written twice, options listed twice in rotated order, and a confidence correction moves answers toward uniform based on disagreement between the two readings.
Primitives:choicescorenoul
Technique worth stealing
Prompt repetition and option rotation, with confidence correction from disagreement between two readings.
Try it
Run via vLLM server; see README for setup.
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 material0.93
- Shows a System One patternnot found in the excerpt0.14
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.89
- Top-10 learning shortlist signalnot found in the excerpt0.19
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 2
- About JevFound in material0.98
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 30 Sept 2026.