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
chakuho is a Python HTTP server that answers typed decision questions (choice, noul/boolean, score) by reading a local OpenAI-compatible LLM's next-token distribution, returning calibrated probabilities instead of generated text. It targets developers who want Jev-style System One decisions using an already-running general instruct model.
How it uses Jev
The caller declares a state and questions with enumerated options. chakuho labels options A–Z/a–z, builds a prompt ending in "Label:", and either samples n=16 one-token completions (default) or reads one logprobs pass, then aggregates and normalizes probabilities over the declared labels. Results are returned as choice/probabilities, noul probability, or normalized score, with coverage and degraded flags.
Primitives:choicescorenoul
Technique worth stealing
Map enumerated options to single-token labels and read the LLM's next-token distribution, aggregating label mass into a probability distribution.
Try it
uv sync && uv run chakuho serve --port 9750, 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 projectFound in material0.91
- Shows a System One patternunclear0.58
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelFound in material0.91
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 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 20 Oct 2026.