Automated README summary
Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
quackd is a Python command-line tool for connecting and commanding multiple robots from one place. Each robot registers through an adapter manifest declaring its body and skills; an LLM pilot picks skills toward a goal, and flocks divide work by messaging each other.
How it uses Jev
Jev is an optional decision LLM placed in front of the pilot via --decision-llm. It generates no text; it scores a fixed set of permitted discrete calls against a state and returns a choice with probabilities, answering turns that are a choice among calls the robot already has. Off unless named; --decision-mode shadow records choices without acting.
Primitives:choicescore
Technique worth stealing
Put a non-generative decision model in front of an LLM pilot to pick among permitted calls, while the LLM still writes poses and prose and the executor enforces safety gates.
Try it
Run quackd run --goal "..." with a registered robot; add --decision-llm to enable Jev, or --decision-mode shadow to record only.
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 projectnot found in the excerpt0.02
- Shows a System One patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.13
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.08
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale0.93 / 2
- About JevFound in material0.75
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 26 Oct 2026.