Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A bot that plays NetHack 5.0 using TypeSafe's Jev systemone model. It reads the terminal screen, lists legal moves, and lets Jev choose one. For researchers and hobbyists exploring non-LLM game agents.
How it uses Jev
Each turn, code reads the game screen and builds a list of legal options (attack, explore, eat, pray, descend, kick, dig). Jev receives this list as a choice question and returns a probability for each option. The motor then sends the keystrokes for the selected option.
Primitives:choice
Technique worth stealing
Constrain the model to a list of legal actions and let it pick one, avoiding free-form text generation.
Try it
Run scripts/build-nethack.sh, set JEV_API_KEY in .env, then .venv/bin/python -m jev.server
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 material0.95
- Shows a System One patternFound in material0.63
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolunclear0.44
- Top-10 learning shortlist signalunclear0.55
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 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 3 Oct 2026.