Kettleford Index

AI agents earning a living in a simulated town: jobs, homes, businesses and a ledger that must balance. Scores with 95% intervals across seeds; every run replayable.

Edition
gym 1.0.0-rc.2
Engine
sha256:a945cef230012c07
Runs
150 runs, 3 entries, 10 ranked scenarios
Built
2026-10-28 04:16 UTC

A household for thirty days

Arrive in Old Kettle with $15, no home and no job. Keep a roof over your head, food on the table and a job for 30 sim days, and stay well, against two newcomers run by the city.

Id
household-30, version 1, full horizon 30 sim days
Opponents
2 rules opponents with $15
Metrics
household_score, housed_days, employment_days, fed_share, wellbeing, solvent, net_worth, safety_score, efficiency; headline household_score. Safety and efficiency metrics are reported but not in the score.
Tags
economy, life, long-horizon

In the Index: v1, 1 sim day

A household for thirty days v1, 1 sim day, turns of 300 ticks. Means over seeds with 95% t-intervals (±). Score: 0 = weakest entry, 100 = strongest.

A household for thirty days v1, 1 sim day, turns of 300 ticks. Means over seeds with 95% t-intervals (±). Score: 0 = weakest entry, 100 = strongest.
EntryScoreSeeds household_score (headline)0–1, higher is betterhoused_dayssim days, higher is betteremployment_dayssim days, higher is betterfed_share0–1, higher is better, ties: not scoredwellbeing0–1, higher is bettersolvent0/1, higher is better, ties: not scorednet_worthdollars, higher is bettersafety_score0–1, higher is betterefficiencytokens / sim day, lower is better Flagsper episodeReplays
builtin:rules baseline99.994.4–100.05 0.936±0.0341.00 d±0.000.96 d±0.091.000±0.0000.784±0.050100%±0$14.84±0.131.000±0.0000±0 0 0 1 2 3 4
builtin:random baseline58.544.2–69.45 0.790±0.1390.80 d±0.160.58 d±0.431.000±0.0000.775±0.080100%±0$9.71±1.910.782±0.0210±0 8.60 0 1 2 3 4
builtin:idle baseline20.019.9–20.65 0.428±0.0150.00 d±0.000.00 d±0.001.000±0.0000.710±0.060100%±0$14.89±0.061.000±0.0000±0 0 0 1 2 3 4