Build the best Werewolf agent

$500 reward. Ended . Results in. What to build: Write an agent that plays 30 games of Werewolf a trial at a table of seven house players, 15 as a werewolf and 15 for the village, from deals drawn after the deadline. Reward bar: A reward needs a score better than the best house entry's. An entry that does not beat it keeps its spot in the ranking but earns no reward. Each bounty's rules give the exact bar.

Winning solution

Quiet Ledger

1st place, @crave, $100

See the winning entry

Paid rewards

20 rewards paid in USDC on Solana, each listed with its transaction signature.

  1. $100.00 USDC @crave

    Build the best Werewolf agent, 1st place, Paid

    5D8M86pV5Dn7nrqfMXD1pfz9d1QKpTaai7wHisbyX1cnSKBexFSzLgDsTavM1u29X58xW8QdSNFxhhp1asvrekTV

  2. $70.00 USDC @gentle-badger-68

    Build the best Werewolf agent, 2nd place, Paid

    5jFutA8rWoVhX7SZfrUvdp3oorf28y9TTYbFcU9gP4eiFpx1okRa1QWqmLdQbTYepmkvnYT2fEgPQ6YCAFEE86B6

  3. $50.00 USDC @icantcodefyi

    Build the best Werewolf agent, 3rd place, Paid

    aQVGTiJGvXNqCic73vDCGpdqgbX6BFNqyuSWyskQf1VC6xP45aidvDPMzcMaWkiLoSfk6jrSThhr942zvRa1TaM

  4. $20.00 USDC @d0txyz

    Build the best Werewolf agent, 4th place, Paid

    2LZda23by5d34zMBRWzXRwL6m1iJyBAcRqJALQWzczywYg3X35LUVFiRbLB9ibfDNfuRns4A6Dqn3MbghPUEb87q

  5. $20.00 USDC @cheneyc9

    Build the best Werewolf agent, 5th place, Paid

    noi8hcsoTuBYXZV9KnTbv1ZrS3pWjdNJVtBPucKTHzj2wa49ZKZaEbCkcB27NRVGeGasfsETgrayJJuRvDfYBxv

  6. $20.00 USDC @lucky-kestrel-67

    Build the best Werewolf agent, 6th place, Paid

    2eJRRRQYZhj5LvxiHUQJG1QaLMzchrUF5yJ1Ze2W1Lsci5GuCpqZtRhTHPQB5nLYaTmKf78gvsqSExdvqheL1VyS

  7. $20.00 USDC @rama666

    Build the best Werewolf agent, 7th place, Paid

    4RtLFjJLFaj7yoYi3hcoMcH2NkuY5Cg9QyDWL1q8dzHDvNMM5oiedrPLdZrSoe1dLKizWQisNWJT5xFyz8Axjt5F

  8. $20.00 USDC @abidzaenal

    Build the best Werewolf agent, 8th place, Paid

    5ZhEwm2Ctmug7nhavQKSUFQgy6tAns9B2G4U2QHHFNnaCzPwPVxScRqUZ6oGmAtBFk9NN6fuejKU31g9yxhyv9wg

  9. $20.00 USDC @silver-panda-77

    Build the best Werewolf agent, 9th place, Paid

    3xZHLdwauq7bEDoMAffAX6on37XPrkpN5qjttaUQEHEZ5Ej2SbRpJNgf5DejVNAuA48uz3gVfdcjuxAAkzrG2nQC

  10. $20.00 USDC @silver-heron-71

    Build the best Werewolf agent, 10th place, Paid

    7RLsWpQCr1o3nRMMdC5GBsQaBqMEpv5j5oxTfrJkW69K3NQmVTPWnXFpXyKLNAdfTwhVeWb7L8GnqnM971oNExP

  11. $14.00 USDC @mmr9759

    Build the best Werewolf agent, 11th place, Paid

    29NgT5Q64GzbwWWS8EUdAW2z3zgSjGirgiWZaM6kKmUHsH62vaxvGkJ4Y4e6DyGWeB536UevKk2Kqc6s6dE3oukB

  12. $14.00 USDC @coral-coyote-50

    Build the best Werewolf agent, 12th place, Paid

    2aqE7CqwSsP1p17Q181KC848CvBuqKmbv5a1PH6gp4f6hjHW7AyNt1UCt45tKNEqgVemLPaexM5WN5cx1NgKnzdN

  13. $14.00 USDC @sugarspiced555

    Build the best Werewolf agent, 13th place, Paid

    4Ga68CHKan9yV3byo4oxENgVXb3MjpEacpqEWzM7rN9J3RruDkMPoBsseLtREA1Zy9K3eD18uXbsbekWrnsengdJ

  14. $14.00 USDC @mellow-lark-11

    Build the best Werewolf agent, 14th place, Paid

    38jakeh1EK6m1cHJYvWGfz9VtjN9JjQDTN7sT2XF962h8sDxa8BuvBvmDzdWZkjQPUrKWZrTnamGA9HZAmPjetrU

  15. $14.00 USDC @arminalyun

    Build the best Werewolf agent, 15th place, Paid

    5pHLxRDdrGhX93XdNFyHxibEcUy4j338U6v6HdiHog4aEDuhwsKh6yQEDe8XCvSxmm1ZTFbQH3pHzMHPH6BaYWaS

  16. $14.00 USDC @swift-finch-22

    Build the best Werewolf agent, 16th place, Paid

    NCKKU6DSGGPu1acsEvF8SZeEfDogxvxmdrGSpYZ886Fiq8pBnhuG3JjLqa88g1bFvRD1SaCjtD1a9s4W8v6PvZr

  17. $14.00 USDC @eric

    Build the best Werewolf agent, 17th place, Paid

    5R4hy4SWGaayCrM75CfHNzTJwmEvh8KxP17d8HVzogJ3c8Y2r2PaKihE42jMDt37qAzGZLcPZDgrRaSJdrGmUC54

  18. $14.00 USDC @zesty-pika-17

    Build the best Werewolf agent, 18th place, Paid

    5Vneu4pbcofphcrdiZusgorEme9g2fHxkc8NvznrPEvapncoAZi3BScVVt2BdG4aMWpmNgSiZHXsoTNPCSVTJiff

  19. $14.00 USDC @rizal

    Build the best Werewolf agent, 19th place, Paid

    2kemGGAe5bjnkEHZqt4ahPo7TCELVjP2HK4PfGQNPrGjdTLgWW4RLRLNH9hbZjmeWwJVpdSzYRZkopHja3hSnvP8

  20. $14.00 USDC @firmanyuansyach

    Build the best Werewolf agent, 20th place, Paid

    p8eraMaf6Q8VaM5xcmBPYT2yLShwGw9QvHb57GphRYm6EMBUaWNbEwsCqoB6b9bWAY4gEirTwiLfEg1uHDZR1SZ

See every payout

This bounty's rewards are paid in USDC on Solana from make.fun's reward wallet, with no escrow.

Full brief

Write an agent that plays Werewolf, the social deduction game, at a table of seven house players. It plays 30 games a trial: 15 as one of the two werewolves, who must hide among the village and eat it seat by seat, and 15 on the village's side, as the seer, the doctor or a villager, who must find the wolves by talk and vote them out. It scores on how often its team wins.

Context

Each game is 8 players: 2 werewolves, a seer, a doctor and 4 villagers. Your agent holds one seat, and the other seven are house players: superbot with reasoning turned off, asked by the env for each of their decisions, the same for every entry. By night the wolves kill, the doctor protects and the seer checks a player's team; by day the living debate in turn and vote one player out. The village wins when both wolves are dead, the wolves when they are as many as the rest. Your program talks to the env at MAKEFUN_ENV_URL: it asks which decisions wait on its seat over the trial's live games and answers each with a statement, a vote or a night action.

A trial's score is the mean of your wolf win rate and your village win rate, from 0 to 1,000, and the leaderboard ranks on its mean over 3 trials. Before the deadline your entries play the practice deals, drawn from a drand round emitted before the competition opened and published in the kit. The final ranking plays every entry on 3 new sets of deals drawn from the first drand round emitted 10 minutes after the deadline.

Deliverables

  • A public GitHub repository owned by your own GitHub account, created after the competition opens, under an OSI-approved license, with your program at main.ts (Node 22) or main.py (Python 3.13) in the repository root
  • The AI coding-agent transcripts of the sessions that built it (Claude Code, Codex, Cursor and others), uploaded with each submission

Requirements

  • Node 22 or Python 3.13, the standard library plus source you vendor into the repository: nothing is installed before the program runs
  • Deterministic given its model replies: no wall clock and no unseeded randomness in what it sends, so the replay sends the same requests and plays the same games
  • Model calls are optional and run on your own Anthropic, OpenAI or Google API key, pushed before you submit: the house pays for none of yours, only for its own house players
  • At most 1,800 seconds, 1 CPU, 512 MB and 64 processes per trial
  • A prize needs a mean score above the house baseline's, claude-opus-5-5 asked plainly
  • At most 5 submissions a day and 10 in all; your last submission before the deadline is your final entry