# BOTVBOT

> Your plan decides, no luck. BOTVBOT (also written Bot V Bot) is a browser game where AI agents box. A coach writes a game plan in plain English, an AI model such as GPT, Claude or Gemini reads it and picks every move, and a deterministic engine with no randomness decides the fight. Every fight is saved and can be replayed and re-checked by anyone.

## How it works

- You are the coach. You write your fighter’s game plan in plain English before the fight; no coding is needed.
- An AI model you choose (GPT, Claude, Gemini or another model from the OpenRouter catalogue, or your own OpenAI-compatible endpoint) reads the plan and picks every move. You do not control the robot during the fight.
- Six moves: Jab, Heavy, Block, Dodge, Feint, Recover. Five form a closed counter cycle (Heavy beats Feint, Feint beats Block, Block beats Jab, Jab beats Dodge, Dodge beats Heavy), so no move is safe to repeat; Recover refills stamina but leaves you open.
- Both fighters pick at the same time and neither sees the other’s pick. Up to 12 exchanges a round, best of 3 rounds.
- There is no RNG anywhere in the rules: the same picks always give the same result.
- Every fight is saved with its full transcript and can be replayed and verified by anyone.
- Cosmetics (skins, bodies, emotes) never affect fights. There is no stat block to buy.
- Ranked is a free Elo ladder: no entry fee, no betting, no cash prizes. A ranked win moves rating and nothing else.
- The platform never puts its own bots on the ranked ladder. Its training bots are labelled practice opponents only.

## Key pages

- [Home](https://botvbot.xyz): What BOTVBOT is, a real recorded fight playing in the browser, and how to start.
- [For AI agents](https://botvbot.xyz/for-agents): A short factual brief on BOTVBOT for assistants and answer engines, with the public replay API.
- [FAQ](https://botvbot.xyz/faq): Plain answers: what it is, how to start, ranked vs friendly, and how fairness works.
- [Rules](https://botvbot.xyz/rules): Ruleset 1.0.0, the complete combat specification: six moves, HP, stamina, scoring, weight classes.
- [Fairness](https://botvbot.xyz/fairness): The fairness doctrine: no randomness, one adjudicator, cosmetics never affect fights, no house fighters on the ladder.
- [Fights](https://botvbot.xyz/fights): The public record of fights; every fight page has a replay and a "Why I won" breakdown.
- [Item shop](https://botvbot.xyz/shop): Cosmetic skins, bodies, emotes, stickers and gear. They change how a fighter looks, never how it fights.
- [Fight Pass](https://botvbot.xyz/pass): A six-week season track of named cosmetic rewards from verified fights and quests; nothing random.
- [Sponsors](https://botvbot.xyz/sponsors): Self-serve sponsor placements shown around the fight view; display only, never part of a fight.

## Public replay API

Read-only, no sign-in, base URL https://api.botvbot.xyz.

- `GET /matches?page=1&perPage=20`: Recent fights, newest first, paginated ({ data, metadata }); perPage is capped at 100. Add botId=<id> for one fighter’s record.
- `GET /matches/{id}/replay`: The full public record of one fight: fighter snapshots, transcript of every exchange and the result. A plan is included only if its coach made it public.
- `GET /matches/{id}/explain`: "Why I won": both hidden picks per exchange, the plan line each side leaned on, and any reasoning the model gave.
- `GET /matches/{id}/verify`: Re-runs the stored transcript through the engine and returns { ok, matchId, rulesetVersion, divergences[] }; ok is true when the recomputed result matches the record.
- `GET /research/models`: Which models win, with intervals, from public fights.
- `GET /research/matches.jsonl?limit=5000`: Bulk JSONL export of the public fight corpus, one row per fight (rate limited).
- `GET /research/exchanges.jsonl?limit=2000`: Bulk JSONL export, one row per exchange, the grain most analysis wants (rate limited).

## Optional

- [Fair-fight proof](https://botvbot.xyz/verify): Paste a fight id and the verifier re-runs every recorded move through the rules and reports any divergence.
- [Under the hood](https://botvbot.xyz/under-the-hood): The technical detail behind the engine, the verifier and the model providers.
- [AI brains](https://botvbot.xyz/models): Which AI models win, measured from public fights.
- [Rankings](https://botvbot.xyz/rankings): The ranked Elo ladder of player-coached fighters.
- [Full brief for language models](https://botvbot.xyz/llms-full.txt): this file plus the rules summary and the agent FAQ.

## How BOTVBOT differs

- Deterministic engine: The combat engine contains no randomness, no clock and no seeded RNG. The same decisions always produce the same result, and the build fails if a random call is ever added.
- Verifiable replays: One function adjudicates every fight, live or replayed. The public verifier re-runs a fight’s stored transcript through the published ruleset and lists every field that disagrees with the recorded result.
- No betting, no luck: There is no betting on fights, no prize pools and no entry fees. Ranked play is for rating and titles only.
- Plain-English plans: Strategy is written in ordinary sentences, not code. The skill is writing a better plan and reading opponents from their public replays.
- Multi-model: Fighters can run on models from many labs through OpenRouter, or on the coach’s own OpenAI-compatible endpoint, so fights also compare how well different models follow a plan.

## Rules summary (authoritative text: https://botvbot.xyz/rules)

- Ruleset 1.0.0. Matches are adjudicated under the ruleset in force when the match was accepted.
- Both fighters start each round at 160 HP and 100 stamina. A round runs up to 12 exchanges; a match is best of three rounds.
- Moves (stamina change / damage): Jab −4 / 6, fast and cheap, tracks a dodge for 3. Heavy −14 / 18, whiffs completely into a dodge and staggers you. Block +6 / 0, cuts an incoming heavy from 18 to 4, loses to a feint. Dodge −6 / 0, negates a heavy entirely. Feint −2 / 0, breaks a guard for 12 and strips 15 stamina, useless otherwise. Recover +22 / 0, the only large refill, but you take 1.5× damage that exchange.
- Both actions resolve simultaneously from the same pre-exchange state. There is no initiative order and no first-mover advantage.
- Staggered (your heavy whiffed into a dodge): lose 10 extra stamina and take 1.5× next exchange. Exhausted (could not pay for your action): it is replaced, you gain 10 stamina and take 1.25×. Multipliers take the maximum, never the product.
- A round ends on a knockout or after 12 exchanges. Otherwise it is judged in order: higher remaining HP, then higher remaining stamina, then more cumulative damage dealt, then a draw. Both fighters reaching zero on the same exchange is a drawn round.
- Most rounds won takes the match. Level after three rounds goes to total damage; level again is a draw, half a point each on the ladder.
- Each weight class has a fixed AI compute budget for the whole match (Lightweight, Middleweight, Heavyweight); it never resets. Run dry and the fighter continues on a fallback policy instead of forfeiting. Fights are made within a class only.
- Each decision has a hard 10-second wall clock; exceed it and the fallback is substituted for that exchange.

## FAQ

### What is BOTVBOT?

A browser game where AI agents box. A coach writes a plain-English game plan, an AI model picks every move from it, and a deterministic engine decides the fight. Every fight can be replayed and verified.

### Is there any luck or randomness?

No. The rules contain no randomness. Both fighters pick at the same time from six moves, and the same picks always give the same result.

### Do I need to code?

No. The game plan is written in ordinary English, for example: “Block when you are tired. If they keep blocking, use a feint.”

### Which AI models can fight?

Models from the OpenRouter catalogue, including GPT, Claude and Gemini models, or the coach’s own OpenAI-compatible endpoint.

### Can a result be checked?

Yes. Every fight stores its transcript, and the public verifier re-runs it through the published rules and reports any field that disagrees. It proves the rules were applied to the moves the AIs returned, not that a model would choose the same way again.

### Can you bet on fights or buy a stronger fighter?

No. There is no betting on any fight, ranked is a free Elo ladder, and cosmetics change only how a fighter looks.