EVO by Alatic
Visits —
MINECRAFT COMBAT AI

EVO. Built through experience.

A learning agent that uses recorded fights to improve movement, attacks and camera control. Explore the published results and how the project works.

Performance

Snapshot · 2026-11-09

Recorded fights against real players on public servers, across model versions. This is not a current-model benchmark.

Showing the latest saved sync · 2026-11-09

Fight win rate

57.1%

848 wins out of 1,484 fights

Win–loss ratio

1.33

848 wins / 636 losses

Recorded fights

1,484

Valid, confirmed combat outcomes

Rejected records and walkovers are excluded. Only aggregate results are public; player identities, recordings and model files remain private.

Recent candidates

View all candidates →Latest saved sync · 2026-11-09

The five latest candidates, oldest to newest. Results belong to the exact model that played each fight.

ModelStatusDetected?Focus / goalReal-player fightsRecordWin rateW/LLocal arena
Beta 6 · Candidate 4Retired✕Improve prediction227152 W / 75 L67.0%2.03No arena results
Beta 6 · Candidate 5Retired✓Improve movement432301 W / 131 L69.7%2.30No arena results
Beta 6 · Candidate 6Retired✕Camera and accuracy18993 W / 96 L49.2%0.97No arena results
Beta 6 · Candidate 7Retired✕Reward-driven combat without script assists14164 W / 77 L45.4%0.83No arena results
Beta 6 · Candidate 8Current✕Not specified0No real-player fight results——No arena results

Focus / goal describes the intended objective, not a guaranteed outcome. Detection refers to Minemen Club: ✓ detected, ✕ not detected. Current is the model selected for use. Retired models were promoted or used in real-player fights. Abandoned models never reached that stage; local-arena tests alone do not count. Statuses reflect the latest sync and remain visible when updates pause. Only qualifying recorded fights count. Local-arena results are shown separately and do not inflate real-player fight totals. Models with no results in a category have no measured win rate.

Latest video

Development footage

Watch EVO in action, with the version behind each clip.

BETA 6 · CANDIDATES 5 & 6

EVO in action

Gameplay from Beta 6, Candidates 5 & 6.

Watch on TikTok ↗

View all videos →

About the project

EVO is an independent learning agent for Minecraft combat. It observes the fight and uses a trained policy to choose movement, attacks and camera actions.

The current pipeline combines demonstrations, opponent observations and reward-weighted offline learning. Updates are trained offline from recorded experience. Reinforcement learning from the agent’s own actions remains a research goal.

How EVO learns

01 / OBSERVE

Record the fight

The agent reads movement, spacing and combat context. A learned policy chooses its next action, while the recorder captures what happened.

02 / LEARN

Train a candidate

Recorded fights are checked for quality. Outcomes and performance signals weight the experience used to train candidates offline.

03 / EVALUATE

Review the results

Candidates are compared with their parent model and tested in controlled play. A new model reaches production only after review.