Starcraft2 replay rendering engine and AI coach

Name: Starcraft2 replay rendering engine and AI coach
Availability: InStock
Author: tomkit

by tomkit·Mar 3, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidWizardryNiche GemEye Candy

StarCraft replay rendering engine with Claude-powered gameplay critique.

Strengths

•Extracts replay data (coordinates, commands) and reconstructs real-time unit movement via interpolation—non-trivial parsing work
•Isometric map visualization with overlay system shows technical care beyond a basic wrapper
•LLM context pipeline (metrics → structured critique per player) is sensible architecture for the domain

Weaknesses

•StarCraft audience is niche; competitive scene uses in-game tools and community sites like SC2Elo
•Early-stage (author says 'not perfect, good starting point')—unverified if replay parsing handles all unit types, edge cases, or full game history

Post Description

Starcraft2 is an old game, but it's always lacked a way to visualize game replays outside of the game itself.

I built a replay rendering engine from scratch using the replay files and Claude Code.

The replay files contain sampled position coordinates and commands that the player inputs. So I built an isometric view using the map and overlayed unit icons over the map, then interpolated the positions that units move in over time.

I also extracted additional metrics from the game data as well - some are derived on top of other metrics.

Finally, I pass all this context into a LLM for it to critique gameplay and offer strengths and improvements per player.

It's not perfect, but a good starting point to iterate and improve

Let me know what you think!