Parse demo files, track performance trends across maps, replay rounds in 2D, and get AI-powered tactical insights — all running locally on your machine.
From high-level trends to frame-by-frame round analysis.
Full scoreboard, aim analysis, utility usage, economy timeline, side effectiveness, and behavioral radar — all from a single demo file.
Track K/D, KAST%, HLTV rating, win rate, aim score and more across matches. Filter by map to see where you excel.
Watch any round play out on the radar. Player movement, grenades with flight paths, kill lines, flash effects — all rendered in real time.
AI-detected CT/T roles per map with spider charts. See if you're an anchor, rotator, lurker, or entry fragger — backed by positional data.
No cloud. No accounts. No telemetry. Your demo files stay on your machine. Everything runs through a local Docker container or Python process.
Connect your own API key (OpenAI, Anthropic, Gemini, Mistral) and get match-specific feedback: The Good, The Bad, The Ugly.
A few glimpses of what you'll see after parsing your first demo.
Watch a demo round play out on a stylized dust2 map. Movement trails, grenades, kills — just like the full app.
Every kill broken down into counterstrafe quality, engagement speed, crosshair placement, and reaction time.
Every round told as a story — kills, utility, economy, and positioning all in one view.
Your playstyle quantified per side — aggression, trading, isolation, survival, and sniper tendencies in one radar view.
Track grenade usage per round, flash effectiveness with blind durations, and your full economy timeline.
Chat with an AI that has read your entire match. Ask about any round, positioning mistake, or tactical pattern.
Select a topic or ask anything about the match...
Run with Docker or Python. One command and the local server starts on port 8000.
Upload .dem files or point to your CS2 replays folder. Parsing is automatic.
Explore match breakdowns, track trends, replay rounds, and get AI feedback.
Free, open source, and runs entirely on your machine.
docker compose up -dIncludes everything. Mount your demos folder and go.
pip install -r requirements.txt
python api.pyRequires Python 3.11+. Direct local install.
pr1maly is a passion project built in free time. Your support helps keep it going.
Found a bug? Have a feature idea? Let me know.
Open an IssueIf pr1maly helps your game, consider buying me a coffee.