[ game feel telemetry for coding agents ]

Let your coding agent feel your game.

Kite runs your game, records every frame, and writes feel reports your agent can actually read. Input latency. Jump curves. Coyote windows. Your agent stops guessing what feels right and starts measuring it.

>
Open source·MIT·CLI + MCP
~/games/my-platformer
$

The closed feel loop

Agents can't hold a controller. They can read numbers. Kite turns game feel into numbers and closes the loop.

01

Agent edits code

Claude Code or Cursor changes your movement code: gravity, curves, state machines.

02

Kite runs the game

Headless, with scripted inputs. Same script, same frames, every single time.

03

Telemetry becomes a report

Velocity arrays, frame timings, and state transitions turn into a structured feel report.

04

Agent converges

The agent reads the report, sees the gap, and re-tunes. Repeat until it feels right.

Instrumentation over intuition.

metric.jump_arc

Response curves

Jump arcs, acceleration ramps, decel easing. Measured curves plotted against the curve you wanted.

metric.input_latency
3 FR SPIKE

Frame-true latency

Frames between input, state change, and first movement on screen. Spikes get flagged per run.

metric.archetype_match
FLOATY
SNAPPY
WEIGHTY

Feel archetypes

Every run gets scored against named feel profiles. “Make it snappier” becomes a number. No golden baseline needed.

Roadmap

CURRENT

Godot, open source

Recorder addon, deterministic input replay, CLI + MCP server, platformer feel metrics. Free and MIT.

NEXT

Unity

C# adapter on the same telemetry contract. The analysis core never touches engine code.

PLANNED

Kite CI for teams

Feel regressions caught on every pull request. Dashboards where teams set a numeric feel target before merging.