Skip to content
ProductArena

How kitty’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score13/100

Agent-ready 28.1 × 0.30 = 8.43

API quality 0.0 × 0.20 = 0.00

Openness 17.4 × 0.20 = 3.48

Built-in AI 0.0 × 0.15 = 0.00

Automation 7.5 × 0.15 = 1.13

(8.43 + 0.00 + 3.48 + 0.00 + 1.13) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 13.04 ÷ 1.00 = 13.0

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready28.1/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://sw.kovidgoyal.net/llms.txt“PROBE llms.txt: HTTP 404 at https://sw.kovidgoyal.net/llms.txt”
  • [probe] https://sw.kovidgoyal.net/kitty/overview/.md“PROBE docs-md: HTTP 404 at https://sw.kovidgoyal.net/kitty/overview/.md”
  • [probe] https://sw.kovidgoyal.net/openapi.json“PROBE openapi: all candidate paths 404 (https://sw.kovidgoyal.net/openapi.json, https://sw.kovidgoyal.net/swagger.json, https://sw.kovidgoyal.net/api/openapi.json, https://sw.kovidgoyal.net/.well-known/openapi.json)”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“official CLI documented at https://sw.kovidgoyal.net/kitty/remote-control/”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Use an official CLIweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“official CLI documented at https://sw.kovidgoyal.net/kitty/remote-control/”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“official CLI documented at https://sw.kovidgoyal.net/kitty/remote-control/”
  • [probe] https://sw.kovidgoyal.net/openapi.json“PROBE openapi: all candidate paths 404 (https://sw.kovidgoyal.net/openapi.json, https://sw.kovidgoyal.net/swagger.json, https://sw.kovidgoyal.net/api/openapi.json, https://sw.kovidgoyal.net/.well-known/openapi.json)”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 53.4 ÷ 190 × 100 = 28.1

API quality0.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://sw.kovidgoyal.net/llms.txt“PROBE llms.txt: HTTP 404 at https://sw.kovidgoyal.net/llms.txt”
  • [probe] https://sw.kovidgoyal.net/openapi.json“PROBE openapi: all candidate paths 404 (https://sw.kovidgoyal.net/openapi.json, https://sw.kovidgoyal.net/swagger.json, https://sw.kovidgoyal.net/api/openapi.json, https://sw.kovidgoyal.net/.well-known/openapi.json)”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://sw.kovidgoyal.net/llms.txt“PROBE llms.txt: HTTP 404 at https://sw.kovidgoyal.net/llms.txt”
  • [probe] https://sw.kovidgoyal.net/kitty/overview/.md“PROBE docs-md: HTTP 404 at https://sw.kovidgoyal.net/kitty/overview/.md”
  • [probe] https://sw.kovidgoyal.net/openapi.json“PROBE openapi: all candidate paths 404 (https://sw.kovidgoyal.net/openapi.json, https://sw.kovidgoyal.net/swagger.json, https://sw.kovidgoyal.net/api/openapi.json, https://sw.kovidgoyal.net/.well-known/openapi.json)”

Test against a sandbox environment without touching production dataweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://sw.kovidgoyal.net/openapi.json“PROBE openapi: all candidate paths 404 (https://sw.kovidgoyal.net/openapi.json, https://sw.kovidgoyal.net/swagger.json, https://sw.kovidgoyal.net/api/openapi.json, https://sw.kovidgoyal.net/.well-known/openapi.json)”
  • [probe] https://sw.kovidgoyal.net/llms.txt“PROBE llms.txt: HTTP 404 at https://sw.kovidgoyal.net/llms.txt”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/graphics-protocol/“Terminal graphics protocol”

API quality = 0.0 ÷ 60 × 100 = 0.0

Openness17.4/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/“Control it from scripts or the shell; Extend with kittens using the Python language; Use startup sessions to specify working environments; Programmable tabs, splits and multiple layouts to manage windows.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“official CLI documented at https://sw.kovidgoyal.net/kitty/remote-control/”

Export all of my data in open formats and leaveweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/conf/“kitty.conf - kitty”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/conf/“kitty.conf”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Openness = 17.4 ÷ 100 × 100 = 17.4

Built-in AI0.0/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Operate the product with natural-language commandsweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Built-in AI = 0.0 ÷ 20 × 100 = 0.0

Automation7.5/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“Control kitty from scripts”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/remote-control/“kitty can be controlled from scripts or the shell prompt. You can open new windows, send arbitrary text input to any window, change the title of windows and tabs, etc.”
  • [claimed-docs] https://sw.kovidgoyal.net/kitty/“Control it from scripts or the shell; Extend with kittens using the Python language; Use startup sessions to specify working environments; Programmable tabs, splits and multiple layouts to manage windows.”
  • [probe] https://sw.kovidgoyal.net/kitty/remote-control/“PROBE runtime (recorded 2026-09-04, kitty 0.48.2 via official installer): launched `kitty --detach -o allow_remote_control=socket-only --listen-on unix:/tmp/...`; `kitten @ ls` returned full window/tab/layout state as JSON, `kitten @ send-text "echo PA_PROBE_OK"` executed in the live window, `kitten @ get-text` read the output back, `kitten @ close-window` tore it down — complete external agent-control loop verified hands-on.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 6.0 ÷ 80 × 100 = 7.5