Skip to content
agentboards
Browse sections All boards
Compare/KIT vs Kon

KITvsKon

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

KIT
Mark3 Labs · Terminal agent
#36OSSMCP
Panel
6.8
3 spec wins
Reliability
6.3
Usefulness
6.7
Cost
8.3
Longevity
5.8

“KIT stands for Knowledge Inference Tool, which is what you name something when the good acronym was taken.”

Kon
0xku · Terminal agent
#86OSS
Panel
6.8
2 spec wins
Reliability
6.3
Usefulness
6.3
Cost
9.0
Longevity
5.3

“It ships themes, in a tool whose entire argument is that it refuses to waste tokens on anything decorative.”

Spec by spec

SpecKITKon
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linuxmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlNoYesOptional web_search and web_fetch tools are enabled with --extra-tools; there is no driven browser.
Sandboxed executionNoNo
Multi-agent orchestrationYesNo
Headless / CI modeYesYes"kon -p" runs one prompt non-interactively with tools auto-approved and returns documented exit codes.
Models
BackboneAnthropic, OpenAI, Google Gemini, Ollama, Azure OpenAI, AWS Bedrock, OpenRouterOpenAI, OpenAI Codex, GitHub Copilot, Azure AI Foundry, DeepSeek, xAI, Zhipu
Bring your own modelYesYes
Local modelsYesYesAny OpenAI- or Anthropic-compatible local endpoint works, with auth checks relaxable through --openai-compat-auth none.
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITMIT
GitHub stars156356

Which one would each critic pick

CriticKITKonPick
El Juez——not enough reviews
El Amigo7.07.3Kon — Pick it if you resume yesterday's work more often than you start something new; pick a heavier agent when you want it to hold more of the project.
El Crítico6.36.0KIT — Sub-agents are markdown presets and their only boundary is a per-agent tool allowlist, which is a text file standing between a generated instruction and a built-in shell.
El Profesor7.07.8Kon — The core prompt is stated at under 270 tokens and the whole fixed harness at about 1,000, which is an accounting almost nobody in this category publishes.
La Inversora6.36.0KIT — 128 stars, permissive licence, no company and nothing to charge for, from a lab whose reputation was built giving away protocol plumbing rather than selling products.
La Jefa6.35.8KIT — It scaffolds a GitHub Actions workflow that reviews pull requests on a comment, and it has a non-interactive JSON mode, which is the first thing here I can put on a dashboard.
El Hacker8.07.8KIT — MIT, and custom tools, commands and widgets are written in Go and compiled in. It runs as an ACP agent over stdio, and Ollama is a first-class provider.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Turn this comparison into a practical check

Give KIT and Kon the same small task. Keep a personal record of the tests, time and actual cost, then return to it from the homepage.

Open a test workspace for these agents →
Loading agent listings… Models and guides are ready.
↑↓ navigate · Enter open · Esc closeModels & guides