agentboards.org
Compare/InsCode Desktop vs Kun

InsCode DesktopvsKun

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

InsCode Desktop
InsCode · AI-native IDE
#251MCP
Panel
4.0
0 spec wins
Reliability
3.8
Usefulness
5.0
Cost
4.0
Longevity
3.3

“A desktop client of about ten megabytes ships an embedded browser so you can screenshot the app it just changed.”

Kun
KunAgent · AI-native IDE
#84MCP
Panel
5.8
2 spec wins
Reliability
5.7
Usefulness
6.2
Cost
6.5
Longevity
4.8

“It writes your code and also your slide deck, which is the most accurate description of an engineering week ever shipped as a feature list.”

Spec by spec

SpecInsCode DesktopKun
Architecture
CategoryAI-native IDEAI-native IDE
Runslocallocal
Platformsmacos, windowsmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesHigh-risk commands are named as requiring tiered authorisation, and the live preview runs the project's dev, start or serve script. Yes
Multi-file editsYesYes
Git operationsNoYes
Browser controlYesAn embedded preview view renders the running app and can capture screenshots and annotated regions to send back to the agent. YesBrowser output is attached to tasks and screenshots are captured through browser automation.
Sandboxed executionNoNo
Multi-agent orchestrationNoNo
Headless / CI modeNoNo
Models
BackboneTaoToken, OpenAI-compatible endpoints, AnthropicOpenAI, Claude, Gemini, Ollama, DeepSeek, Kimi, GLM, Qwen, MiniMax
Bring your own modelYesYes
Local modelsNoYesOllama ships as a named provider preset, and base URLs are editable so any OpenAI-compatible or Anthropic-compatible endpoint can be added.
Cost
Pricing modelbyokbyok
Starts atn/an/a
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceNoNo
LicenseproprietaryPolyForm-Noncommercial-1.0.0
GitHub starsn/a6,324

Which one would each critic pick

CriticInsCode DesktopKunPick
El Juez——not enough reviews
El Amigo4.86.3Kun — Pick it if your week is half repository and half documents; pick Zed if the only thing you want an agent near is code.
El Crítico4.05.8Kun — Scheduled tasks, loops and background jobs run without you watching, and the row records no isolation for any of them.
El Profesor4.36.5Kun — The graphical client and the terminal client both attach to one local runtime, so threads, plans and approvals are shared state rather than two synchronised copies.
La Inversora4.35.0Kun — Source-available with no published price at all: the vendor has built the product and has not yet decided what it sells, which is a decision that gets made under pressure.
La Jefa3.34.8Kun — Sixty desktop installs each running their own local service, no SSO, no audit log, and no headless mode, so nothing here reaches a pipeline or a report.
El Hacker3.86.5Kun — PolyForm Noncommercial, so I can read it and never ship a competing fork, but Ollama is a named preset and every base URL is editable.

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

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.