agentboards.org
Compare/CodeFuse IDE vs Kun

CodeFuse IDEvsKun

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

CodeFuse IDE
Ant Group · AI-native IDE
#240OSS
Panel
4.8
1 spec wins
Reliability
4.0
Usefulness
3.8
Cost
7.0
Longevity
4.5

“It is described as the desktop editor of a wider project, which is a lot of confidence for one download link.”

Kun
KunAgent · AI-native IDE
#84MCP
Panel
5.8
5 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

SpecCodeFuse IDEKun
Architecture
CategoryAI-native IDEAI-native IDE
Runslocallocal
Platformsmacos, linux, windowsmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientNoYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesAs an IDE feature; the repository does not document an autonomous agent that runs commands on its own. Yes
Multi-file editsNoYes
Git operationsNoYes
Browser controlNoYesBrowser output is attached to tasks and screenshots are captured through browser automation.
Sandboxed executionNoNo
Multi-agent orchestrationNoNo
Headless / CI modeNoNo
Models
BackboneCodeFuseOpenAI, Claude, Gemini, Ollama, DeepSeek, Kimi, GLM, Qwen, MiniMax
Bring your own modelYesYes
Local modelsYesThe IDE advertises seamless integration of various models so the endpoint is the user's choice; no hosted model is bundled. YesOllama 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 at$0/mon/a
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesNo
LicenseApache-2.0PolyForm-Noncommercial-1.0.0
GitHub stars2946,324

Which one would each critic pick

CriticCodeFuse IDEKunPick
El Juez——not enough reviews
El Amigo5.06.3Kun — 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 Crítico4.55.8Kun — Scheduled tasks, loops and background jobs run without you watching, and the row records no isolation for any of them.
El Profesor5.06.5Kun — 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 Inversora4.05.0Kun — 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 Jefa4.34.8Kun — 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 Hacker6.36.5Kun — 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.