Async IDEvsKun
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Async IDE
ZYKJShadow · AI-native IDE
#37OSSMCP
Panel
6.42 spec wins
- Reliability
- 5.7
- Usefulness
- 6.5
- Cost
- 8.2
- Longevity
- 5.3
“It bridges to Telegram, Slack, Discord and Feishu, so four separate apps can now tell you the build is broken.”
Kun
KunAgent · AI-native IDE
#84MCP
Panel
5.81 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
| Spec | Async IDE | Kun |
|---|---|---|
| Architecture | ||
| Category | AI-native IDE | AI-native IDE |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | YesBrowser automation with custom headers and fingerprint is one of the built-in tools. | YesBrowser output is attached to tasks and screenshots are captured through browser automation. |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesAgent and Team toolchains are shared with the IM bot bridge, each with its own model, workspace and allowlist config. | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Anthropic, OpenAI, Gemini, Ollama, vLLM, any OpenAI-compatible endpoint | OpenAI, Claude, Gemini, Ollama, DeepSeek, Kimi, GLM, Qwen, MiniMax |
| Bring your own model | Yes | Yes |
| Local models | Yes | 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 model | byok | byok |
| Starts at | $0/mo | n/a |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | No |
| License | Apache-2.0 | PolyForm-Noncommercial-1.0.0 |
| GitHub stars | 474 | 6,324 |
Which one would each critic pick
| Critic | Async IDE | Kun | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 6.3 | Async IDE — Pick it if you want an agent that understands symbols rather than strings; pick an established editor with an agent extension if your setup has to come with you. |
| El Crítico | 6.0 | 5.8 | Async IDE — It is an editor written from scratch on Electron and Monaco rather than forked from VS Code, so it inherits none of the extension catalogue its users already depend on. |
| El Profesor | 7.0 | 6.5 | Async IDE — The control loop is named and exposed: Think, Plan, Execute, Observe, with each stage visible and interruptible rather than collapsed into one opaque completion. |
| La Inversora | 5.8 | 5.0 | Async IDE — 477 stars and one team building an entire editor: the most capital-intensive category on this board, attempted with no capital at all. |
| La Jefa | 5.3 | 4.8 | Async IDE — The only documented install is a git clone and an npm install, which is not a rollout; it is sixty people each maintaining their own build. |
| El Hacker | 7.8 | 6.5 | Async IDE — Apache-2.0, Ollama and vLLM named directly rather than implied, MCP servers attach, and each agent carries its own model, workspace and allowlist. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.