Async IDEvsCodeArts Agent
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
6.44 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.”
CodeArts Agent
Huawei Cloud · AI-native IDE
#44MCP
Panel
6.81 spec wins
- Reliability
- 7.0
- Usefulness
- 6.8
- Cost
- 5.8
- Longevity
- 7.5
“There is a HarmonyOS agent and an ArkTS-tuned model, available on the China site only, which is a very specific way to be excluded.”
Spec by spec
| Spec | Async IDE | CodeArts Agent |
|---|---|---|
| Architecture | ||
| Category | AI-native IDE | AI-native IDE |
| Runs | local | local, cloud |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | YesThe v26.5.1 release notes describe a CLI in which you run commands and a TUI in which you use natural language to complete coding tasks. |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | YesGit operations are listed among the coding tasks the CLI completes, and the IDE reviews Git commit diffs. |
| Browser control | YesBrowser automation with custom headers and fingerprint is one of the built-in tools. | No |
| 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. | YesSub-agents are created and executed automatically for task decomposition and delegation, and multiple sessions run concurrently. |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Anthropic, OpenAI, Gemini, Ollama, vLLM, any OpenAI-compatible endpoint | GLM-5.2, openPangu-2.0-Flash, openPangu-2.0-Pro, GLM-5.2-ArkTS-SPARK |
| Bring your own model | Yes | YesThird-party models can be configured by the individual on the entry and basic tiers, and centrally by an administrator on the professional tier. |
| Local models | Yes | No |
| Cost | ||
| Pricing model | byok | mixed |
| Starts at | $0/mo | n/a |
| Free tier | Yes | Yes |
| Bring your own key | Yes | No |
| Openness | ||
| Open source | Yes | No |
| License | Apache-2.0 | proprietary |
| GitHub stars | 474 | n/a |
Which one would each critic pick
| Critic | Async IDE | CodeArts Agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 7.0 | CodeArts Agent — Pick this if your company already runs on Huawei Cloud and you want the same agent in four places; pick a self-serve terminal agent if you do not want an account first. |
| El Crítico | 6.0 | 6.3 | CodeArts Agent — Sub-agents are created and scheduled automatically for decomposition, so the operator never chooses the split, and concurrent sessions multiply whatever that automatic choice got wrong. |
| El Profesor | 7.0 | 7.0 | no preference |
| La Inversora | 5.8 | 7.5 | CodeArts Agent — Personal tiers run CNY 0, 98, 198 and 498 a month, and the on-demand meter is denominated in model tokens. The plugin is a funnel into the parent's inference business. |
| La Jefa | 5.3 | 7.5 | CodeArts Agent — Single sign-on, IP allow-lists, per-scope governance and token quotas, with a seat-based professional edition sized from 1 to 1000. This is the first row this quarter written for me. |
| El Hacker | 7.8 | 5.5 | 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.