Google AntigravityvsCodeArts Agent
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Google Antigravity
Google · AI-native IDE
#68MCP
Panel
6.05 spec wins
- Reliability
- 5.3
- Usefulness
- 6.7
- Cost
- 6.2
- Longevity
- 5.8
“Google's own IDE ships Claude and gpt-oss next to Gemini, the most honest model review Google has ever published.”
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 | Google Antigravity | 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 | YesA first-party browser subagent drives Chrome from a separate profile with allowlist/denylist controls (https://antigravity.google/docs/ide/browser/); IDE-side only, not in the agy CLI. | No |
| Sandboxed execution | YesOS-level isolation rather than containers: "no virtual machines or Docker images to manage" - Linux uses kernel namespaces to isolate the filesystem, hide host processes and cut networking; macOS uses sandbox-exec with Seatbelt (SBPL) profiles. | No |
| Multi-agent orchestration | Yes | YesSub-agents are created and executed automatically for task decomposition and delegation, and multiple sessions run concurrently. |
| Headless / CI mode | Yes | No |
| Models | ||
| Backbone | Gemini 3.1 Pro, Gemini 3.8 Flash, Claude Sonnet 4.6, Claude Opus 4.6, gpt-oss-120b | GLM-5.2, openPangu-2.0-Flash, openPangu-2.0-Pro, GLM-5.2-ArkTS-SPARK |
| Bring your own model | YesSetting `modelProvider: "gemini"` in ~/.gemini/antigravity-cli/settings.json plus a GEMINI_API_KEY runs the CLI on your own key and billing instead of a signed-in Google account, and a model selector picks between Gemini, Claude and gpt-oss models in the IDE. | 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 | YesGOOGLE_GEMINI_BASE_URL sends model requests to any Gemini-compatible endpoint, so a self-hosted shim works as a mechanism; no Ollama or LM Studio integration is documented. | No |
| Cost | ||
| Pricing model | mixed | mixed |
| Starts at | $20/mo | n/a |
| Free tier | Yes | Yes |
| Bring your own key | Yes | No |
| Openness | ||
| Open source | No | No |
| License | proprietary | proprietary |
| GitHub stars | 2,446 | n/a |
Which one would each critic pick
| Critic | Google Antigravity | CodeArts Agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 7.0 | no preference |
| El Crítico | 6.3 | 6.3 | no preference |
| El Profesor | 6.3 | 7.0 | CodeArts Agent — Retrieval is split between a cloud index over repositories of tens of millions of lines and a local language server supplying diagnostics, jumps and symbols. Two sources, two jobs. |
| La Inversora | 7.3 | 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 | 4.0 | 5.5 | CodeArts Agent — Closed source, and third-party models are mine to configure on the entry tiers but an administrator's decision on the professional one. It is an MCP server as well as a client. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.