Google AntigravityvsIBM Bob
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
6.07 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.”
IBM Bob
IBM · AI-native IDE
#93MCP
Panel
5.70 spec wins
- Reliability
- 5.5
- Usefulness
- 5.7
- Cost
- 4.7
- Longevity
- 6.8
“It is metered in Bobcoins, so your refactor now has an exchange rate.”
Spec by spec
| Spec | Google Antigravity | IBM Bob |
|---|---|---|
| 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 | No |
| 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 | YesBob spawns subagents that run in parallel, each in its own mode, with per-spawn approval. |
| Headless / CI mode | Yes | YesBob Shell is documented for task scripting and CI/CD pipeline integration. |
| Models | ||
| Backbone | Gemini 3.1 Pro, Gemini 3.8 Flash, Claude Sonnet 4.6, Claude Opus 4.6, gpt-oss-120b | multi-model routing |
| 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. | No |
| 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 | subscription |
| Starts at | $20/mo | $20/mo |
| Free tier | Yes | No |
| 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 | IBM Bob | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 5.8 | Google Antigravity — Pick Antigravity if you want several agents running at once with a browser checking their work; pick Cursor if you want one agent that edits well and stays out of the way. |
| El Crítico | 6.3 | 5.5 | Google Antigravity — Agents drive your editor, terminal and a live Chrome with no container between them and your machine; the only isolation on offer is a git worktree. |
| El Profesor | 6.3 | 5.5 | Google Antigravity — No benchmark is published; the design bet is verification by artifact, with plans, walkthroughs and screenshots the human reviews instead of raw tool logs. |
| La Inversora | 7.3 | 7.0 | Google Antigravity — Google is bundling the IDE into Google AI Pro and Ultra subscriptions, distribution no startup on this board can match and a roadmap no buyer controls. |
| La Jefa | 5.3 | 6.5 | IBM Bob — Sixty developers is $1,200 a month on the entry plan and $12,000 on the top one, and the difference between them is an allowance nobody can forecast. |
| El Hacker | 4.0 | 3.8 | Google Antigravity — Proprietary, local models only via a GOOGLE_GEMINI_BASE_URL override, no key field in the IDE; the agy CLI takes a Gemini API key and MCP servers sit in a mcpServers block with a serverUrl for remote ones. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.