IDE-shaped surface backed by Gemini. Built-in planner agent + editor agent + review pass. Best when the repo is large enough that smaller-context IDEs lose the thread.
Antigravity (Google)
Antigravity is Google's answer to Cursor. The differentiator: Gemini's 2M-token context window means the IDE can hold the entire repo in its working memory. Best fit when your codebase is big and your platform is already Google.
Antigravity's built-in review pass uses Gemini — same model that wrote the code. A second opinion from Claude (different lineage, different priors) catches what Gemini's self-review wouldn't. Paste the diff + ticket; ask for a structured review.
- antigravityFree preview
- claudeFree tier
- antigravity~$20 (post-GA est.)
- claude$20 Pro
- antigravity~$100 (5 seats)
- claude$100 (5× $20 Pro)
Antigravity 2.13.0 adds Documents section and virtualized file viewer
Version 2.13.0 introduces a new Documents section in the sidebar for external files and a virtualized viewer for large code files with syntax highlighting and inline comments. Additional improvements include whitespace-only diff filtering, sandbox command badges, and enhanced side question panel management.
Antigravity 2.13.0 adds Documents section and sidebar organization features
Introduces a dedicated Documents section for external files like Google Drive links and PDFs, adds whitespace filtering in diffs, virtualized viewer for large code files with syntax highlighting, and improves side question handling with minimize/restore functionality and command palette integration.
Gemini 3.8 Flash reasoning models now available in Antigravity Enterprise via ADC
Antigravity 2.12.2 enables enterprise users to select and use Google's Gemini 3.8 Flash reasoning models through Application Default Credentials (ADC) for agentic tasks. This provides enterprise teams direct access to Google's flagship reasoning capabilities within the Antigravity platform.
Antigravity 2.12.2 enables enterprise access to Gemini 3.8 Flash reasoning models
Enterprise users can now select and use Google's Gemini 3.8 Flash reasoning models via Application Default Credentials (ADC) in Antigravity. This provides enterprise developers access to Google's flagship reasoning capabilities for more sophisticated agentic tasks.
- 1Open the repo in AntigravityAntigravity
Same as VS Code. The first index pass takes a minute or two for a large repo; subsequent prompts use the cached context.
- 2Hand the planner the ticketAntigravity
Antigravity's planner agent reads the whole repo. Generates a plan that respects existing patterns.
- 3Editor agent applies the planAntigravity
Multi-file edits with diffs you accept hunk-by-hunk. The 2M context means it rarely loses the thread mid-refactor.
- 4Cross-vendor review with ClaudeClaude
Push the branch and grab the diff. Paste it into Claude with the ticket; ask for a structured review. The cross-vendor angle catches Gemini-flavored blind spots before a human reviewer does.
- 5Apply review fixesAntigravity
Bounce Claude's findings back to Antigravity's editor agent. The whole-repo context makes review-fix patches especially clean.
Ran a 4-week refactor (replacing an internal pubsub layer) with Antigravity as the primary IDE. The 2M-context kept the agent on-track across ~30 files; previous attempt with a smaller-context IDE drifted by file 12.
Antigravity is in preview. Quotas, model availability, and pricing may shift before GA. Don't bet a deadline on a specific feature without a fallback IDE.
If your repo has committed .env or service-account keys, the agent will happily quote them in chat. Audit git history before pointing the agent at the repo.


What changed in AI tools and the stacks that ship. One email a week.