What are the best alternatives to Google Antigravity?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Google Antigravity among coding agents are Anthropic Claude Code, Cursor, JetBrains AI, Warp. Each is graded on the same public evidence, and no vendor pays for placement.

Does Google Antigravity support MCP and tool calling?

Full under the Agentic Index verification standard. Google Antigravity publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Agent Features research report + JSON Feature Rubric. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Google Antigravity have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Google Antigravity publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: Agent Features research report + JSON Feature Rubric. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Google Antigravity require human approval before an agent acts?

Full under the Agentic Index verification standard. Google Antigravity publishes public evidence of human approval steps and guardrails, so an agent action can be held for review before it executes. Evidence basis: Agent Features research report + JSON Feature Rubric. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Google Antigravity

Visit site

Coding agent Verified 2026-06-23

Entry price$20/moFull pricing detail

Google's agentic IDE (desktop, CLI, and SDK) with multi-model support, MCP, and a built-in browser.

Google Antigravity is an agentic IDE spanning desktop, CLI, and SDK with multi-model support, MCP, and a built-in browser. In public preview since November 2025 and now at 2.0, it absorbs the retired Gemini CLI; it's free with Pro at $20/month and Ultra roughly $100–250/month.

Vendor details

Canonical URL

https://antigravity.google

Subcategory

Coding — agentic IDE

Use cases & customers

Primary use cases

agentic codingsoftware development

Target customers

developers

Deployment options

desktopCLISDK

In practice

You want an agentic coding tool that works in the editor, the terminal, and your own scripts. Google Antigravity spans desktop, CLI, and an SDK, so the agent meets your workflow.

An agent that can't see the running app guesses at front-end work. Antigravity has a built-in browser, so it can observe and act on what it builds.

You don't want to be tied to a single model in your IDE. Antigravity supports multiple models and MCP, so you connect the tools and models you choose.

Agentic Index coverage score

10.0 / 14 capabilities · 71%

Integrations & Tool CallingAgent Features research report + JSON Feature Rubric	Full
Workflow OrchestrationAgent Features research report + JSON Feature Rubric	Full
Knowledge Grounding & RAGAgent Features research report + JSON Feature Rubric	Partial
Human Oversight & GuardrailsAgent Features research report + JSON Feature Rubric	Full
Security, Identity & GovernanceAgent Features research report + JSON Feature Rubric	Full
Observability & AuditabilityAgent Features research report + JSON Feature Rubric	Partial
Memory & State PersistenceAgent Features research report + JSON Feature Rubric	Partial
Deployment & Data ResidencyAgent Features research report + JSON Feature Rubric	Partial
Prebuilt Agents, Templates & PacksAgent Features research report + JSON Feature Rubric	Unable to verify
Triggers & Channel CoverageAgent Features research report + JSON Feature Rubric	Partial
Model Flexibility & RoutingAgent Features research report + JSON Feature Rubric	Full
APIs, SDKs & MCP ExtensibilityAgent Features research report + JSON Feature Rubric	Full
Testing, Debugging & OptimizationAgent Features research report + JSON Feature Rubric	Partial
Browser & Computer UseAgent Features research report + JSON Feature Rubric	Full

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-07-24·Agent capabilityPartially Verified

Google Antigravity added support for defining custom agents using standard Markdown format via an agent.md file. The release also introduces progressive streaming for the codesearch command, an optional index argument for copy, and default read access to the system temporary directory.

Bears on: Agent capability

View source

2026-07-21·Agent capabilityPartially Verified

Google added new controls for model reasoning effort by introducing a dedicated effort command and launch flag. The platform also introduced stable model slugs for consistent sessions, subagent model configuration options, and a redesigned model picker.

Bears on: Agent capability

View source

2026-07-20·Security / enterprisePartially Verified

Security researchers disclosed a sandbox escape vulnerability where the Antigravity agent could write a file that a trusted external tool would execute to bypass the sandbox entirely. Google acknowledged the risk of these indirect prompt injections and rolled out patches to address the issue.

Bears on: Security / enterprise

View source

View all 3 changes for Google Antigravity →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

$20/mo

hybrid

Free tier

Included quota

AI Pro ($20/mo, entry paid): higher rate limits than Free, all models (Gemini/Claude/GPT), and priority agent processing. Free is ~20 requests/day (cut from 250 at launch).

What is public

Antigravity's access is bundled into Google AI (Google One) subscription tiers: Free/Individual ($0, heavily rate-limited), AI Pro $20/mo, AI Ultra $100/mo (~5x Pro quota), and top-tier AI Ultra $200/mo (~20x Pro quota, cut from $250 at I/O 2026). A cheaper AI Plus tier also grants expanded limits. Pro/Ultra include multi-model access (Gemini, Claude, GPT). Enterprise is via Google Cloud's Gemini Enterprise Agent Platform (contact sales).

Billing mechanics

Flat monthly subscription per tier sets your quota (rate limits / usage allotment). Each tier bundles Gemini-model usage; AI credits act as a pay-as-you-go OVERAGE mechanism once the plan quota is hit (credits were removed from base plans in May 2026 and base entitlements raised). Heavy frontier-model use (e.g., Claude Opus) burns quota fast and can trigger multi-day lockouts on lower tiers.

Cost watchouts

Opaque credit-to-token value (undocumented), frontier-model usage burning quota fast, multi-day lockouts reported on Pro/Ultra, free-tier limits repeatedly cut, credit top-ups

Variable cost rationale

Subscription is flat, but opaque quotas plus credit overage on heavy frontier-model use make real spend hard to predict

Additional watchouts

Pricing has been volatile — free quotas slashed and a credit system introduced; cost predictability is the main developer complaint

Overage / add-ons

Once plan quota is exhausted, agent tasks stop until refresh (e.g., every 5 hrs on Free) OR you enable AI-credit overages. Credits are ~$0.01 each, bought in bulk ($25/2,500 or $199/20,000); Pro/Ultra subscribers can buy PAYG top-up credits.

Sales call required

No, self serve available

Free / trial

Free tier

Lowest paid plan

Free; Pro $20/mo; Ultra ~$100–250/mo

Commercial notes

Top Ultra cut from $250 to $200 (May 2026); a new $100 mid Ultra added; Ultra bundles 20TB storage + YouTube Premium; Antigravity CLI replaced the Gemini CLI (June 18, 2026)

Key ambiguities

Google doesn't publish how many tokens/requests one credit buys, per-model credit costs, or the exact included credit/quota amounts per tier; 'rate limits are not guaranteed'

Cancellation / refund

Monthly Google AI subscriptions, cancel anytime; refund terms per Google One; pricing has changed repeatedly (free-tier cuts, Ultra restructure)

Support SLA / resale

Higher tiers add priority access and extended agent sessions; enterprise support via Google Cloud / Gemini Enterprise Agent Platform

Missing data

Per-tier included credit/quota amounts, credit-to-token conversion, and per-model credit costs are not publicly documented

Agentic Index verified 2026-06-25

Official pricing page Docs

Related vendors

Alternatives to Google Antigravity

The closest documented capability profiles to Google Antigravity among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Anthropic Claude Code10.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Testing, Debugging & Optimization
Cursor11.0 / 14Adds documented Prebuilt Agents, Templates & PacksGoogle Antigravity vs Cursor →
JetBrains AI10.0 / 14Adds documented Prebuilt Agents, Templates & Packs
Warp10.0 / 14Adds documented Prebuilt Agents, Templates & Packs
Cognition10.5 / 14Fuller documented coverage on Knowledge Grounding & RAG and Memory & State Persistence
Factory12.5 / 14Adds documented Prebuilt Agents, Templates & Packs

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Google Antigravity with other vendors →Compare all coding agents →See where Google Antigravity ranks →

Data confidence: high

Head to head

Google Antigravity vs Cursor Google Antigravity vs Kiro

Google Antigravity

Vendor details

Canonical URL

Category

Subcategory

Use cases & customers

Primary use cases

Target customers

Deployment options

In practice

Agentic Index coverage score

Recent platform changes

Pricing

Related vendors

Alternatives to Google Antigravity

Head to head

Contact us