Skip to content
ProductArena

Rank #5 of 13 in AI Coding Agents

Google Antigravity logo

Google Antigravity

Built-in AI assistant

Google · commercial

antigravity.google ↗Try it →
PA Score37/100AGENT-READY55/100BUILT-IN AI70/100API2/100
MCP✓CLI✓API~
no public signals
ArenasAI Coding Agents#5/13

Access

Open app ↗CLI docs ↗

Compare head-to-head

Codex logovs CodexClaude Code logovs Claude CodeCursor logovs CursorGitHub Copilot logovs GitHub CopilotGemini CLI logovs Gemini CLIOpenCode logovs OpenCodeDevin logovs Devinvs AiderCline logovs Clinecubic logovs cubicSlate logovs SlateConductor logovs Conductor

Alternatives to Google Antigravity →

Products

Google, product by product →

Google ships more than one product — each judged line competes in its own arena on the same stories as everyone else.

LineArenaRankPA Score
GeminiAI Assistants#7/917/100
Antigravitythis pageAI Coding Agents#5/1337/100
Gemini CLIAI Coding Agents#12/1321/100
Gemini Notebook (NotebookLM)AI Research Agents#6/67/100
JulesSoftware Factory#7/923/100
Agent Development KitAgent Frameworks & SDKs#4/935/100
FirebaseBackend as a Service#3/435/100
AngularFrontend Frameworks#3/528/100

Not yet judged (4 — no arena where they compete): Google AI Studio · Flow · Gemini in Chrome · Gemini Code Assist

Try itExperimental

See what an agent can do with Google Antigravity before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -s --compressed https://antigravity.google/docs/getting-started.md | head -6recorded session — replayed, not live
recorded 2026-09-14 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

51.1/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

55.3/100

Autonomy agents — stories about autonomy agents in this arenaAutonomy agentsevidence →

Stories about autonomy agents in this arena

41.0/100

Code generation — quality of generated code — correctness, style, fit to the codebaseCode generationevidence →

Quality of generated code — correctness, style, fit to the codebase

27.5/100

Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understandingevidence →

How deeply the tool maps your repo — cross-file context, architecture awareness, history

42.3/100

Ecosystem — integrations, plugins, and third-party ecosystem storiesEcosystemevidence →

Integrations, plugins, and third-party ecosystem stories

22.7/100

Ide terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integrationevidence →

Meeting you in the IDE and terminal — extensions, inline flows, context

70.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

4.8/100

Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →

Free-tier ceilings, usage caps, and rate limits before you have to pay

16.9/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

29.6/100

Review safety — keeping generated changes safe — diffs, approvals, guardrailsReview safetyevidence →

Keeping generated changes safe — diffs, approvals, guardrails

14.5/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 74/74 stories · click a row’s chevron for the rationale and evidence

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10X

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10C

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10T

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/a0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10X

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10C

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10X

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2disputed4/10D

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/a0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1disputed4/10D

Run a coding agent locally from my terminal C

Terminal workflow

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration3full8/10T

Add a project instructions file to set coding standards and conventions the agent follows C

Context management

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding3full7/10C

Chat with the coding assistant directly inside my IDE for contextual help C

Ide integration

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration3full7/10X

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3full7/10C

Describe a feature or bug in plain language and have the agent implement or fix it across multiple files C

Feature implementation

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation3partial7/10X

Have the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me C

Maintenance automation

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation3partial6/10X

Inspect diffs and run checks to catch problems before merging C

Pr review

developerReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety3partial6/10X

Reproduce issues, narrow down root causes, and verify fixes C

Issue diagnosis

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding3partial6/10X

Understand how a codebase fits together to find where to start making changes C

Codebase mapping

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding3partial6/10C

Connect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context C

Tool integration

developerEcosystem — integrations, plugins, and third-party ecosystem storiesEcosystem3partial5/10C

Delegate longer-running coding tasks to run in the background in an isolated cloud environment C

Background execution

developerAutonomy agents — stories about autonomy agents in this arenaAutonomy agents3partial5/10C

Have the agent map and explain an entire unfamiliar codebase without manually selecting context files C

Codebase mapping

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding3partial5/10C

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3partial5/10C

Receive inline code completions and next-edit suggestions as I type C

Code completion

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation3partial5/10C

Have the agent stage changes, write commit messages, create branches, and open pull requests C

Pr review

developerReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety3partial3/10C

Get automatic code review with contextual feedback on every pull request C

Pr review

developerReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety3none0/10

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10

Turn a tracked issue into a complete pull request end-to-end C

Feature implementation

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation3none0/10

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Choose which underlying AI model powers my session from multiple providers C

Model choice

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2full8/10X

Include multiple project directories in a single session for broader context C

Context management

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding2full8/10C

Manage multiple agent-driven coding sessions from one unified workspace C

Session management

engineering-leadIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration2full8/10X

Review diffs visually and run multiple sessions side by side in a desktop app C

Session management

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration2full8/10X

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2full8/10C

Launch fleets of autonomous agents that work in parallel on different tasks for hours or days C

Parallel agents

ai-native userAutonomy agents — stories about autonomy agents in this arenaAutonomy agents2partial7/10C

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2full7/10C

Run the agent non-interactively in scripts for workflow automation C

Terminal workflow

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration2full7/10C

Set up always-on agents that run on schedules or triggers to maintain and fix my software autonomously C

Scheduled automation

ai-native userAutonomy agents — stories about autonomy agents in this arenaAutonomy agents2full7/10X

Start a task on one device and continue it later from another device or browser C

Cross device continuity

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration2full7/10C

Debug issues and troubleshoot using natural-language queries C

Debugging

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation2partial6/10C

Have a cloud agent build, test, and demo a feature end-to-end for my review C

Background execution

ai-native userAutonomy agents — stories about autonomy agents in this arenaAutonomy agents2partial6/10X

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial6/10C

Control which external tools and integrations the agent is allowed to access C

Safe execution

engineering-leadReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety2disputed5/10D

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial4/10T

Generate a working app from a sketch, image, or PDF design C

Multimodal generation

ai-native userCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation2partial4/10C

Have the agent operate inside a sandbox when interacting with code, tools, and network resources C

Safe execution

engineering-leadReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety2disputed4/10D

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial3/10C

Authenticate through an enterprise identity or cloud platform for compliance and scalability G

Authentication

engineering-leadPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2none0/10

Authenticate with an API key instead of an account login G

Authentication

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2none0/10

Have the agent build and recall memory automatically across sessions C

Context management

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding2none0/10

Sign in with my existing product subscription plan to use the coding agent C

Authentication

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Configure a reproducible cloud environment with the dependencies and setup steps my repository needs C

Background execution

developerAutonomy agents — stories about autonomy agents in this arenaAutonomy agents2n/auntestednone yet

Get contextual explanations and automatic fixes for security vulnerabilities C

Security checks

developerReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety2noneuntestednone yet

Kick off agent tasks directly from GitHub, GitLab, Linear, or Slack C

Tool integration

developerEcosystem — integrations, plugins, and third-party ecosystem storiesEcosystem2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Equip the agent with custom skills to perform specialized tasks C

Marketplace

developerEcosystem — integrations, plugins, and third-party ecosystem storiesEcosystem1full8/10C

Opt out of having my code and prompts used for AI model training C

Data governance

engineering-leadReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety1partial5/10C

Debug a live running web application directly from my coding assistant C

Debugging

developerCode generation — quality of generated code — correctness, style, fit to the codebaseCode generation1partial4/10C

Integrate third-party partner-built agent apps into my workflows C

Marketplace

engineering-leadEcosystem — integrations, plugins, and third-party ecosystem storiesEcosystem1disputed4/10D

Run several task attempts in parallel and compare results before choosing one C

Parallel agents

developerAutonomy agents — stories about autonomy agents in this arenaAutonomy agents1partial4/10C

Sign in with a personal account to get free-tier access without managing API keys G

Authentication

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits1disputed3/10D

Create a shared workspace from my docs and repos as a common source of truth for the team C

Team knowledge

engineering-leadEcosystem — integrations, plugins, and third-party ecosystem storiesEcosystem1none0/10

Let the tool automatically pick the best model for each task C

Model choice

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits1none0/10

View interactive diffs and share selected code as context from within my JetBrains IDE C

Ide integration

developerIde terminal integration — meeting you in the IDE and terminal — extensions, inline flows, contextIde terminal integration1none0/10

See license and public-code matching references for AI-suggested code C

Security checks

engineering-leadReview safety — keeping generated changes safe — diffs, approvals, guardrailsReview safety1noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 43 stories with headroom

What would move Google Antigravity’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Review safety — keeping generated changes safe — diffs, approvals, guardrailsGet automatic code review with contextual feedback on every pull request

    nonemoves PA Scoreimpact 30

    Antigravity offers in-editor 'Review Changes' diff viewing and Artifact-based plan review, but there is no evidence of a GitHub/GitLab pull-request bot or CI-integrated review that automatically posts contextual feedback on every PR.

  2. Code generation — quality of generated code — correctness, style, fit to the codebaseTurn a tracked issue into a complete pull request end-to-end

    nonemoves PA Scoreimpact 30

    Missing: issue-tracker ingestion, automated branch/PR creation, and any documented GitHub/GitLab PR workflow example.

  3. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    No evidence in the pack mentions data export, open-format portability, or account/data deletion features for Antigravity; docs cover projects, agents, artifacts, and CLI but never data portability or export-and-leave capability.

  4. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    No evidence anywhere in the pack indicates Antigravity can be self-hosted; it is described only as a downloadable desktop app/IDE/CLI/SDK connecting to Google's cloud-hosted models, with account/entitlement gating and TOS restrictions mentioned in community reports, but no self-hosted server or on-prem deployment option is documented.

  5. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    No evidence of any webhook subscription mechanism; Antigravity is an IDE/CLI/agent platform with hooks, MCP, and scheduled tasks, but nothing about outbound event subscriptions via webhooks.

  6. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    A direct probe for OpenAPI/Swagger specs at all standard candidate paths returned 404s, and no documentation item mentions a machine-readable API spec despite extensive docs on SDK, CLI, and MCP.

  7. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    No evidence of versioned APIs or a documented deprecation policy; OpenAPI probe returned 404s across all candidate paths and no docs mention API versioning or deprecation timelines.

  8. Review safety — keeping generated changes safe — diffs, approvals, guardrailsHave the agent stage changes, write commit messages, create branches, and open pull requests

    partialq3/10moves PA Scoreimpact 21

    Missing: explicit docs on commit-message authoring, branch creation workflow, and pull-request creation/integration with GitHub/GitLab.

Showing the top 8 of 43 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map6 surfaces · 51 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

docs48 stories

Product docs37 stories

Hacker News21 stories

Changelog docs4 stories

OpenAPI spec3 stories

llms.txt1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s --compressed https://antigravity.google/docs/getting-started.md | head -6reproduced
$ curl -s --compressed https://antigravity.google/docs/getting-started.md | head -6
# Getting Started with Antigravity 2.0

### Download

Visit [antigravity.google/download](https://antigravity.google/download) to download Google Antigravity 2.0. Select your operating system below:
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-14
$curl -s https://antigravity.google/llms.txt | head -4reproduced
$ curl -s https://antigravity.google/llms.txt | head -4
# Google Antigravity

> Google Antigravity is an advanced agentic coding platform and CLI designed for orchestrating autonomous subagents, scheduled tasks, and interactive code verification.
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-14

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

7 of 20 testable claims verified · 1 contradicted → integrity 25/100

38 distinct capability claims found in Google Antigravity’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

7

Verified

12

Unverified

1

Contradicted

26

Undersold

Verified (8)
Unverified (15)
Contradicted (3)
Undersold (26)
Claims outside our story set (12)

Real capability claims found in Google Antigravity’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Speak prompts aloud and have them transcribed into clear text prompts via Gemini Audio”

    source ↗

  • “Agents can autonomously act across the editor, terminal, and browser”

    source ↗

  • “Give inline comments/feedback on generated Artifacts to guide the agent”

    source ↗

  • “Navigate and customize the tool via terminal slash-commands like /config and /keybindings”

    source ↗

  • “Quickly access plugin, MCP, skill, and hook configuration via slash commands”

    source ↗

  • “Attach multimedia files (images, video, audio, documents) alongside text prompts for the agent”

    source ↗

  • “An agent can delegate tasks like running tests or codebase searches to dedicated subagents”

    source ↗

  • “Ships with several specialized subagents pre-packaged out of the box”

    source ↗

  • “Planning Mode has the agent produce structured implementation plans (Artifacts) before executing”

    source ↗

  • “Agent always pauses and requires explicit user approval before applying proposed changes”

    source ↗

  • “Plugins bundle skills, rules, MCP servers, and hooks into a single namespaced package”

    source ↗

  • “Provide inline text feedback to steer the agent before it modifies local files”

    source ↗
Suggest a story for these →

Business model

free-tiersubscription-flatenterprise-custom

Free for individuals with weekly rate limits; Google AI Pro/Ultra subscriptions raise limits and add a credit pool; teams buy consumption pricing via Gemini Enterprise.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score35 (Sep 14 '26)37 (Sep 16 '26)
Agent-ready50 (Sep 14 '26)55 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)