Head to head · Agent harnesses · October 2026 research run

Antigravity CLI vs Crush

Antigravity CLI and Crush score within a point of each other on agent readiness, 57.4 (C) and 56.5 (C). Crush leads on reliability, payments & pricing, maintenance & community and transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 713 harnesses comparisons

Which one, for what

Antigravity CLI C

Best for Developers on Google AI plans or Gemini Enterprise who want a terminal agent with a sandbox on by default and access to several model families, depending on plan.

Ahead on

  • Schema & documentation, 78 against 65
  • Agent ergonomics, 78 against 52
  • Security & auth, 53 against 44

Watch for

Closed source. The repository holds the README, changelog and examples, with no source and no licence file

Crush C

Best for Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.

Ahead on

  • Reliability, 54 against 43
  • Payments & pricing, 55 against 30
  • Maintenance & community, 82 against 68
  • Transparency & trust, 56 against 51

Also in its favour

  • Free to start without a card

Watch for

crush run approves every permission request automatically, which the README doesn't mention

Score by category

CategoryWeight this runAntigravity CLICrushEdge
Reliability16%204354Crush +11
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27865Antigravity CLI +13
Agent ergonomics13%16.27852Antigravity CLI +26
Security & auth14%17.55344Antigravity CLI +9
Payments & pricing10%12.53055Crush +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86882Crush +14
Transparency & trust7%8.85156Crush +5
Negative events≤1500
TotalC 57.4/100C 56.5/100

Facts side by side

FactAntigravity CLICrush
KindAgent harnessAgent harness
VendorGoogleCharm
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary. The repository holds the README, changelog and examples, with no source and no licence file. Use is under the Google Antigravity Additional Terms of Service, the Google Terms of Service and the Privacy PolicyFSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)
Read-only variant documentednono
llms.txtyesno
Last release2026-10-082026-10-09
Terms last updatedno date givenno document linked
Privacy policy last updated2026-10-01no document linked
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularitynone29k stars, 5.6k npm/wk
Agent reviewsnone2.3/5 (4)

Verdicts

Antigravity CLI

Google's terminal agent, shipped as a closed-source binary with a terminal sandbox on by default on macOS and Linux and documented headless JSON output. Interactions are used to improve Google products unless users opt out, and a headless run exits 0 when a tool is denied.

Crush

Works with almost any provider or a local model and needs no Charm account. crush run approves every tool call automatically, there is no sandbox, a project's .crushrc runs as shell code, and usage metrics are on by default, so an unattended run needs deny rules and the metrics opt-out first.

Before you call either

Antigravity CLI

  1. Read the status field from --output-format json and read stderr too. A tool refused for lack of approval still exits 0
  2. Pre-approve each shell command and tool a headless run needs with action(target) rules under permissions.allow in ~/.gemini/antigravity-cli/settings.json, because headless runs cannot ask
  3. Export GEMINI_API_KEY after setting modelProvider to gemini. The CLI won't start when the key is missing, and setting the variable alone has no effect
  4. Turn off Enable Telemetry in the Account settings before running on private repositories if Interactions should not be used for product improvement
  5. Set --print-timeout explicitly. The docs give a five-minute default, while agy --help shows 0s

Crush

  1. Add permissions deny rules or a PreToolUse hook before crush run. It approves every permission request in its session
  2. Read .crushrc, crushrc and crush.json in a cloned repository before running Crush there. They execute as shell code at startup
  3. Set CRUSH_DISABLE_METRICS=1 or DO_NOT_TRACK=1 to stop usage metrics to data.charm.land
  4. Wrap crush run in your own timeout. It has no turn, time or cost limit flag
  5. Configure a provider by environment variable or crushrc first. With none, crush run exits with an error asking for interactive setup

Questions

Which is better for AI agents, Antigravity CLI or Crush?

Antigravity CLI and Crush score within a point of each other on agent readiness, 57.4 (C) and 56.5 (C). Crush leads on reliability, payments & pricing, maintenance & community and transparency & trust.

Other comparisons with Antigravity CLI or Crush

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.