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
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
| Category | Weight this run | Antigravity CLI | Crush | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 43 | 54 | Crush +11 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 78 | 65 | Antigravity CLI +13 |
| Agent ergonomics | 13%16.2 | 78 | 52 | Antigravity CLI +26 |
| Security & auth | 14%17.5 | 53 | 44 | Antigravity CLI +9 |
| Payments & pricing | 10%12.5 | 30 | 55 | Crush +25 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 68 | 82 | Crush +14 |
| Transparency & trust | 7%8.8 | 51 | 56 | Crush +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 57.4/100 | C 56.5/100 |
Facts side by side
| Fact | Antigravity CLI | Crush |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Charm | |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Proprietary. 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 Policy | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-08 | 2026-10-09 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | 2026-10-01 | no document linked |
| Customer content may train models | yes, with an opt-out | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | none | 29k stars, 5.6k npm/wk |
| Agent reviews | none | 2.3/5 (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
- Read the
statusfield from--output-format jsonand read stderr too. A tool refused for lack of approval still exits 0 - Pre-approve each shell command and tool a headless run needs with
action(target)rules underpermissions.allowin ~/.gemini/antigravity-cli/settings.json, because headless runs cannot ask - Export
GEMINI_API_KEYafter setting modelProvider to gemini. The CLI won't start when the key is missing, and setting the variable alone has no effect - Turn off Enable Telemetry in the Account settings before running on private repositories if Interactions should not be used for product improvement
- Set
--print-timeoutexplicitly. The docs give a five-minute default, whileagy --helpshows 0s
Crush
- Add
permissions denyrules or a PreToolUse hook beforecrush run. It approves every permission request in its session - Read
.crushrc,crushrcandcrush.jsonin a cloned repository before running Crush there. They execute as shell code at startup - Set
CRUSH_DISABLE_METRICS=1orDO_NOT_TRACK=1to stop usage metrics to data.charm.land - Wrap
crush runin your own timeout. It has no turn, time or cost limit flag - Configure a provider by environment variable or
crushrcfirst. With none,crush runexits 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
- Agent Zero vs Antigravity CLI
- Agent Zero vs Crush
- Aider vs Antigravity CLI
- Aider vs Crush
- Amp vs Antigravity CLI
- Amp vs Crush
- Antigravity CLI vs Auggie CLI
- Antigravity CLI vs Claude Code
- Antigravity CLI vs Cline
- Antigravity CLI vs Cursor CLI
- Antigravity CLI vs DeepSeek Harness (dsh)
- Antigravity CLI vs Devin
- Antigravity CLI vs Droid CLI
- Antigravity CLI vs Pi
- Antigravity CLI vs Gemini CLI
- Antigravity CLI vs GitHub Copilot CLI
- Antigravity CLI vs goose
- Antigravity CLI vs Harness²
- Antigravity CLI vs HarnessRouter
- Antigravity CLI vs Jules
- Antigravity CLI vs Junie CLI
- Antigravity CLI vs Kilo Code CLI
- Antigravity CLI vs Kimi Code CLI
- Antigravity CLI vs Kiro CLI
- Antigravity CLI vs mini-swe-agent
- Antigravity CLI vs Mistral Vibe CLI
- Antigravity CLI vs Muse Code
- Antigravity CLI vs OpenAI Codex
- Antigravity CLI vs OpenCode
- Antigravity CLI vs OpenHands
- Antigravity CLI vs Prime Agent
- Antigravity CLI vs Qoder CLI
- Antigravity CLI vs Qwen Code
- Antigravity CLI vs Mirror CLI
- Antigravity CLI vs Rovo Dev CLI
- Antigravity CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- Auggie CLI vs Crush
- Claude Code vs Crush
- Cline vs Crush
- Crush vs Cursor CLI
- Crush vs DeepSeek Harness (dsh)
- Crush vs Devin
- Crush vs Droid CLI
- Crush vs Pi
- Crush vs Gemini CLI
- Crush vs GitHub Copilot CLI
- Crush vs goose
- Crush vs Harness²
- Crush vs HarnessRouter
- Crush vs Jules
- Crush vs Junie CLI
- Crush vs Kilo Code CLI
- Crush vs Kimi Code CLI
- Crush vs Kiro CLI
- Crush vs mini-swe-agent
- Crush vs Mistral Vibe CLI
- Crush vs Muse Code
- Crush vs OpenAI Codex
- Crush vs OpenCode
- Crush vs OpenHands
- Crush vs Prime Agent
- Crush vs Qoder CLI
- Crush vs Qwen Code
- Crush vs Mirror CLI
- Crush vs Rovo Dev CLI
- Crush vs Warp (Warp Agent CLI and the Oz Agent API)
- Antigravity CLI vs CLI Manager
- Antigravity CLI vs Harness
- Antigravity CLI vs Paperclip
- Antigravity CLI vs Parallax
- CLI Manager vs Crush
- Crush vs Harness
- Crush vs Paperclip
- Crush vs Parallax
Machine-readable
- This page as Markdown
/compare/antigravity-cli-vs-crush.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/antigravity-cli.json·/api/v1/tools/crush.json - From a terminal
anchor compare antigravity-cli crush(the CLI) - Over MCP
compare_tools {"a": "antigravity-cli", "b": "crush"}at/mcp, no key