Head to head · Agent harnesses · October 2026 research run

Antigravity CLI vs Orca

Orca scores 57.4 (C) on agent readiness against Antigravity CLI's 54.7 (C), and leads in 3 of 7 scored categories. Antigravity CLI leads on schema & documentation, agent ergonomics and security & auth. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 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 70
  • Security & auth, 53 against 43

Watch for

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

Orca C

Best for Developers who want an orchestrator agent to split work across parallel coding agents, on desktop or mobile.

Ahead on

  • Reliability, 58 against 43
  • Payments & pricing, 40 against 30
  • Maintenance & community, 75 against 68

Also in its favour

  • No key needed to call it
  • Open source
  • No incidents deducted, where Antigravity CLI loses 3 points for them

Watch for

Anonymous usage data collected by default, with an opt-out

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Orca +15

Antigravity CLI 43

Local-package reading. An official installer for macOS, Linux and Windows, with an Android build for Termux, that checks a SHA-512 checksum from Google's release manifest before it installs (install.sh re-read on 4 November) (20). No public CI or test suite, since the repository holds no source and no workflows, only issue templates (0). Open issues and pull requests could not be read, so the crash and regression line is unchecked (0). Behaviour changes ship in patch releases as Changed or Improved bullets with no breaking-change heading, such as 1.4.6 (23 October) closing ~/.docker and ~/.kube to sandboxed commands, and 1.2.10's exit-code change (8). Version 1.x, so stable under the rule (15). 20+0+0+8+15 = 43.

Orca 58

Local software. Desktop and mobile builds and a Homebrew cask (20). Unit, end-to-end and platform test workflows; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Tags to v1.4.251, no changelog file (8). Version 1.4 (15). 20 + 15 + 0 + 8 + 15 = 58.

Schema & documentation Antigravity CLI +13

Antigravity CLI 78

Framework reading. No published JSON Schema for settings.json, mcp_config.json or hooks.json was found, although the docs type each key (10). llms.txt at antigravity.google/llms.txt, and every docs page has a Markdown copy (10). Pages say when to use each permission preset and execution mode, what each allows and when the sandbox applies (15). Presets, modes, output formats, status values and effort levels are enumerated (13). The headless page documents the output envelope, the status values and exit codes, with a jq example (15). A dated changelog on the docs site and versioned release notes and tags in the repository (15). 10+10+15+13+15+15 = 78.

Orca 65

Harness reading. A docs site with CLI orchestration and native chat pages (65).

Security & auth Antigravity CLI +10

Antigravity CLI 53

Framework reading (credentials and telemetry defaults, approvals and sandboxing, guardrails, audit, security programme), five lines. Credentials are a Google account sign-in kept in the operating system keyring, or a Gemini API key in settings.json. The README says using the CLI allows Google to collect Interactions until the user opts out (10). Since 1.3.5 on macOS and Linux and 1.4.4 on Windows 11 24H2 the default for personal accounts is Auto mode, which runs commands in the terminal sandbox, hides ~/.ssh, .env and, since 1.4.6, ~/.docker and ~/.kube, blocks network access outside approved domains, and has a separate agent review commands that leave the sandbox. Auto approves file edits and safe commands without asking, Turbo turns the sandbox off, and business accounts start in Default (18). Hooks run before and after tool calls and can block one, and since 1.4.11 a PreInvocation hook can stop a turn. No documented defence against prompt injection in fetched content was found (7). The CLI log records model resolution, and approvals show in the conversation, but no exportable audit log was found (10). google.com has a valid security.txt with reports to g.co/vulnz (per the 10 October check), antigravity.google serves none, no CLI advisory appears in the changelog, and NVD returns no CVE for Antigravity on 4 November. The repository's advisory page couldn't be read (8). 10+18+7+10+8 = 53.

Orca 43

Harness reading. Anonymous usage data with an opt-out, per the README's link to its telemetry docs (15 of 30). Worktrees per agent and a sandboxed Linux build (12 of 20). No prompt-injection guidance (5). No audit log (5). A dependency-security workflow (6 of 20). 15 + 12 + 5 + 5 + 6 = 43.

Payments & pricing Orca +10

Antigravity CLI 30

Harness reading of the published rubric. No payment protocol in the docs, the pricing page or the plans page (0). Plan prices are public without a login, with a $0 individual plan and Gemini Enterprise Standard or Plus from $30 a seat a month, and Google AI Pro at $20 and Ultra at $100 or $200 a month per Google's 19 May 2026 post. Overages draw on AI credits at Gemini Enterprise consumption rates, which were not read, so this is plan-level pricing (10). The pricing page lists the $0 plan as needing no subscription, and none of the pages read asks for a payment method, but the account flow was not tested (20). Sign-in is a browser flow with a Google account, or a Gemini API key set by hand, and the CLI won't start unauthenticated (0). 0+10+20+0 = 30.

Orca 40

Scored on the cloud option. No protocol (0). The cloud price wasn't found on the pages read (0). The desktop app is free and MIT with no card (20). The local app needs no sign-up that we found (20). 0 + 0 + 20 + 20 = 40.

Agent ergonomics Antigravity CLI +8

Antigravity CLI 78

Framework reading, adapted to a harness driven by a pipeline. MCP tools can be allowed or refused by server and tool, and a 20,000-token budget for user rules stops large rule sets from crowding out skills and MCP tools (16). No turn or spend cap appears in the flag reference, and --print-timeout sets a wall-clock limit only, with no limit by default (10). The JSON envelope carries a status field and token usage, and since 1.4.11 a finished_reason field says why a turn ended early (16). Exit codes are documented, but a tool soft-denied in headless mode still exits 0 (14). --continue and --conversation resume earlier runs (14). A Python SDK on PyPI, which is a separate package, and no second SDK language for the CLI (8). 16+10+16+14+14+8 = 78.

Orca 70

Harness reading. An orchestrator agent that splits work across workers in their own workspaces, chat or raw CLI, a browser and a CLI in one app (70).

Maintenance & community Orca +7

Antigravity CLI 68

1.4.12 on 30 October 2026, marked Latest in the docs changelog, 5 days before this check (30). 56 tagged releases from 1.1.11 (6 August) to 1.4.12, each with a changelog entry; 1.5.0 is tagged and in the repository changelog on 4 November but not yet in the docs changelog, so it isn't counted (20). Responsiveness rests on a public changelog, a community forum linked from the terms and the GitHub repository, but no replies could be read (8). The google-antigravity Python SDK is a separate package and no SDK for the CLI itself was found; PyPI couldn't be read on 4 November, so the line rests on the 10 October reading (10). No public CI or dependency list for the CLI, since the source is not published (0). 30+20+8+10+0 = 68.

Orca 75

Tags to v1.4.251 and commits on 6 November 2026 (30). Many releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). Extensive CI (10). 30 + 20 + 0 + 15 + 10 = 75.

Score by category

CategoryWeight this runAntigravity CLIOrcaEdge
Reliability16%204358Orca +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27865Antigravity CLI +13
Agent ergonomics13%16.27870Antigravity CLI +8
Security & auth14%17.55343Antigravity CLI +10
Payments & pricing10%12.53040Orca +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86875Orca +7
Transparency & trust7%8.85554Antigravity CLI +1
Negative events≤15-30
TotalC 54.7/100C 57.4/100

Facts side by side

FactAntigravity CLIOrca
KindAgent harnessAgent harness
VendorGoogleLovecast Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreemiumFree
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 PolicyMIT
Read-only variant documentednono
llms.txtyesno
Last release2026-10-302026-11-06
Terms last updatedno date givenno document linked
Privacy policy last updated2026-10-01no document linked
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet

How the scores have moved

Verdicts

Antigravity CLI

Google's terminal agent, a closed-source binary whose default Auto mode runs commands in a terminal sandbox on macOS, Linux and Windows 11, with documented headless JSON output. Interactions are collected for Google product improvement unless users opt out, a headless run exits 0 when a tool is denied, and 1.4.7 fixed a cross-user token flaw without an advisory.

Orca

An open-source orchestrator for coding agents with worker agents in their own worktrees, chat and terminal views, a browser and a CLI, on desktop and mobile, with heavy test automation. It collects anonymous usage data by default, and the cloud option's pricing wasn't found.

Before you call either

Antigravity CLI

  1. Read the status and finished_reason fields 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 /config before running on private repositories if Interactions should not be used for product improvement
  5. Grant sandbox access to ~/.docker or ~/.kube explicitly since 1.4.6 if a task needs Docker or Kubernetes credentials

Orca

  1. See the telemetry docs on onorca.dev to opt out of anonymous usage data
  2. Use the orchestration CLI to hand a large task to one agent that starts workers

Questions

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

Orca scores 57.4 (C) on agent readiness against Antigravity CLI's 54.7 (C), and leads in 3 of 7 scored categories. Antigravity CLI leads on schema & documentation, agent ergonomics and security & auth.

Are Antigravity CLI and Orca open source?

No open-source release is listed for Antigravity CLI. Orca is open source (MIT).

Other comparisons with Antigravity CLI or Orca

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.