HarnessMatch
Menu

Coding agent

Antigravity CLI

Google's managed multi-agent terminal harness for consumer and enterprise workflows.

Status
Active
License
Proprietary binary distribution
Evidence
Documented, 16 sources
Product record checked
2026-07-28
Compare harnessesInspect sources

At a glance

A proprietary terminal interface to Google's shared Antigravity agent harness, with a managed multi-provider model catalog, asynchronous subagents, structured headless output, SSH use, browser actions, MCP, plugins, skills, hooks, granular permissions, and optional native OS sandboxing.

Good choice if

  • Individual Gemini CLI users moving to Google's supported consumer terminal product
  • Terminal, SSH, or headless work that benefits from parallel background agents
  • Teams using a managed model catalog through Google AI plans or the Gemini Enterprise Agent Platform

Check before choosing

  • Model access is managed by Google plans or Google Cloud; the documentation does not offer BYOK endpoints or local-model execution
  • Native OS sandboxing is available but off by default, while workspace file reads and writes are auto-allowed by the permission engine unless stricter policy is configured
  • Always-proceed modes and one-command sandbox escapes can remove review or containment boundaries
See 3 more considerations
  • Conversation rewind and fork operate on session history, not the local Git checkout, so they do not provide file rollback or worktree isolation
  • Telemetry is enabled by default and must be changed in settings when that collection is not desired
  • The public GitHub repository distributes releases and support material but does not expose the core harness source, engineering tests, security policy, or evaluation suite

Why it qualifies as a coding harness

This confirms category fit, not product quality. Every required criterion links back to first-party evidence.

Qualifies4 of 4 required criteria evidenced

  • Adaptive agent loop

    Documented

    The system repeatedly observes results and chooses the next action instead of following a fixed one-pass graph.

    EvidenceAntigravity CLI overview

  • Repository tool execution

    Documented

    The system can use tools to inspect and change a repository or its execution environment.

    EvidenceAntigravity CLI overview

  • Task-aware context management

    Documented

    The runtime assembles, updates, compacts, retrieves, or persists task-relevant context while work proceeds.

    EvidenceConversation management

  • Model-independent runtime control

    Documented

    Permissions, budgets, interruption, policy, or stop controls operate outside the model's own text generation.

    EvidenceFine-grained permissions

Membership establishes category fit only. It does not score quality, safety, autonomy, model capability, or benchmark performance. · Read the membership rule.

How it works under the hood

Seven mechanisms mapped from first-party records. These labels describe what the harness provides, not how intelligent its model is.

7/7layers documented
  • Execution & isolationSandbox availableDocumented mechanism, not a performance score.
  • Tooling & integrationsExtensible + browserDocumented mechanism, not a performance score.
  • Context & stateManaged contextDocumented mechanism, not a performance score.
  • Lifecycle & recoverySession resumeDocumented mechanism, not a performance score.
  • ObservabilityStructured tracesDocumented mechanism, not a performance score.
  • VerificationTool-assistedDocumented mechanism, not a performance score.
  • Governance & permissionsPolicy controlsDocumented mechanism, not a performance score.

Public code audit

Unrankedsupport-only repository
Security policy
Not found
CI workflow
Not found
Automated tests
Not found
Evaluation assets
Not found
Contributor documentation
Not found

The 1.1.8 public tree contains only 15 issue-template, changelog, README, demo, and customization-example files. It exposes no core harness source, license file, CI workflow, engineering tests, security policy, contributor guide, evaluation suite, or independently reproducible benchmark result.

Inspect commit 03e095ac3619462ecd0928f3f5470387dbda6a00, checked 2026-07-28

Measured configurations

No benchmark run passes the full metadata admission policy for this harness yet. Missing data is not scored as zero.

Benchmark policy and all runs

Capability support

Documented first-class product support, checked against the sources below.

External tools (MCP)
DocumentedProduct-supported MCP integrationSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Local models
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.
Agent parallelism
DocumentedDelegated or parallel agent workflowSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Runs without an open UI
DocumentedNon-interactive or automation surfaceSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Browser control
DocumentedBuilt-in or product-supported browser controlSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Isolated execution
OptionalOptional OS or container isolationSource · checked 2026-07-28The source establishes the mechanism, not its quality or availability in every mode.
Undo file changes
Not documentedNo first-class support established by the current recordAbsence of current documentation is not proof that the capability is impossible.

Primary evidence

Each capability claim is tied to a first-party record and a verification date.

Product record checked 2026-07-28
Antigravity CLI overviewShared agent harness, terminal and SSH surface, headless focus, settings sync, conversation export, and Gemini CLI migrationOfficial docsGemini CLI consumer transitionConsumer migration, enterprise continuity, launch scope, shared harness direction, and retained Gemini CLI mechanismsOfficial announcementPlans and quotasIndividual and enterprise access paths, plan-dependent quotas, CLI availability, third-party models, and changing limitsOfficial docsModel availabilityPlan-specific managed Gemini, Claude, and GPT-OSS model availability without implying harness performanceOfficial docsInstallation and authenticationNative installation, agy command, Google sign-in, secure credential storage, SSH flow, and enterprise onboardingOfficial docsExecution modesRequest-review, accept-edits, planning, permission bypass, review boundaries, and subagent inheritanceOfficial docsFine-grained permissionsDeny, ask, and allow precedence, file and command policy, browser and MCP actions, workspace defaults, and promptsOfficial docsNative terminal sandboxOpt-in nsjail, sandbox-exec, and AppContainer isolation, default state, interactive containment, and one-command escapeOfficial docs
View 8 additional sources
Additional first-party evidence8 sources
Background tasks and subagentsParallel asynchronous agents, custom agent definitions, task monitoring, reasoning logs, tool outputs, and approval routingOfficial docsConversation managementWorkspace-scoped history, session resume, conversation forks, and the explicit absence of filesystem branchingOfficial docsPlugins and skillsPlugin packaging, skills, custom subagents, hooks, rules, workspace scope, and MCP configurationOfficial docsMCP integrationLocal and remote MCP servers, transports, configuration scope, authentication, discovery, and permission promptsOfficial docsCLI settings referenceCommands, headless controls, review presets, sandbox and workspace defaults, telemetry, rewind, and observability panelsOfficial docsAntigravity CLI 1.1.8 releasePinned shipped version, typed NDJSON traces, tool and subagent trajectory fields, JSON-schema output, token accounting, and public support-repository boundaryOfficial repositoryArtifact reviewPlan and diff artifacts, approval and rejection, line-level feedback, media review, and pre-write co-steeringOfficial docsCLI projectsProject-scoped conversations, startup selection, project creation, resume behavior, and cross-project conversation forksOfficial docs