antigravity-workers
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTIGRAVITY_AGY_PATH | No | Override the CLI executable path. | |
| ANTIGRAVITY_BRAIN_DIR | No | Directory used to discover generated artifacts. | ~/.gemini/antigravity-cli/brain |
| ANTIGRAVITY_STATE_DIR | No | State directory. Windows: %LOCALAPPDATA%/CodexAntigravityWorkers; other platforms: ~/.codex/antigravity-workers. | |
| ANTIGRAVITY_FAST_MODEL | No | Fast model. | gemini-3.8-flash-low |
| ANTIGRAVITY_IMAGE_SMOKE | No | Set to '1' to enable image smoke tests. | |
| ANTIGRAVITY_MAX_WORKERS | No | auto; derived from CPU and memory, capped at 16. Explicit values: 1–32. | auto |
| ANTIGRAVITY_DEFAULT_MODEL | No | Default model. | gemini-3.1-pro-high |
| ANTIGRAVITY_BALANCED_MODEL | No | Balanced model. | gemini-3.8-flash-medium |
| ANTIGRAVITY_MAX_TEAM_AGENTS | No | Server default 32; bundled plugin configuration 64. | 32 |
| ANTIGRAVITY_MEDIA_SMOKE_FILE | No | Optional path to a media file for media smoke tests. | |
| ANTIGRAVITY_MAX_MEDIA_FILE_MB | No | Maximum size in MB per input media file. | 250 |
| ANTIGRAVITY_MAX_MEDIA_TOTAL_MB | No | Maximum total size in MB across a request's media inputs. | 1024 |
| ANTIGRAVITY_MAX_INLINE_ARTIFACT_MB | No | Maximum size in MB for inline artifacts. | 12 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_accountA | Report the active Antigravity account identifier without reading or returning OAuth credentials or tokens. |
| list_modelsA | List models currently available to the active Antigravity account and show the configured quality, balanced, and fast routes. |
| doctorB | Check the Antigravity CLI, global worker state, and configured defaults. |
| start_media_analysisA | Analyze explicitly supplied images, PDFs, audio, video, documents, datasets, or other files with Antigravity's native multimodal capabilities. Inputs are copied into a per-run isolated Git workspace. |
| start_image_generationB | Generate one image with Antigravity's native generate_image tool and capture it in the persistent artifact ledger. |
| start_image_editA | Edit or transform one to five explicitly supplied reference images with Antigravity's native generate_image tool and capture the result. |
| get_media_runA | Read a multimodal run, optionally wait up to 30 seconds, and inline completed image or audio artifacts when small enough. |
| list_artifactsA | List generated media artifacts and their absolute paths, hashes, MIME types, and sizes from the global ledger. |
| start_analysisB | Start an asynchronous read-only Antigravity worker for bounded investigation or planning. |
| start_reviewA | Start an asynchronous read-only Antigravity worker to critically review code or a proposed change. |
| start_editA | Start an asynchronous Antigravity implementation worker in an isolated Git worktree. It cannot directly alter the active checkout. |
| get_runA | Read a worker run and optionally wait up to 30 seconds for progress or completion. |
| list_runsB | List recent Antigravity worker runs from the global operational ledger. |
| continue_runB | Continue a completed Antigravity conversation as a new asynchronous run in the same workspace or isolated worktree. |
| start_teamC | Start a queued multi-agent Antigravity team. Workers investigate in parallel, exchange reports through a lead coordinator, perform correction rounds, and finish awaiting independent Codex review. |
| get_teamA | Read a multi-agent team, optionally wait for progress, and optionally include its agent-to-agent transcript. |
| list_teamsA | List recent multi-agent teams from the persistent operational ledger. |
| message_agentA | Send a persisted message from Codex or one team member to another. Delivery continues the recipient's Antigravity conversation and records the reply. |
| team_dashboardB | Return a compact live dashboard snapshot with team progress, agent states, recent events, messages, and result preview. |
| cancel_teamA | Cancel all queued or running workers in a multi-agent team. |
| resume_teamA | Restart an interrupted or failed team from its original assignments, preserving a link to the prior team ledger. |
| cancel_runA | Request cancellation of an active Antigravity worker process. |
| apply_runA | Apply a successful edit worker's reviewed patch to its original Git checkout. Run only after Codex has inspected the patch and validation evidence. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Most tools are clearly separated by domain (account, models, media, runs, teams), but start_media_analysis vs start_analysis vs start_review vs start_edit could cause some confusion since all are 'start' actions on different worker types. The descriptions help distinguish them, though the media vs analysis boundary is slightly less obvious.
The naming is mostly consistent with verb_noun patterns: get_account, list_models, start_analysis, get_run, cancel_run, apply_run. Minor deviations exist: 'doctor' is a noun-only command, and 'team_dashboard' is noun-first rather than verb_noun, but the overall pattern is predictable.
23 tools is on the higher end but appropriate for a server covering account info, model listing, media generation/analysis, async runs, and multi-agent teams. Each tool serves a distinct operational purpose, though a few could be consolidated (e.g., team_dashboard vs get_team).
The surface covers the main lifecycle: starting runs, reading runs, continuing, cancelling, and applying edits; teams can be started, read, messaged, cancelled, and resumed. Minor gaps include no explicit tool for listing models' details beyond routes, no media cancellation, and no direct team result artifact listing, but core workflows are covered.