Antigravity Basics
Guides to the Antigravity IDE: installation and setup, basic operations, pricing plans, and comparisons with other AI IDEs for newcomers.
When Antigravity Says the Server Crashed Unexpectedly: Check the CPU, WSL, or Version First?
The editor opens but the agent dies right away with 'server crashed unexpectedly'. A short triage across three suspects, CPU AES support, WSL or SSH paths, and the app version, built from public forum and issue reports, with the unconfirmed parts marked as unconfirmed.
Before You Press Delete on an Antigravity Project, Can You Name Three Things That Stay?
Does deleting a project in Antigravity 2.0 remove your source code? A community explanation, split into its two storage locations, plus a read-only script and a safe order for freeing disk space.
Workflows Retire in 20 Days — What to Decide Before You Run /migrate-workflows
Workflows retire on November 1, 2026. Before you run the migration command, sort what to keep, merge, or set aside — and rewrite the one thing the command can't carry over: your descriptions.
Start Your Antigravity Deny List From Your Own Shell History
Before you let an agent drive your terminal, decide the first commands for the Deny list by counting your own shell history. A short script, a three-box sorting table, and a throwaway-repo test to confirm the rules actually bite.
I Counted My Rules Against the 20,000-Token Budget in Antigravity 2.17.0 Before Upgrading
Antigravity 2.17.0 gives rules their own 20,000-token budget. My six operating rule files came to 28,613 tokens, so the two largest would be demoted to pointers. Here is a small script to count yours first, and how I chose what to demote myself.
Wait or Pay When the Baseline Runs Out: Deciding Credit Overages Per Task
When your baseline quota is exhausted, one setting decides whether you wait for the refresh or spend purchased credits. Here is how I split attended work from unattended runs, and the small gate I put in front of the jobs nobody is watching.
When an agent ends without a reason, I check the page's character encoding first
A page handed to ReadURL can end an Antigravity agent with nothing but Agent execution terminated. Here is how I tell those pages apart before handing them over, and why I now fetch and re-encode first.
When You Cannot Decide Between Rules and Skills: Rethinking Where Instructions Live
Rules and Skills load at different moments in Antigravity. Rules go in full on every turn; Skills lead with a heading and load the rest on demand. After the same note drifted apart in two places on a client site, here are the questions I use to place an instruction, plus a small script to measure what you carry each turn.
Why Filename Search Misses Every Error String in Your Repo
Antigravity 2.12 improved partial filename search. Measuring name lookups against full-text search across a 2,088-file repository, the reading cost differed by 67x and error strings hit filenames only 4.5% of the time. Here is where the line actually falls.
Redrawing Your Workspace Boundary Now That Review Mode Auto-Approves Reads
Antigravity CLI 1.1.20 made in-workspace reads auto-approved in review mode. Here is what I found when I actually counted what became readable across two real working trees.
Choosing a Remote Control Host Machine Comes Down to Daemon Lifetime and Revocation Paths
What to settle before you flip on Remote Control in Antigravity 2.0: how the headless daemon behaves per OS, why there are two separate sign-out paths, and how to inventory the read surface on a candidate host machine.
Count What Writes Outside Your Workspace Before You Upgrade to CLI 1.1.14
Antigravity CLI 1.1.14 makes paths outside the workspace read-only by default. If your source assets and delivery targets live outside the repository, it is worth knowing what breaks before you upgrade. Here is a script that inventories your write targets, and the two ways it quietly undercounts them.
How Much Slower Search Gets When /codesearch Cannot Run ripgrep
Antigravity CLI 1.1.13 moved the bundled ripgrep binary, and /codesearch quietly falls back to local search when it cannot run. I measured the cost of that fallback on a real repository and wrote down how to tell which path your machine is on.
Deleting Duplicate Rows Will Not Shrink Your Antigravity CLI Conversation Database
A schema-agnostic way to audit conversation database growth, plus measurements showing why deletion reclaims nothing and why freelist_count is the wrong number to trust when you estimate how much you can get back.
Running Antigravity CLI 1.1.13 on a Machine You Cannot Sign In From
I put agy on a box with no browser and the sign-in screen stopped me cold. Here is how direct GEMINI_API_KEY auth from CLI 1.1.13 works, how to confirm it took effect, and why you should not hand it the key your app already uses.
Guarding the Turn Boundary in Non-Interactive Runs: A Command Table and a Fail-Closed Gate
A scheduled job meant only to record usage was calling the model on every run. Here is how I split commands into ones that start a turn and ones that do not, built a gate that refuses anything unclassified, and measured it against real scripts.
The Line I Thought Matched Nothing Was Approving Everything: Auditing Empty Allowlist Entries
Allowlist entries that decompose to zero command words matched every command and silently auto-approved it. Here is how I scanned my own config, separated the hole the fix closed from the one it did not, and rewrote matching to a prefix-token comparison.
The Hooks That Get Rejected Are the Cheap Ones: Measuring Matcher Reachability
Hook configurations that can never execute are now rejected at load time. But when I checked my own config against all 21 tool names, the real problems were on the side that passed. A static reachability checker, plus measured numbers on what over-matching actually costs.
I Copied the Same agent.md Into Another Repo and It Quietly Did a Different Job
CLI 1.1.6 lets you carry agent definitions around as files. I dropped one definition into eight repos, built a preflight that resolves its declared capabilities before the agent runs, and measured it against a naive checker.
The Flaky Hook Started Failing Every Time — Migrating to Declarative Sessions in the Antigravity SDK
Registering hooks after session init is gone, replaced by declaration at session creation. Here is what happened when I moved four agent definitions across, plus the harness I used to measure ordering non-determinism over 2,000 runs.
Who Approved the Right Side of &&? Splitting Shell Commands Before Matching Allow Rules
The approval dialog showed part of what actually ran. Here is a harness that splits compound shell commands without breaking quotes or command substitution, matches allow rules per segment, and the numbers from running it over 45 real commands.
Are You Actually Using Every Permission You Granted? Tightening Antigravity's Unified Permissions from Real Usage Logs
Once you flip a unified permission policy to 'allow everything,' unused grants quietly pile up. This is the grant-to-usage reconciliation loop: match granted permissions against your action logs, revoke what was never exercised, and narrow what's too broad — with working TypeScript and real numbers from solo operation.
Before Your Finger Learns the Approval Dialog: Folding Antigravity Permissions Into One Policy
Scattered approval dialogs, per-MCP allowlists, repeated re-auth. Built around Antigravity 2.2.1's unified permissions and OAuth keyring storage, here is how I fold every permission into a single policy and design away approval fatigue, with working code and measured numbers.
When a Stable Line and a Feature Line Ship Together, Which Build Should a Solo Operator Ride?
By shipping a 2.0 (stable) line and a 2.1 (feature) line in parallel, Antigravity now asks solo developers to decide which one to ride. Here is a design for selecting and switching builds without breaking your automation.
Point Real-Browser Self-Debug at a Throwaway Preview, Not Localhost or Production
Antigravity 2.0's real-browser self-debug is genuinely useful, but aim it at the wrong place and it touches production data. Here is a practical way to confine it to a per-branch throwaway preview and neutralize email, billing, and webhook side effects.
Riding Two Release Lines — Splitting Antigravity's 2.0 and 2.1 Tracks Between Unattended and Interactive Work
On July 1, Antigravity published 2.0-line and 2.1-line builds side by side. Here is a version policy that keeps unattended automation on the stable line and interactive work on the feature line, with a declaration file and drift detection.
Parallel Agents Multiply Artifacts Too — Designing Lifespans and Cleanup for Intermediate Outputs
Worktrees, screenshots, temp branches — parallel agents leave debris at parallel speed. A design for defining artifact lifespans and automating cleanup without ever destroying uncommitted work.
Don't Build Your Own Peak: Time-Spreading Background Agent Schedules
Antigravity 2.0's desktop auto-schedules tasks in the background. Convenient, but cluster them at round hours and you build your own peak, and the late-night jobs fail together. Here is a design that spreads times and bans overlap, with real results.
When Your MCP Servers Vanish From the Chat App in Antigravity 2.0
After Antigravity 2.0 split into an IDE and a separate chat-style agent app, an MCP server I had set up in the IDE stopped showing up on the chat side. Here is why the settings scopes are separate, and how to fix it by making a single workspace-level source of truth that both apps read.
Keep an Agent Running on a Nearly Empty Quota — Designing Graceful Degradation
When the monthly quota is almost gone, stopping the agent entirely is not the only option. Here is how to design graceful degradation — dropping capability one tier at a time while still producing valuable output — with policy code.
Antigravity and Gemini CLI — Why the June 2026 Sunset Changed the Comparison
Gemini CLI's consumer offering ended on June 18, 2026, and its terminal role passed to the Go-based Antigravity CLI. With the premise changed, here is how the two design philosophies differ and what to check before you migrate.
Combining All Four Antigravity Surfaces in One Project — Up to Running Your Own SDK Agent
How to split a single project across Antigravity 2.0, CLI, IDE, and SDK, and how to bridge between them — from diverging on design to converging on production, all the way to running a small custom agent with the Python SDK, with implementation included.
Before Your Antigravity Agents Fight Over the Same File — Ownership Manifests and Conflict Detection
Multi-agent workflows do not break at the design stage. They break at runtime. Here are the field notes: an ownership manifest that pins each agent's editable region, a git-only conflict detector, and a three-part handoff contract.
Antigravity 2.0, CLI, IDE, SDK — Weaving All Four Surfaces Through a Real Project
Antigravity ships as a desktop app, a CLI, an IDE, and a Python SDK. Beyond picking one, this guide shows how to weave all four across a single project — with a headless-execution wrapper for automation, plus the cost and migration traps to sidestep.
When the Default Model Changes Underneath You: Pinning and Diff-Gating Scheduled Runs
Antigravity 2.0 promoted Gemini 3.5 Flash to the default fast model. It is a welcome upgrade, but any scheduled run that leaned on the default starts producing subtly different output one morning. Here is how I pin the model explicitly, fingerprint the output, and gate drift, sized for a solo developer's pipeline.
When CLI, Desktop, and SDK Share One Agent Harness: Designing for Consistent Behavior
Now that Antigravity's CLI, desktop, and SDK share one agent harness, here is how to separate what stays consistent from what differs by environment, and how to align behavior with smoke tests and a version-tracking habit.
Migrating to Antigravity 2.0 Without Stopping Your Automation: Parallel-Run and Rollback Design
How to move to Antigravity 2.0 without breaking running automation: how to set up a parallel-run window, verify output parity, pin versions, and keep a one-command rollback path, based on migrating four sites one at a time.
Choosing Among Desktop, CLI, SDK, and Managed Agents for the Same Job
Antigravity 2.0 has several surfaces: desktop, CLI, SDK, and the Managed Agents API. Which one should run a given task? Here is a framework for choosing the surface from the nature of the work.
Antigravity vs Gemini Code Assist (2026): Which Google AI Coding Tool to Use?
Antigravity and Gemini Code Assist are both Google AI tools for developers, but they serve very different purposes. This guide breaks down the differences by features, cost, and use cases to help you choose — or use both together.
Antigravity vs OpenAI Codex: Which AI Coding Agent to Choose in 2026
Antigravity or OpenAI Codex? A hands-on 2026 comparison of architecture, features, pricing, and the clear cases where each wins — plus when it pays to use both.