Antigravity CLI vs Letta

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.

Letta 60

No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.

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.

Letta 35

Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is unrestricted; standard, acceptEdits and strict are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.

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.

Letta 85

v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.

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.

Letta 58

Local-software lines, read for the harness. @letta-ai/letta-code on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.

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.

Letta 67

Harness reading. Toolsets switch with /model, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). letta -p --output-format json for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.

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.

Letta 70

Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an applies_to block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.