lbjlaq/antigravity-manager

Overview

Your personal high-performance AI scheduling gateway is not just account management, but the ultimate solution to break down API call barriers. It is a full-featured desktop application designed specifically for developers and AI enthusiasts. It perfectly combines multi-account management, protocol conversion, and intelligent request scheduling to provide you with a stable, fast, and cost-effective experience. Through this application, you can convert common web sessions (Google/Anthropic) into standardized API interfaces, eliminating protocol gaps between different vendors. *: Language servers (LSPs) designed specifically for AI protocols, providing you with smarter code completion, diagnostics, and protocol debugging experiences. * : Instantly gain insight into the health status of all accounts, including Gemini Pro, Gemini Flash, Claude, and Gemini Drawing. * : The system filters and recommends "best accounts" in real time based on the redundancy of current account quotas, supporting . * : Visually displays the specific quota percentages and last sync time of active accounts. * : When adding an account, a copyable authorization link is generated in advance, supporting authorization from any browser; After a successful callback, the app will automatically complete and save (if necessary, click "I have authorized, continue" to manually finish). * : Supports single token entry, batch JSON import (such as backups from other tools), and automatic hot migration from old V1 database versions. * : Supports dual view switching between "list" and "grid." Provides 403 block detection, automatically labeling and bypassing accounts with privilege issues. * : * : Provides /v1/chat/completions endpoints, compatible with 99% of existing AI applications. * : Provides native /v1/messages interface, supporting full functionality (such as Chain of Thought and system prompts). * : Supports direct calls from Google's official SDK. * : When a request encounters 429 (Too Many Requests) or 401 (Expire), the backend triggers it in milliseconds, ensuring uninterrupted business. * : You can classify complex raw model IDs into the "specification family" (such as routing all GPT-4 requests uniformly to gemini-3-pro-high). * : Supports custom regular expression-level model mappings to precisely control the implementation model for each request. * : [New] The system automatically prioritizes accounts based on account type (Ultra/Pro/Free) and quota reset frequency, prioritizing high-speed account reset consumption to ensure service stability under high-frequency calls.

Overview (machine translated)

This page was translated automatically. Technical details may differ from the original.

Recommended Tools

Try a different keyword or remove a filter.

Install