📄 工具详情 ⚙️ 安装教程 📚 使用教程
能力标签
🤖 Agent🔄 工作流🌐 翻译🐳 Docker💻 CLI🔗 REST API🧠 Claude✨ GPT
Pi反重力轮转代理
⚙️
Agent工作流

Pi反重力轮转代理

基于 TypeScript · 无代码搭建完整 AI 自动化流程
英文名：pi-antigravity-rotator
⭐ 11 Stars 🍴 1 Forks 💻 TypeScript 📄 MIT 🏷 AI 7.5分
7.5AI 综合评分
多账户轮转代理管理AI工作流负载均衡
⬇ 下载源码 ZIP ⚙️ 配置说明
✦ AI Skill Hub 推荐

AI Skill Hub 推荐使用：Pi反重力轮转代理 是一款优质的Agent工作流。AI 综合评分 7.5 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。

📚 深度解析

Pi反重力轮转代理 是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升，基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化（模拟鼠标键盘操作），AI Agent 工作流通过理解任务意图、动态规划执行路径，能够处理更复杂的非结构化任务。

Pi反重力轮转代理 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。

在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 7.5 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

Pi反重力轮转代理 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

GitHub Stars
⭐ 11
开发语言
TypeScript
支持平台
Windows / macOS / Linux
维护状态
轻量级项目，按需更新
开源协议
MIT
AI 综合评分
7.5 分
工具类型
Agent工作流
Forks
1

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

Pi反重力轮转代理 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

📌 核心特色
  • 可视化 Agent 工作流编排，无需编写复杂代码
  • 支持多步骤自动化任务链，实现全流程无人值守
  • 与外部 API、数据库和第三方服务无缝集成
  • 内置错误处理与自动重试机制，保障稳定运行
  • 提供可复用的自动化模板，快速在同类场景部署
🎯 主要使用场景
  • 自动化日常重复性工作，将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同
以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。
安装命令
# 方式一：npm 全局安装
npm install -g pi-antigravity-rotator

# 方式二：npx 直接运行（无需安装）
npx pi-antigravity-rotator --help

# 方式三：项目依赖安装
npm install pi-antigravity-rotator

# 方式四：从源码运行
git clone https://github.com/tuxevil/pi-antigravity-rotator
cd pi-antigravity-rotator
npm install
npm start
📋 安装步骤说明
  1. 访问 GitHub 仓库获取工作流文件
  2. 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
  3. 上传工作流文件
  4. 按照提示配置必要的环境变量和 API Key
  5. 运行测试确认流程正常后投入使用
以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。
常用命令 / 代码示例
# 命令行使用
pi-antigravity-rotator --help

# 基本用法
pi-antigravity-rotator [options] <input>

# Node.js 代码中使用
const pi_antigravity_rotator = require('pi-antigravity-rotator');

const result = await pi_antigravity_rotator.run(options);
console.log(result);
以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。
配置示例
# pi-antigravity-rotator 配置说明
# 查看配置选项
pi-antigravity-rotator --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量（覆盖配置文件）
export PI_ANTIGRAVITY_ROTATOR_CONFIG="/path/to/config.yml"
📑 README 深度解析 真实文档 完整度 87/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

Pi Antigravity Rotator

Multi-account rotation proxy for Google Antigravity. Distributes API usage across multiple Google accounts with per-model routing, real-time quota tracking, automatic token management, and infringement detection.

⚠️ WARNING: Using this proxy may put connected Google accounts at risk of Terms of Service enforcement, including restriction, suspension, or permanent bans. Use at your own risk.

<details> <summary><strong>⚠️ Terms of Service Warning — Read Before Installing</strong></summary>

[!CAUTION] This is an unofficial tool and is not endorsed by Google. Routing traffic through this proxy may violate Google's Terms of Service or trigger automated abuse or policy enforcement systems. By using this proxy, you acknowledge: - Your account may be restricted, suspended, shadow-banned, or permanently banned - Multi-account rotation and proxying can increase account risk compared to normal interactive usage - You assume all responsibility for the accounts and traffic routed through this tool Recommendation: Do not use your primary Google account. Prefer disposable or lower-risk accounts, and keep account exposure conservative.

</details>

v2.0 Highlights

  • Full dashboard config editor with import/export.
  • Official Docker and compose deployment.
  • pi-antigravity-rotator doctor for config/state validation.
  • Optional account tier metadata and runtime healthScore.
  • Strong security warnings when admin routes are open without PI_ROTATOR_ADMIN_TOKEN.

Features

  • Compatibility Adapters -- Includes standard OpenAI-compatible /v1/chat/completions and Anthropic-compatible /v1/messages APIs. Features comprehensive OpenAI Responses API compatibility (/v1/responses), enabling seamless integration with advanced agentic systems like Codex.
  • Per-model routing -- Each model (Gemini Pro, Flash, Claude) routes to its own active account independently. Multiple agents using different models won't interfere with each other.
  • Real-time quota monitoring -- Polls Google's quota API every 5 minutes to track remaining usage per model per account
  • Per-model timer tracking -- Timer classification (fresh/7d/5h) is evaluated per model using each model's actual resetTime from the quota API, not a per-account estimate
  • Smart rotation -- Rotates only the specific model whose quota dropped, leaving other models on their current accounts
  • Infringement detection -- On 403 with infringement/abuse/suspension keywords, the account is immediately flagged and excluded from routing
  • Safer 429 handling -- On provider 429, stops the current request and avoids cascade-burning sibling accounts
  • Concurrency guardrails -- Limits each account to one in-flight request by default to avoid bursty pressure
  • Operator fresh-window controls -- You can block new fresh window starts globally, then selectively allow specific accounts to override that policy
  • Protective pause -- Pauses all routing for several hours after serious ToS/abuse-style flags so the rest of the pool is not burned
  • Token auto-refresh -- Tokens are refreshed automatically before expiry; no manual management
  • Endpoint cascade -- Tries daily, autopush, and prod API endpoints for resilience
  • Advanced Telemetry & Statistics -- Track exactly how much USD you save compared to a paid API plan, predict quota depletion with the Forecast grid, view Latency tracking (p50/p95), and explore 60-day historical usage heatmaps
  • Web dashboard -- Real-time view of model routing table, per-account quota bars with per-model timers, and flagged account alerts
  • Auto-update notifications -- The dashboard checks npm for new releases every 30 minutes and shows a banner with one-click update when a newer version is available
  • Broadcast notifications -- Operator-controlled announcements and alerts delivered directly to the dashboard
  • State persistence -- Survives restarts; routing assignments, per-model request counters, cooldowns, and flags are saved to disk

Features Enabled for Codex Agents

  • Native Reasoning Visibility: If using models with thinking enabled (e.g., gemini-3.5-flash-high), interleaved reasoning/thinking blocks are streamed back in real-time as OpenAI reasoning_content chunks. This lets Codex inspect the model's inner thoughts before it acts.
  • Function / Tool Routing: Function calls emitted by Codex are fully translated to Gemini functionCalls and returned back to Codex safely, enabling full agentic capabilities. Multi-turn tool conversations work correctly for all models including Claude (claude-sonnet-4-6, claude-opus-4-6-thinking) — parallel tool calls are batched into a single turn and tool results are properly grouped to satisfy Claude's strict tool_use/tool_result ordering requirements.
  • Strict Validation: The rotator strictly validates the Responses input contract and rejects unsupported tools (e.g., web_search) proactively to ensure Codex doesn't hit unexpected runtime exceptions.

Optional: require this token for dashboard/API access. If unset, legacy open access is preserved.

export PI_ROTATOR_ADMIN_TOKEN="change-me"

Option A: Install from npm

```bash npm install -g pi-antigravity-rotator

Option C: Docker

docker compose up -d

The included compose file persists runtime data under ./docker-data and sets PI_ROTATOR_DIR=/data.

Quick Start

Option B: Clone from source

```bash git clone https://github.com/tuxevil/pi-antigravity-rotator.git cd pi-antigravity-rotator npm install

Configuration

Config files (accounts.json, state.json) are stored in ~/.pi-antigravity-rotator/ by default. Override with:

```bash

Environment variables

export PI_ROTATOR_DIR=/path/to/config export PI_ROTATOR_QUOTA_USER_AGENT="antigravity/1.107.0 darwin/arm64"

Optional: bind the proxy to a safer local-only interface.

export PI_ROTATOR_BIND_HOST="127.0.0.1"

Optional: max accepted proxy request body size in bytes. Default: 26214400 (25 MiB).

export PI_ROTATOR_MAX_BODY_BYTES=26214400

Optional: log verbosity. One of debug, info, warn, error, silent. Default: info.

export PI_ROTATOR_LOG_LEVEL=info

Optional override for Antigravity UA version used by quota fetches

export PI_AI_ANTIGRAVITY_VERSION=1.107.0

Options

FieldDefaultDescription
proxyPort51200Port the proxy listens on
requestsPerRotation5Max per-model requests before attempting request-count rotation
rotateOnQuotaDrop20Rotate when a model's quota drops this many %. Set to 0 to disable
quotaPollIntervalMs300000Quota poll interval in ms (5 minutes)
maxConcurrentRequestsPerAccount1Max simultaneous requests allowed per account
maxConcurrentRequestsPerProjectModel1Max simultaneous requests allowed across accounts sharing the same projectId for the same quota model
projectCircuitBreaker429Threshold3Unique accounts from the same projectId that must hit provider 429 before pausing that project/model
projectCircuitBreakerWindowMs600000Rolling window for the project/model 429 circuit breaker
projectCircuitBreakerCooldownMs3600000Minimum project/model pause after the circuit breaker trips
modelCircuitBreaker429Threshold3Unique accounts across all projects that must hit provider 429 for the same quota model before pausing that model globally
modelCircuitBreakerCooldownMs21600000Minimum model-wide pause after the global model circuit breaker trips
dailyAccountSlowRequests250Daily upstream attempts per account before slow-mode jitter starts
dailyAccountStopRequests350Daily upstream attempts per account before routing stops for that account until the next UTC day
dailyProjectSlowRequests900Daily upstream attempts per projectId before slow-mode jitter starts
dailyProjectStopRequests1200Daily upstream attempts per projectId before routing stops for that project until the next UTC day
slowModeJitterMinMs8000Minimum slow-mode delay before upstream request
slowModeJitterMaxMs25000Maximum slow-mode delay before upstream request
protectivePauseMs21600000Global routing pause after a serious provider enforcement signal
useRequestCountRotationWhenQuotaUnknownOnlytrueUse request-count rotation only until quota telemetry exists for the request's model. Set to false to keep rotating by request count even with known quotas

Configuration for Codex

To connect Codex to your local rotator:

1. Configure the API Base URL: In Codex settings (e.g. in your .codex config or VS Code configuration), set the OpenAI API base URL to point to your rotator's compatibility adapter: 

   "codex.openai.apiBase": "http://localhost:51200/v1"
(Or set the environment variable OPENAI_BASE_URL=http://localhost:51200/v1 in the workspace shell).

2. Set the API Key / Admin Token: If you have set a PI_ROTATOR_ADMIN_TOKEN for your rotator, configure that token as the API key. Otherwise, any non-empty placeholder string (e.g., sk-antigravity) works: 

   "codex.openai.apiKey": "your-rotator-admin-token-here"
(Or set the environment variable OPENAI_API_KEY=... in the shell).

3. Select a Supported Model: Configure Codex to target one of the following models supported by the rotator (which will be mapped to the best available Google Antigravity account/model under the hood): - gemini-3.5-flash or gemini-3.5-flash-high / gemini-3.5-flash-low / gemini-3.5-flash-medium (Recommended for fast general reasoning) - gemini-3.1-pro or gemini-pro-agent / gemini-3.1-pro-high / gemini-3.1-pro-low (For deep reasoning) - claude-sonnet-4-6 or claude-opus-4-6-thinking (Claude models via Vertex AI) - gpt-oss-120b or gpt-oss-120b-medium (Open-source GPT model)

Example Codex configuration entry: 

   "codex.model": "gemini-3.5-flash-high"

Or CLI flag

pi-antigravity-rotator start --config-dir /path/to/config ```

New v2.0 config fields:

  • bindHost: interface to bind on. Default: 0.0.0.0.
  • routingPolicy: current default is timer-first. Optional values now include tier-first, quota-first, and hybrid.
  • tokenBucketEnabled: enables the local per-account request bucket used by hybrid. Default: false.
  • tokenBucketMaxTokens: bucket capacity when enabled. Default: 50.
  • tokenBucketRefillPerMinute: refill speed when enabled. Default: 6.
  • tokenBucketInitialTokens: startup fill level when enabled. Default: 50.
  • accounts[].tier: optional ultra, pro, free, or unknown.

API Endpoints

MethodPathDescription
GET/dashboardWeb dashboard
GET/loginHosted account-link landing page
GET/api/statusJSON status: accounts, quotas, model routing, flags
POST/api/enable/<email>Re-enable a disabled account after its underlying issue is fixed
POST/api/settings/fresh-window-starts/onAllow opening new idle/fresh windows globally
POST/api/settings/fresh-window-starts/offBlock opening new idle/fresh windows globally
POST/api/account-fresh-window-starts/<email>/onAllow one account to override the global fresh-window block
POST/api/account-fresh-window-starts/<email>/offReturn one account to the global fresh-window policy
POST/api/self-updateTrigger npm self-update to latest version (admin-only)
POST/v1internal:streamGenerateContentNative Antigravity proxy endpoint (used by pi)
GET/v1/modelsOpenAI-compatible model list
POST/v1/responsesOpenAI Responses-compatible create endpoint
GET/v1/responses/<id>Retrieve stored Responses result
DELETE/v1/responses/<id>Delete stored Responses result
POST/v1/responses/<id>/cancelCancel an in-progress stored Responses result
GET/v1/responses/<id>/input_itemsList stored input items for a Responses result
POST/v1/chat/completionsOpenAI-compatible non-streaming chat adapter
POST/v1/messagesAnthropic-compatible non-streaming messages adapter

If PI_ROTATOR_ADMIN_TOKEN is set, dashboard/API requests must include either Authorization: Bearer <token>, X-Rotator-Admin-Token: <token>, or ?token=<token> for browser dashboard access. The native pi proxy endpoint and compatibility adapters remain unauthenticated so existing clients keep working. Put this service behind a trusted local boundary if exposing beyond localhost/LAN.

Endpoint

Telemetry posts to:

http://telemetry.dragont.ec:3800/v1/events

Connecting Codex / VS Code Agents

pi-antigravity-rotator can act as the multi-account rotation backend for agentic frameworks, including Codex executing in VS Code or in the terminal.

Since Codex uses the standard OpenAI Responses API, it can seamlessly route its developer-agent workflows through the rotator.

Troubleshooting

Account shows flagged status Google detected potential abuse or enforcement. Review the error message on the dashboard and resolve the provider-side block first. Flagged accounts are quarantined and are not re-enabled through /api/enable/<email> until the underlying provider issue is cleared by replacing or restoring the account.

Account keeps getting disabled after 5 errors Check the error message. Common causes: revoked OAuth consent, expired refresh token (re-run npm run login), or Google account suspension.

Quota bars not showing Quota data appears after the first poll cycle (up to 5 minutes). Ensure accounts have valid tokens.

All accounts exhausted If the outage is temporary (cooldown, model breaker, or protective pause), the proxy returns 429 with Retry-After and retryAfterMs; clients must back off. The proxy returns terminal 503 only when there is no known retry time, for example all accounts are disabled/flagged.

Multiple agents on different models This is fully supported. Each model routes independently. Agent 1 using Gemini Pro and Agent 2 using Claude will each have their own active account and won't interfere with each other's rotation.

🇨🇳 中文文档镜像 AI 翻译 2026-05-28
英文原文章节由系统翻译为中文摘要，便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

Pi Antigravity Rotator 是专为 Google Antigravity 设计的多账号轮询代理工具。它能够将 API 请求智能分发至多个 Google 账号，支持按模型路由、实时配额追踪、自动 Token 管理以及违规检测功能。通过该工具，开发者可以实现高效的资源调度，但需注意，使用此类代理可能会面临 Google 服务条款（Terms of Service）的限制或封禁风险。

⚡ 功能介绍

v2.0 版本带来了重大升级，包含支持导入/导出的全功能 Dashboard 配置编辑器，并提供官方 Docker 和 Docker Compose 部署支持。系统内置 `pi-antigravity-rotator doctor` 命令用于校验配置与状态。在兼容性方面，它不仅支持 OpenAI 兼容的 `/v1/chat/completions` 和 Anthropic 兼容的 `/v1/messages` API，还通过 OpenAI Responses API 兼容性实现了对 Codex 等高级 Agent 系统的无缝集成。此外，针对具备推理能力的模型，系统支持将推理过程以 `reasoning_content` 形式实时流式传输。

📋 环境依赖

在使用前，建议配置 `PI_ROTATOR_ADMIN_TOKEN` 环境变量以确保 Dashboard 和 API 访问的安全。若未设置该 Token，管理路由可能会处于开放状态，存在安全风险。

🛠 安装步骤（Docker/pip/源码）

项目支持多种安装方式：1. 通过 npm 全局安装：`npm install -g pi-antigravity-rotator`；2. 通过源码安装：克隆仓库后执行 `npm install`；3. 使用 Docker 部署（推荐）：通过 `docker compose up -d` 快速启动，系统会自动将运行时数据持久化至 `./docker-data` 目录，并将 `PI_ROTATOR_DIR` 设置为 `/data`。

🚀 使用教程

项目提供了 Quick Start 快速入门指南，帮助开发者快速完成从安装到运行的流程。对于高级用户，可以通过 CLI 参数 `--config-dir` 指定特定的配置目录来启动服务。

⚙️ 配置说明（含 MCP / env）

配置文件（如 `accounts.json` 和 `state.json`）默认存储在 `~/.pi-antigravity-rotator/`。开发者可以通过环境变量 `PI_ROTATOR_DIR` 自定义配置路径，或使用 `PI_ROTATOR_QUOTA_USER_AGENT` 修改 User-Agent。v2.0 版本新增了 `routingPolicy` 参数，支持 `timer-first`、`tier-first`、`quota-first` 及 `hybrid` 等多种路由策略，并可通过 `tokenBucketEnabled` 启用令牌桶限流机制。

🔌 API 说明

系统提供了一系列 API 端点用于管理和监控：`/dashboard` 用于访问 Web 管理面板；`/login` 提供账号绑定落地页；`/api/status` 返回包含账号、配额及模型路由状态的 JSON 数据；`/api/enable/<email>` 用于重新启用被禁用的账号。此外，系统支持将遥测数据（Telemetry）发送至指定的远程端点。

❓ FAQ 摘要

针对常见问题，若账号显示为 `flagged` 状态，通常意味着 Google 检测到了潜在的滥用行为。此类账号会被隔离（Quarantine），在解决供应商端的底层问题之前，无法通过 `/api/enable/<email>` 接口直接重新启用。建议开发者定期通过 Dashboard 查看具体的错误信息并进行排查。

🎯 aiskill88 AI 点评 B 级 2026-05-27

创新的多账户轮转方案，解决AI应用的扩展性问题。代码质量良好，但生态还需完善，维护频率有待提升。

📚 实用指南（长尾问题）
适合谁
  • 构建多智能体协作系统的 Agent 开发者
  • 跨境业务、多语言内容运营团队
最佳实践
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
部署方案
  • Docker：pi-antigravity-rotator 提供官方镜像，docker compose up 一键启动
  • CLI：直接 npm install -g / pip install，命令行调用
  • 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
pi-antigravity-rotator 中文教程pi-antigravity-rotator 安装报错怎么办pi-antigravity-rotator Docker 部署pi-antigravity-rotator Agent 工作流pi-antigravity-rotator 与同类工具对比pi-antigravity-rotator 最佳实践pi-antigravity-rotator 适合谁用

⚡ 核心功能

👥 适合谁
  • 构建多智能体协作系统的 Agent 开发者
  • 跨境业务、多语言内容运营团队
⭐ 最佳实践
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal

👥 适合人群

自动化工程师和运维人员项目经理和业务分析师希望减少重复性工作的专业人士数字化转型团队

🎯 使用场景

  • 自动化日常重复性工作，将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同

⚖️ 优点与不足

✅ 优点
  • +MIT 协议，可免费商用
  • +大幅减少重复性人工操作
  • +可视化流程，清晰直观
  • +可扩展性强，支持复杂场景
⚠️ 不足
  • −初始配置和调试需投入一定时间
  • −强依赖外部服务的稳定性
  • −复杂场景需具备一定技术基础
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。

🔗 相关工具推荐

LangFlow 可视化AI开发
Agent工作流
ragflow Agent工作流
RAGFlow是领先的开源检索增强生成(RAG)引擎,提供完整的AI工作流和智能体框架。支持agentic检索和搜索,适
Claude编码最佳实践
一套开源AI工作流框架，指导开发者从随意编码升级到专业智能体工程实践。通过实战示例和最佳实践，帮助AI工程师、提示词工程
Flowise 可视化AI工作流
Agent工作流
📚 相关教程推荐
MCP 工作流生产级配置方案：从开发环境到团队共享
帮助中心 · AI Skill Hub
MCP 工作流生产级配置方案：从开发环境到团队共享
帮助中心 · AI Skill Hub
MCP 工作流生产级配置方案：从开发环境到团队共享
帮助中心 · AI Skill Hub
MCP 工作流生产级配置方案：从开发环境到团队共享
帮助中心 · AI Skill Hub
📰 相关 AI 新闻
GPT-5.5 最新进展与分析
AI 资讯 · 知识关联
前沿 AI 研究论文速览
AI 资讯 · 知识关联
前沿 AI 研究论文速览
AI 资讯 · 知识关联
AI Agent 自主化能力最新进展
AI 资讯 · 知识关联
🍿 AI 圈相关吃瓜
AutoGPT 自主完成了任务：把我的文件夹全部重命名了
AI 圈观察
Claude 回复了30页，我只问了"你好"
AI 圈观察
Agent 帮我订了3次机票，全部是同一天的
AI 圈观察
🗺️ 相关解决方案
agent
ai-agent-workflow
workflow
ai-workflow-templates
translation
ai-translation-pipeline
docker
docker-deploy
🧩 你可能还需要
基于当前 Skill 的能力图谱，自动补全的工具组合
技能寻求者
MCP · Agent · 工作流
gptme Agent工作流
MCP · Agent · 工作流
natively-cluely-ai-assistant — Claude Skill 中文使用文档
免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。
CrewAI 多代理协作平台
MCP · Agent · 工作流
LEANN AI技能包
MCP · Agent · 工作流
Synthadoc
MCP · Agent · 工作流

❓ 常见问题 FAQ

pi-antigravity-rotator 是一款TypeScript开发的AI辅助工具。开源AI工作流：Intelligent multi-account rotation proxy for Google Antigravity with per-model r。⭐11 · TypeScript 主要应用场景包括：Google Antigravity多账户管理、AI模型请求分配、企业级代理部署。
💡 AI Skill Hub 点评

总体来看，Pi反重力轮转代理 是一款质量良好的Agent工作流，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习 Pi反重力轮转代理
查看分步骤安装教程和完整使用指南，快速上手这款工具
⚙️ 安装教程 📚 使用教程
🌐 原始信息
原始名称 pi-antigravity-rotator
原始描述 开源AI工作流：Intelligent multi-account rotation proxy for Google Antigravity with per-model r。⭐11 · TypeScript
Topics 多账户轮转代理管理AI工作流负载均衡
GitHub https://github.com/tuxevil/pi-antigravity-rotator
License MIT
语言 TypeScript
🔗 原始来源
🐙 GitHub 仓库  https://github.com/tuxevil/pi-antigravity-rotator

收录时间：2026-05-27 · 更新时间：2026-05-30 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。