by ShawTim
Zero-dependency native Gemini HTTP/2 gateway & in-process Pi extension (pi-gemini-app) connecting Gemini subscriptions to OpenAI-compatible coding agents (Cursor, Cline, Codex, Pi) with multi-account pooling.
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
# Add to your Claude Code skills
git clone https://github.com/ShawTim/gemini-app2apiGuides for using ai agents skills like gemini-app2api.
See how gemini-app2api compares with popular alternatives.
Your coding agents. Your Gemini subscriptions. One zero-dependency native HTTP/2 gateway.
Connect your own eligible Gemini accounts to OpenAI-compatible IDEs, CLI agents, and SDKs through a self-hosted Node.js gateway—featuring incremental SSE, caller-owned tool validation, multi-account failover, and a bilingual operations console—or run our standalone zero-dependency in-process extensions (pi-gemini-app for Pi / GooeyPi and openclaw-gemini-app for OpenClaw) with no gateway server required.
English · 繁體中文 · Quick Start · Pi Extension · OpenClaw Plugin · Connect Your Client · API Reference · Operations
[!IMPORTANT] Unofficial interoperability research project. Not affiliated with, endorsed by, or sponsored by Google. Using third-party clients or gateways may violate Google's Terms of Service—your accounts, your responsibility. You must sign in personally with your own eligible Google accounts; no user credentials, tokens, accounts, or Google binaries are distributed. Read the full Disclaimer.

Ever noticed how Gemini can feel constrained inside the consumer Gemini App—losing thread context or struggling to drive multi-step local engineering workflows? The bottleneck is rarely the base model; it is the consumer chat harness wrapped around it.
/v1/chat/completions and /v1/responses endpoints—or install the standalone native in-process Pi extension (pi install npm:pi-gemini-app) for Pi Coding Agent & GooeyPi with zero gateway server required.node:http2, node:crypto), without headless browsers, cookie scraping, or patching local desktop binaries.| Dimension | Gemini App2API | Web / Cookie Scrapers | Desktop App Injection / MITM |
|---|---|---|---|
| Transport | Direct native HTTP/2 (ProcessQuery) + resumable image upload |
Fragile web DOM or reverse-engineered browser cookies | Binary hooks or local traffic interception |
| Auth lifecycle | Standard Google OAuth + refresh tokens in 0600 local state |
Frequent cookie expiration & CAPTCHA friction | Coupled to a single running desktop GUI session |
| Tool calling | Schema-validated prompt protocol + Responses namespace support |
Unvalidated text regex or unsupported | Limited to built-in consumer UI capabilities |
| Multi-account | Pooled routing, soft session affinity, batch usage & tier telemetry | Manual cookie swapping | Single active desktop user |
| Runtime footprint | Pure Node.js >= 22, 0 production npm dependencies |
Playwright / Puppeteer / heavy Python stacks | OS-specific app bundle & binary version lock |
Chat & Responses): Supports GET /v1/models, POST /v1/chat/completions, and POST /v1/responses with JSON or incremental SSE streaming, Structured Outputs (json_schema and json_object via Chat response_format and Responses text.format, schema-validated before delivery), native_search public-web url_citation annotations, reasoning_effort / reasoning.effort mapping, and static PNG/JPEG/WebP image input.type: "namespace" groups), execute approved calls locally, and replay results. The gateway validates every tool name and argument schema before emission—never executing shell commands or touching your workspace.0700/0600 private state permissions, scrypt admin password hashing, SHA-256 API key lookup digests with 0600 private-state key storage (returned only at creation or via authenticated CSRF-protected reveal requests), strict Origin/Host/X-CSRF-Token admin protections, and SSRF-guarded opt-in remote image fetching.English / 繁體中文): Inspect pool pulse, request-latency snapshot sparklines, and metadata-only per-account × per-model telemetry (gemini-neon, gemini-hydrogen, gemini-flash-lite provider-attempt counters—including failover/recovery retries and explicit account tests—output bytes, retries, soft-errors, and error categories, with zero prompt logging) across /admin Overview and the slide-over account inspector drawer; review per-account Current usage / Weekly limit bars and model states, copy ready-to-paste client configs (Codex CLI, Cline, cURL), manage copyable client API keys, explicitly review or accept Gemini Terms of Service, and inspect sanitized HTTP/gRPC diagnostics across desktop and mobile.| Light Theme — Account Inspector & Pool Pulse | Mobile Console — Traditional Chinese (繁體中文) |
|---|---|
![]() |
![]() |

[!TIP] Using Pi Coding Agent or GooeyPi? No gateway server required. Install the standalone zero-dependency native HTTP/2 extension directly from npm (
pi-gemini-app) or Pi Marketplace—zero local HTTP proxy or Docker container needed:pi install npm:pi-gemini-appRun
/login gemini-appand/gemini-quotainside Pi or GooeyPi. Subscription tier is detected automatically viaGetUsageInfo: Free Google accounts automatically filter togemini-auto(Smart Model Selection), while AI Plus / Pro / Ultra accounts exposegemini-neon,gemini-hydrogen,gemini-flash-lite, andgemini-auto(gemini-argontemporarily aliases togemini-neon). Full guide:extensions/pi/README.md.
[!TIP] Using OpenClaw? No gateway server required. Install the standalone zero-dependency npm (
openclaw-gemini-app) provider plugin (extensions/openclaw/), sharing the same direct HTTP/2 transport,HTTPS_PROXYsupport, 15sPINGkeepalives, OAuth login (local browser & remote VPS), and/usage+/gemini-quotaintegration:openclaw plugins install npm:openclaw-gemini-appRun
openclaw models auth login --provider gemini-app, then selectgemini-app/gemini-neonorgemini-app/gemini-hydrogen. Full guide:extensions/openclaw/README.md.
>= 22.0.0) on macOS, Linux, or Windows WSL2 — or Docker Compose (Windows, macOS, Linux).Option A — Node.js (macOS / Linux / WSL2):
git clone https://github.com/ShawTim/gemini-app2api.git
cd gemini-app2api
npm ci --omit=dev --ignore-scripts
# Optional: create a private 0600 .env without overwriting an existing one:
test -e .env || (cp .env.example .env && chmod 600 .env)
# Edit .env to set GATEWAY_ADMIN_PASSWORD (12–256 chars) if desired; leave blank for loopback-only access.
npm start
Option B — Docker Compose (Windows / macOS / Linux):
``
gemini-app2api is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ShawTim. Zero-dependency native Gemini HTTP/2 gateway & in-process Pi extension (pi-gemini-app) connecting Gemini subscriptions to OpenAI-compatible coding agents (Cursor, Cline, Codex, Pi) with multi-account pooling. It has 60 GitHub stars.
gemini-app2api's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/ShawTim/gemini-app2api" and add it to your Claude Code skills directory (see the Installation section above).
gemini-app2api is primarily written in JavaScript. It is open-source under ShawTim on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh gemini-app2api against similar tools.
No comments yet. Be the first to share your thoughts!