omnirush2api

v1.0.1

Published

13 days ago

OAuth to OpenAI-compatible API router for Omnirush.ai models

0High
0Medium
0Low

its_rovoid

omnirush openai oauth router proxy cloudflare-workers reverse-proxy gpt-6-astra gpt-6-sol

Omnirush2API

Overview • Features • Quick Start • Models • Clients • Architecture • Guides • Disclaimer • License

What is Omnirush2API?

Omnirush.ai provides powerful frontier models including GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Sol, delivering deep reasoning, intelligent coding agents, and high-throughput responses through its desktop platform.

However, access to Omnirush quotas is locked behind OAuth device authentication within the official desktop client. Developers could not consume these models as standard OpenAI-compatible endpoints (sk-...) in third-party coding agents, test harnesses, or external IDEs.

Omnirush2API bridges this gap:

It integrates with Omnirush's OAuth Device Flow (omnirush2api login) and automatically auto-discovers local credentials from the official desktop app on Windows, macOS, and Linux, proactively rotating access tokens before expiration.
It serves a standard OpenAI-compatible gateway (/v1/chat/completions, /v1/responses, /v1/models, /v1/health) with Server-Sent Events (SSE) streaming and deep thinking reasoning preservation (delta.reasoning_content).
It supports both a zero-dependency Local CLI Daemon (localhost:20129) and a standalone Cloudflare Worker (worker/worker.js) with multi-account round-robin rotation and automated 429 quota exhaustion fallback.

Disclaimer: This tool is provided strictly for personal educational and interoperability testing purposes. Extracting or reusing OAuth credentials outside official clients carries the risk of account suspension or ban. See Disclaimer & Legal Notice.

Key Features

Unlock Omnirush Frontier Models: Access gpt-6-astra (flagship reasoning), gpt-6.1-sol (advanced coding), and gpt-6-sol (fast iterations).
Dual Operational Modes:
- Local Daemon: Runs on localhost:20129, auto-detecting desktop credentials with zero configuration.
- Cloudflare Worker: Standalone 24 KB bundle ready for copy-paste deployment into Cloudflare Workers or Vercel Edge.
Interactive Terminal Device Flow (omnirush2api login): Log into Omnirush directly from the command line without opening or configuring third-party app stores.
Desktop Credential Auto-Discovery: Automatically finds tokens stored in Windows %APPDATA%\OmniRush\credentials, macOS Keychain / app support, and Linux configs.
Multi-Account Round-Robin: Pool multiple refresh tokens; requests distribute automatically across accounts.
Intelligent 429 Failover: Automatically detects rate limits and quota caps (Retry-After), parks the exhausted account in cooldown, and retries the request transparently with the next ready account.
Streaming SSE with Reasoning Delta: Preserves thinking blocks in delta.reasoning_content for real-time rendering in coding assistants.
Anti-Ban Wire Guard & Signature Masquerading:
- Emulates official OmniRush Electron desktop client headers (User-Agent: OmniRush/1.2.4, Sec-Ch-Ua, Sec-Fetch-*).
- Zero unofficial client signature leaks (strips custom headers; generates realistic device hostnames like DESKTOP-XXXXXX).
- Per-account concurrency locks prevent overlapping requests from triggering "simultaneous sign-in from another place" detection.
- Automated ban detection permanently quarantines closed/suspended accounts from the pool to protect remaining accounts.
Safe & Resource-Bounded:
- Client disconnect cancellation via AbortSignal (prevents wasted quotas when cancelling prompts).
- 120-second upstream timeout guards against stalled connections.
- 25MB request payload limit protects against buffer exhaustion attacks.
- Atomic token persistence using secure 0o600 file permissions.

How to Get Your Refresh Token

Omnirush uses OAuth 2.0 refresh tokens to authorize API requests. You can obtain your refresh token automatically using the built-in login script, or extract it from the OmniRush Desktop app.

1. Automated Script (Recommended - 1-Click Login)

The easiest way to get your refresh token is to run the automated login script:

npm run login

Or using the CLI:

node dist/cli.js login

Or directly via npx:

npx omnirush2api login

What the script does automatically:

Requests an official OAuth Device Authorization session from Omnirush.
Automatically launches your default web browser to the verification page with your code pre-filled.
Polls the backend securely in the background while you click "Authorize" in the browser.
Once authorized, prints your full refresh token in the terminal so you can easily copy it for Cloudflare Workers.
Automatically saves the token to ~/.omnirush2api/tokens.json for the local daemon.

================================================================================
🎉 Omnirush OAuth Login Successful!
================================================================================

Your Refresh Token (Copy this for Cloudflare Worker secret OMNIRUSH_REFRESH_TOKEN):
--------------------------------------------------------------------------------
omni_ref_a1b2c3d4e5f6...
--------------------------------------------------------------------------------

✓ Account:          [email protected] (active)
✓ Tokens Remaining: 4,875,000
✓ Saved to Disk:    ~/.omnirush2api/tokens.json

2. For Method 1: Local Daemon

When running the Local Daemon, getting and managing the refresh token is completely automatic:

Option A (Interactive Login): Run npm run login or node dist/cli.js login. The token is automatically persisted to ~/.omnirush2api/tokens.json. You can start the daemon immediately with node dist/cli.js start.
Option B (Auto-Discovery from Desktop App): If you already have the official OmniRush Desktop app installed and signed in, Omnirush2API automatically discovers your existing session from your system with zero setup. Run node dist/cli.js check to verify detection.

Option C (Environment Variable): Export the token directly:

export OMNIRUSH_REFRESH_TOKEN="omni_ref_your_token_here"
node dist/cli.js start

3. For Method 2: Cloudflare Workers (Serverless)

When deploying to Cloudflare Workers, Omnirush enforces single-use Refresh Token Rotation (RTR). To ensure isolates don't invalidate refresh tokens on cold starts, use the token pair format:

Obtain the token pair: Run the interactive login script:
```
npm run login
```
The script outputs Option A: Cloudflare Worker Secret (Recommended Pair):
```
omr_your_refresh_token|omnirush-your_access_token
```
Add as Worker Secret: In the Cloudflare Dashboard:
- Navigate to Workers & Pages -> your omnirush2api Worker -> Settings -> Variables and Secrets.
- Under Secrets, click Add.
- Name: OMNIRUSH_REFRESH_TOKEN
- Value: Paste the <refreshToken>|<accessToken> pair (or raw refresh token).
- Click Deploy.
(Recommended) Enable Global KV Sync for Multi-Region Deployments: To automatically persist and synchronize rotated tokens across worldwide edge isolates:
- In Cloudflare Dashboard, go to Storage & Databases -> KV -> Create a namespace named OMNIRUSH_TOKENS.
- In your Worker settings under KV Namespace Bindings, bind OMNIRUSH_TOKENS with variable name: TOKEN_KV.
- The worker will seamlessly persist and synchronize rotated tokens globally with zero 401s.

Pro Tip (Multi-Account Pooling): You can paste multiple token pairs (one per line) into OMNIRUSH_REFRESH_TOKEN. Omnirush2API will automatically round-robin requests across all accounts and failover on 429 rate limits!

4. Extracting from OmniRush Desktop App Files (Manual Method)

If you have signed into the OmniRush Desktop app on your computer, your refresh token is stored in the following locations:

Windows:
- %APPDATA%\OmniRush\credentials
- %APPDATA%\OmniRush\credentials.fallback (Plaintext fallback JSON)
macOS:
- ~/Library/Application Support/OmniRush/credentials
- macOS Keychain service: ai.omnirush.desktop.gateway-refresh
Linux:
- ~/.config/OmniRush/credentials
- ~/.config/OmniRush/credentials.fallback

The credentials file contains JSON:

{
  "refresh_token": "omni_ref_...",
  "access_token": "omni_acc_...",
  "gateway_url": "https://omnirush.ai/omnirush/v1",
  "email": "[email protected]"
}

You can copy the "refresh_token" value directly.

Quick Start

Method 1: Local Daemon

Step 1: Install & Build

Clone and install dependencies:

git clone https://github.com/IMROVOID/Omnirush2API.git
cd Omnirush2API
npm install
npm run build

Or install globally via npm:

npm install -g omnirush2api

Step 2: Check or Login Authentication

Authenticate using the interactive terminal OAuth flow:

node dist/cli.js login

Or check if existing local desktop credentials are automatically detected:

node dist/cli.js check

Example output:

[Omnirush2API] Checking local OmniRush credentials and status...

Found 1 unique OmniRush credential(s):

--- [Account #1] ---
  Source: C:\Users\<user>\AppData\Roaming\OmniRush\credentials
  Token:  omni_ref_a1... (128 chars)
  Status: ✓ Active & verified
  Email:  [email protected]
  Plan:   active
  Tokens Remaining: 4,875,000

Local authentication check complete.

Step 3: Start the Router

Run with default settings (port 20129, open access):

node dist/cli.js start

Or specify a custom port:

node dist/cli.js start --port 20129

Or enable optional Bearer API key authorization:

node dist/cli.js start --port 20129 --key sk-my-secret-key

Your local endpoint is available at http://localhost:20129/v1.

Method 2: Cloudflare Workers (Serverless)

Deploy a 24/7 serverless gateway without keeping your computer running.

Step 1: Copy the Code

Open worker/worker.js and copy the entire file contents.

Step 2: Create Worker in Cloudflare Dashboard

Log into the Cloudflare Dashboard.
Go to Workers & Pages -> Create application -> Create Worker.
Set name to omnirush2api and click Deploy.
Click Edit code, select all existing code, delete it, and paste the copied contents of worker/worker.js.
Click Deploy in the top right.

Step 3: Add Variables & Secrets

In your Worker, go to Settings -> Variables and Secrets and add:

| Variable | Type | Required | Description | |---|---|---|---| | OMNIRUSH_REFRESH_TOKEN | Secret | Yes | Your Omnirush refresh token. Multi-account supported: one token per line. | | API_KEY | Secret | Optional | Client bearer key (e.g. sk-omnirush-key). | | GATEWAY_URL | Text | Optional | Upstream URL (defaults to https://omnirush.ai/omnirush/v1). |

Click Save and deploy.

Your Cloudflare Worker API URL:

https://omnirush2api.<your-subdomain>.workers.dev/v1

Model Catalog & Aliases

Omnirush2API automatically maps requested model aliases to canonical upstream models:

| Request Model Alias | Canonical Upstream Model | Context Limit | Max Output | Description | |---|---|---|---|---| | gpt-6-astra, astra, gpt-6, omnirush | gpt-6-astra | 200,000 | 16,384 | Flagship deep reasoning model | | gpt-6.1-sol, sol-pro | gpt-6.1-sol | 200,000 | 16,384 | Frontier reasoning & coding model | | gpt-6-sol, sol | gpt-6-sol | 128,000 | 8,192 | Low-latency high-speed model |

Client Integration

Configuration file path:

~/.9router/db.json

Or configure via Web Dashboard under Providers -> Add Custom Provider:

Provider Type:

openai

Base URL:

http://localhost:20129/v1

API Key:

sk-omnirush

Models:

gpt-6-astra, gpt-6.1-sol, gpt-6-sol

Configuration entry for ~/.9router/db.json:

{
  "providers": [
    {
      "id": "omnirush2api",
      "name": "Omnirush2API",
      "type": "openai",
      "baseUrl": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "models": [
        "gpt-6-astra",
        "gpt-6.1-sol",
        "gpt-6-sol"
      ]
    }
  ]
}

Configuration file path:

.aider.conf.yml

Add configuration:

openai-api-base: http://localhost:20129/v1
openai-api-key: sk-omnirush
model: openai/gpt-6-astra

Configuration file path:

~/.gemini/antigravity/antigravity.json

Add configuration:

{
  "modelProviders": {
    "omnirush2api": {
      "type": "openai",
      "baseUrl": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "defaultModel": "gpt-6-astra"
    }
  }
}

Configuration file path:

~/.cherry-studio/config.json

Or configure via UI in Settings -> Providers -> OpenAI:

Custom Server Address:

http://localhost:20129/v1

API Key:

sk-omnirush

Models:

gpt-6-astra

gpt-6.1-sol

gpt-6-sol

Configuration file path (Global):

~/.claude/settings.json

Configuration file path (Project-level):

.claude/settings.json

Add configuration:

{
  "env": {
    "OPENAI_BASE_URL": "http://localhost:20129/v1",
    "OPENAI_API_KEY": "sk-omnirush",
    "ANTHROPIC_MODEL": "gpt-6-astra"
  }
}

Then run:

claude

Configuration file path:

.vscode/settings.json

Add configuration:

{
  "cline.apiProvider": "openai-compatible",
  "cline.openAiBaseUrl": "http://localhost:20129/v1",
  "cline.openAiApiKey": "sk-omnirush",
  "cline.openAiModelId": "gpt-6-astra"
}

Configuration file path:

~/.codex/config.toml

Add configuration:

[model]
provider = "openai"
base_url = "http://localhost:20129/v1"
api_key = "sk-omnirush"
model_name = "gpt-6-astra"

Configuration file path:

~/.continue/config.json

Add configuration:

{
  "models": [
    {
      "title": "GPT-6 Astra",
      "provider": "openai",
      "model": "gpt-6-astra",
      "apiBase": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush"
    }
  ]
}

Configuration file path (Global):

~/.cursor/User/settings.json

Configuration file path (Project-level):

.vscode/settings.json

Add configuration:

{
  "cursor.openaiBaseUrl": "http://localhost:20129/v1",
  "cursor.openaiApiKey": "sk-omnirush",
  "cursor.model": "gpt-6-astra"
}

Or configure in Cursor Settings -> Models:

Toggle Override OpenAI Base URL: http://localhost:20129/v1
Set OpenAI API Key: sk-omnirush
Add model: gpt-6-astra

Configuration file path:

agent.yaml

Add configuration:

llm:
  api_type: openai
  base_url: "http://localhost:20129/v1"
  api_key: "sk-omnirush"
  model: "gpt-6-astra"
  temperature: 0.7

Configuration file path:

~/.hermes/config.json

Add configuration:

{
  "llm": {
    "provider": "openai",
    "baseUrl": "http://localhost:20129/v1",
    "apiKey": "sk-omnirush",
    "model": "gpt-6-astra"
  }
}

Configuration file path:

librechat.yaml

Add configuration:

endpoints:
  custom:
    - name: "Omnirush2API"
      apiKey: "sk-omnirush"
      baseURL: "http://localhost:20129/v1"
      models:
        default: ["gpt-6-astra", "gpt-6.1-sol", "gpt-6-sol"]
      titleConvo: true
      modelDisplayLabel: "OmniRush"

Configuration file path:

.env.local

Add configuration:

BASE_URL=http://localhost:20129
OPENAI_API_KEY=sk-omnirush
CUSTOM_MODELS=-all,+gpt-6-astra,+gpt-6.1-sol,+gpt-6-sol

Configuration file path:

~/.omniroute/providers.json

Add configuration via CLI:

omniroute provider add --id omnirush2api --type openai --base-url http://localhost:20129/v1 --api-key sk-omnirush --models gpt-6-astra,gpt-6.1-sol,gpt-6-sol

Or add configuration to ~/.omniroute/providers.json:

{
  "providers": [
    {
      "id": "omnirush2api",
      "name": "Omnirush Gateway",
      "type": "openai-compatible",
      "baseUrl": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "models": [
        "gpt-6-astra",
        "gpt-6.1-sol",
        "gpt-6-sol"
      ]
    }
  ]
}

Configuration file path:

.env

Add environment configuration:

OPENAI_BASE_URL="http://localhost:20129/v1"
OPENAI_API_KEY="sk-omnirush"

Python SDK example:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:20129/v1",
    api_key="sk-omnirush"
)

response = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "Write quicksort in Python."}],
    stream=True
)

for chunk in response:
    content = chunk.choices[0].delta.content or ""
    print(content, end="", flush=True)

Node.js SDK example:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:20129/v1",
  apiKey: "sk-omnirush",
});

const response = await client.chat.completions.create({
  model="gpt-6-astra",
  messages: [{ role: "user", content: "Write quicksort in TypeScript." }],
});

console.log(response.choices[0].message.content);

cURL command:

curl -X POST http://localhost:20129/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-omnirush" \
  -d '{"model":"gpt-6-astra","messages":[{"role":"user","content":"Hello!"}]}'

Configuration file path:

openclaw.json

Add configuration:

{
  "providers": {
    "omnirush2api": {
      "type": "openai-compatible",
      "baseURL": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "models": [
        "gpt-6-astra",
        "gpt-6.1-sol",
        "gpt-6-sol"
      ]
    }
  }
}

Configuration file path (Linux / macOS):

~/.local/share/opencode/opencode.jsonc

Configuration file path (Project-level):

opencode.jsonc

Add configuration:

{
  "providers": {
    "omnirush2api": {
      "type": "openai-compatible",
      "baseUrl": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "models": [
        "gpt-6-astra",
        "gpt-6.1-sol",
        "gpt-6-sol"
      ]
    }
  },
  "default_model": "omnirush2api/gpt-6-astra"
}

Configuration file path:

config.toml

Add configuration:

[llm]
model = "openai/gpt-6-astra"
base_url = "http://localhost:20129/v1"
api_key = "sk-omnirush"

Configuration file path:

.vscode/settings.json

Add configuration:

{
  "roo-cline.apiProvider": "openai-compatible",
  "roo-cline.openAiBaseUrl": "http://localhost:20129/v1",
  "roo-cline.openAiApiKey": "sk-omnirush",
  "roo-cline.openAiModelId": "gpt-6-astra"
}

Configuration file path:

~/.trae/config.json

Add configuration:

{
  "modelProviders": [
    {
      "name": "Omnirush2API",
      "apiType": "openai",
      "endpoint": "http://localhost:20129/v1",
      "apiKey": "sk-omnirush",
      "models": [
        "gpt-6-astra",
        "gpt-6.1-sol",
        "gpt-6-sol"
      ]
    }
  ]
}

Configuration file path:

~/.codeium/windsurf/model_config.json

Add configuration:

{
  "customOpenAI": {
    "endpoint": "http://localhost:20129/v1",
    "apiKey": "sk-omnirush",
    "model": "gpt-6-astra"
  }
}

Architecture & Structure

Omnirush2API/
├── src/
│   ├── types/
│   │   ├── auth.ts              # OAuth contracts, pool states, device authorize models
│   │   ├── openai.ts            # OpenAI request/response/SSE schemas & chunk deltas
│   │   └── config.ts            # Server and Cloudflare Worker runtime configuration
│   ├── auth/
│   │   ├── oauth-client.ts      # Device code flow, token exchange & proactive refresh
│   │   ├── clicreds.ts          # OS desktop credential auto-discovery (Windows/macOS/Linux)
│   │   ├── token-store.ts       # Secure ~/.omnirush2api/tokens.json atomic storage
│   │   └── pool-manager.ts      # Multi-account round-robin pool with 429 cooldown backoff
│   ├── proxy/
│   │   ├── model-catalog.ts     # Model list & alias resolver (astra, gpt-6 -> gpt-6-astra)
│   │   ├── normalizer.ts        # Request normalizer for Omnirush wire API
│   │   ├── stream-transformer.ts# Real-time SSE transformer with reasoning_content support
│   │   ├── wire-guard.ts        # Anti-ban wire guard, desktop signature masquerade & ban detector
│   │   └── completion-handler.ts# Core completion proxy with cancellation & failover retry
│   ├── server/
│   │   ├── routes.ts            # Route dispatcher (/v1/models, /v1/chat/completions, /v1/health)
│   │   └── http-server.ts       # Native Node.js HTTP server with graceful shutdown
│   ├── cli/
│   │   ├── commands/
│   │   │   ├── login.ts         # Interactive terminal device OAuth login flow
│   │   │   ├── check.ts         # Credentials verification & quota status inspect
│   │   │   ├── start.ts         # Daemon launcher with argument parsing
│   │   │   └── tokens.ts        # Token pool management (list, add, remove)
│   │   └── index.ts             # CLI command dispatcher
│   └── worker/
│       └── index.ts             # Cloudflare Workers / Vercel Edge fetch entrypoint
├── worker/
│   └── worker.js                # Standalone zero-dependency Cloudflare Worker bundle (29 KB)
├── dist/
│   └── cli.js                   # Standalone Node.js CLI executable bundle (54 KB)
├── tests/                       # 42 automated unit & integration tests across 11 suites
├── scripts/
│   └── build.ts                 # esbuild build pipeline
├── package.json
└── tsconfig.json

Advanced Guides

Anti-Ban Wire Guard & Account Protection

Omnirush enforces automated account closure protections triggered by:

"Your OmniRush account was closed automatically because its sign-in was used from another place at the same time or through an unofficial client, which our Terms of Service don't allow."

Omnirush2API includes built-in wire defenses to protect your accounts:

Official Desktop Client Masquerading:
- Outbound requests emulate the official OmniRush Electron desktop client (OmniRush/1.2.4, Electron/32.2.0, Chrome/128.0).
- Includes standard client security headers: Sec-Ch-Ua, Sec-Fetch-Mode: cors, Sec-Fetch-Site: cross-site, and X-OmniRush-Client: desktop-app.
- Strips all unofficial client headers and identifiers.
- Emulates authentic hardware hostnames (DESKTOP-XXXXXX / MacBook-XXXX) during OAuth device authorization.
Per-Account Request Serialization (Anti-Concurrency Lock):
- Enforces a strict per-account mutex lock to prevent concurrent overlapping requests that trigger multi-session fraud detectors.
Automated Ban Detection & Permanent Quarantine:
- Actively parses upstream responses for account closure notices or suspension warnings.
- Upon detection, the affected account is immediately and permanently quarantined (isBanned: true) from the pool.
- Halts all further retries against the banned account to protect remaining accounts in the pool.
Token Isolation Recommendation (Crucial for Cloudflare Workers):
- Do NOT run the OmniRush Desktop app on your PC at the same time using the exact same refresh token configured in a Cloudflare Worker.
- Cloudflare Workers execute from global datacenter IP addresses (e.g. Frankfurt, Amsterdam, US-West). Firing requests simultaneously from your home IP and Cloudflare datacenter IPs with the same account triggers Omnirush's automated location anomaly detection.
- Best Practice: Use dedicated accounts for Cloudflare Workers, or close your local desktop app when routing requests through your edge worker.

Multi-Account Pooling & 429 Failover

If an account reaches its quota limit, Omnirush2API automatically shifts traffic to the next account without interrupting your active coding session.

In Cloudflare Workers or your local environment, pass multiple refresh tokens separated by newlines in OMNIRUSH_REFRESH_TOKEN:

OMNIRUSH_REFRESH_TOKEN="token_account_1
token_account_2
token_account_3"

Workflow:

Round-Robin: Requests cycle across active accounts to distribute load evenly.
Quota Detection: When an account encounters HTTP 429 (Retry-After), the router parses the duration and parks that account in cooldown.
Transparent Retry: The current request is immediately retried using the next available account in the pool.
Health Diagnostics: Query /v1/health to monitor active versus cooldown accounts.

Environment Variables

| Variable | Mode | Default | Description | |---|---|---|---| | PORT | Local | 20129 | Local HTTP daemon port | | HOST | Local | 127.0.0.1 | Local bind address | | API_KEY | Both | (None) | Client authorization bearer token | | OMNIRUSH_REFRESH_TOKEN | Both | (From tokens.json)| Newline-separated list of refresh tokens | | OMNIRUSH_GATEWAY_URL | Both | https://omnirush.ai/omnirush/v1 | Upstream Omnirush gateway URL |

Development & Testing

Run typecheck:

npm run typecheck

Run automated test suite:

npm test

Build standalone bundles:

npm run build

Continuous Integration (CI)

Every commit and pull request runs automated verification through GitHub Actions:

Typecheck: npm run typecheck
Unit & Integration Tests: npm test
Bundle Verification: npm run build

Skipping Automated Tests

To skip the test suite on specific commits (e.g. for docs updates or asset additions), include any of the following tags in the commit message:

[skip test] or [skip tests]
[skip-test] or [skip-tests]

Disclaimer & Legal Notice

IMPORTANT: Please read this notice carefully before using or deploying Omnirush2API.

Educational & Research Purposes Only: This project is developed and distributed exclusively for personal educational, research, and non-commercial API interoperability testing purposes.
Risk of Account Suspension or Ban: Extracting OAuth tokens, managing session credentials, or routing automated API requests outside the official Omnirush Desktop client may violate Omnirush's Terms of Service and End User License Agreements. Omnirush may rate-limit, revoke tokens for, suspend, or permanently ban your account without prior warning.
No Warranty & No Guarantee: The author and contributors make no claims, promises, or guarantees regarding the safety, status, or longevity of your Omnirush account. This software is provided "AS IS", without warranty of any kind, express or implied.
Assumption of Risk: You assume full and sole responsibility for any outcomes or damages resulting from using this software, including but not limited to account termination, loss of API access, or data loss. Use strictly at your own risk.
Trademark Attribution: All product names, logos, and brands (such as "Omnirush", "GPT-6 Astra", "GPT-6 Sol") are trademarks or registered trademarks of their respective owners. Omnirush2API is an independent open-source project and is neither affiliated with, maintained by, nor endorsed by Omnirush.ai.

License

This project is licensed under the GNU General Public License v3.0 (GPLv3). See the LICENSE file for details.

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

Omnirush2API

Table of Contents

What is Omnirush2API?

Key Features

How to Get Your Refresh Token

1. Automated Script (Recommended - 1-Click Login)

2. For Method 1: Local Daemon

3. For Method 2: Cloudflare Workers (Serverless)

4. Extracting from OmniRush Desktop App Files (Manual Method)

Quick Start

Method 1: Local Daemon

Step 1: Install & Build

Step 2: Check or Login Authentication

Step 3: Start the Router

Method 2: Cloudflare Workers (Serverless)

Step 1: Copy the Code

Step 2: Create Worker in Cloudflare Dashboard

Step 3: Add Variables & Secrets

Model Catalog & Aliases

Client Integration

Architecture & Structure

Advanced Guides

Anti-Ban Wire Guard & Account Protection

Multi-Account Pooling & 429 Failover

Environment Variables

Development & Testing

Continuous Integration (CI)

Skipping Automated Tests

Disclaimer & Legal Notice

License