OmniRoute/README.ms.md

🚀 OmniRoute — Gerbang AI Percuma

Jangan sekali-kali berhenti mengekod. Penghalaan pintar ke model AI PERCUMA & kos rendah dengan sandaran automatik.

Proksi API universal anda — satu titik akhir, 36+ pembekal, masa henti sifar.

Penyelesaian Sembang • Pembenaman • Penjanaan Imej • Audio • Kedudukan Semula • 100% TypeScript

---

🤖 Pembekal AI percuma untuk ejen pengekodan kegemaran anda

Sambungkan mana-mana alat IDE atau CLI berkuasa AI melalui OmniRoute — get laluan API percuma untuk pengekodan tanpa had.

OpenClaw ⭐ 205K	NanoBot ⭐ 20.9K	PicoClaw ⭐ 14.6K	ZeroClaw ⭐ 9.9K	IronClaw ⭐ 2.1K
OpenCode ⭐ 106K	Codex CLI ⭐ 60.8K	Claude Code ⭐ 67.3K	Gemini CLI ⭐ 94.7K	Kilo Code ⭐ 15.5K

_{📡 Semua ejen menyambung melalui http://localhost:20128/v1 atau http://cloud.omniroute.online/v1 atau model http://cloud.omniroute.online/v1 —i_24_TOKEN dan satu —i_konfigurasi kuota}

---

🌐 Website • 🚀 Quick Start • 💡 Features • 📖 Docs • 💰 Pricing • 💬 WhatsApp

🌐 Available in: 🇺🇸 English | 🇧🇷 Português (Brasil) | 🇪🇸 Español | 🇫🇷 Français | 🇮🇹 Italiano | 🇷🇺 Русский | 🇨🇳 中文 (简体) | 🇩🇪 Deutsch | 🇮🇳 हिन्दी | 🇹🇭 ไทย | 🇺🇦 Українська | 🇸🇦 العربية | 🇯🇵 日本語 | 🇻🇳 Tiếng Việt | 🇧🇬 Български | 🇩🇰 Dansk | 🇫🇮 Suomi | 🇮🇱 עברית | 🇭🇺 Magyar | 🇮🇩 Bahasa Indonesia | 🇰🇷 한국어 | 🇲🇾 Bahasa Melayu | 🇳🇱 Nederlands | 🇳🇴 Norsk | 🇵🇹 Português (Portugal) | 🇷🇴 Română | 🇵🇱 Polski | 🇸🇰 Slovenčina | 🇸🇪 Svenska | 🇵🇭 Filipino

---

🤔 Mengapa OmniRoute?

Berhenti membazir wang dan mencapai had:

• Kuota langganan tamat tempoh tidak digunakan setiap bulan
• Had kadar menghalang anda pertengahan pengekodan
• API Mahal ($20-50/bulan bagi setiap pembekal)
• Pertukaran manual antara pembekal

OmniRoute menyelesaikan ini:

• ✅ Maksimumkan langganan - Jejaki kuota, gunakan setiap bit sebelum ditetapkan semula
• ✅ Auto sandaran - Langganan → Kunci API → Murah → Percuma, masa henti sifar
• ✅ Berbilang akaun - Round-robin antara akaun bagi setiap pembekal
• ✅ Universal - Berfungsi dengan Kod Claude, Codex, Gemini CLI, Kursor, Cline, OpenClaw, sebarang alat CLI

---

🔄 Cara Ia Berfungsi

┌─────────────┐
│  Your CLI   │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
│   Tool      │
└──────┬──────┘
       │ http://localhost:20128/v1
       ↓
┌─────────────────────────────────────────┐
│           OmniRoute (Smart Router)        │
│  • Format translation (OpenAI ↔ Claude) │
│  • Quota tracking + Embeddings + Images │
│  • Auto token refresh                   │
└──────┬──────────────────────────────────┘
       │
       ├─→ [Tier 1: SUBSCRIPTION] Claude Code, Codex, Gemini CLI
       │   ↓ quota exhausted
       ├─→ [Tier 2: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM, etc.
       │   ↓ budget limit
       ├─→ [Tier 3: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
       │   ↓ budget limit
       └─→ [Tier 4: FREE] iFlow, Qwen, Kiro (unlimited)

Result: Never stop coding, minimal cost

---

🎯 What OmniRoute Solves — 16 Real Pain Points

Every developer using AI tools faces these problems daily. OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.

💸 1. "I pay for an expensive subscription but still get interrupted by limits"

Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.

How OmniRoute solves it:

• Smart 4-Tier Fallback — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
• Real-Time Quota Tracking — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
• Multi-Account Support — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
• Custom Combos — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
• Codex Business Quotas — Business/Team workspace quota monitoring directly in the dashboard

🔌 2. "I need to use multiple providers but each has a different API"

OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.

How OmniRoute solves it:

• Unified Endpoint — A single http://localhost:20128/v1 serves as proxy for all 36+ providers
• Format Translation — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
• Response Sanitization — Strips non-standard fields (x_groq, usage_breakdown, service_tier) that break OpenAI SDK v1.83+
• Role Normalization — Converts developer → system for non-OpenAI providers; system → user for GLM/ERNIE
• Think Tag Extraction — Extracts <think> blocks from models like DeepSeek R1 into standardized reasoning_content
• Structured Output for Gemini — json_schema → responseMimeType/responseSchema automatic conversion
• stream defaults to false — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs

🌐 3. "My AI provider blocks my region/country"

Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like unsupported_country_region_territory during OAuth and API connections. This is especially frustrating for developers from developing countries.

How OmniRoute solves it:

• 3-Level Proxy Config — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
• Color-Coded Proxy Badges — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
• OAuth Token Exchange Through Proxy — OAuth flow also goes through the proxy, solving unsupported_country_region_territory
• Connection Tests via Proxy — Connection tests use the configured proxy (no more direct bypass)
• SOCKS5 Support — Full SOCKS5 proxy support for outbound routing
• TLS Fingerprint Spoofing — Browser-like TLS fingerprint via wreq-js to bypass bot detection

🆓 4. "I want to use AI for coding but I have no money"

Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.

How OmniRoute solves it:

• Free Tier Providers Built-in — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
• Free-Only Combos — Chain gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus = $0/month with zero downtime
• NVIDIA NIM Free Credits — 1000 free credits integrated
• Cost Optimized Strategy — Routing strategy that automatically chooses the cheapest available provider

🔒 5. "I need to protect my AI gateway from unauthorized access"

When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.

How OmniRoute solves it:

• API Key Management — Generation, rotation, and scoping per provider with a dedicated /dashboard/api-manager page
• Model-Level Permissions — Restrict API keys to specific models (openai/*, wildcard patterns), with Allow All/Restrict toggle
• API Endpoint Protection — Require a key for /v1/models and block specific providers from the listing
• Auth Guard + CSRF Protection — All dashboard routes protected with withAuth middleware + CSRF tokens
• Rate Limiter — Per-IP rate limiting with configurable windows
• IP Filtering — Allowlist/blocklist for access control
• Prompt Injection Guard — Sanitization against malicious prompt patterns
• AES-256-GCM Encryption — Credentials encrypted at rest

🛑 6. "My provider went down and I lost my coding flow"

AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.

How OmniRoute solves it:

• Circuit Breaker per-provider — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
• Exponential Backoff — Progressive retry delays
• Anti-Thundering Herd — Mutex + semaphore protection against concurrent retry storms
• Combo Fallback Chains — If the primary provider fails, automatically falls through the chain with no intervention
• Combo Circuit Breaker — Auto-disables failing providers within a combo chain
• Health Dashboard — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency

🔧 7. "Configuring each AI tool is tedious and repetitive"

Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.

How OmniRoute solves it:

• CLI Tools Dashboard — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
• GitHub Copilot Config Generator — Generates chatLanguageModels.json for VS Code with bulk model selection
• Onboarding Wizard — Guided 4-step setup for first-time users
• One endpoint, all models — Configure http://localhost:20128/v1 once, access 36+ providers

🔑 8. "Managing OAuth tokens from multiple providers is hell"

Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with client_secret is missing, redirect_uri_mismatch, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.

How OmniRoute solves it:

• Auto Token Refresh — OAuth tokens refresh in background before expiration
• OAuth 2.0 (PKCE) Built-in — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
• Multi-Account OAuth — Multiple accounts per provider via JWT/ID token extraction
• OAuth LAN/Remote Fix — Private IP detection for redirect_uri + manual URL mode for remote servers
• OAuth Behind Nginx — Uses window.location.origin for reverse proxy compatibility
• Remote OAuth Guide — Step-by-step guide for Google Cloud credentials on VPS/Docker

📊 9. "I don't know how much I'm spending or where"

Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.

How OmniRoute solves it:

• Cost Analytics Dashboard — Per-token cost tracking and budget management per provider
• Budget Limits per Tier — Spending ceiling per tier that triggers automatic fallback
• Per-Model Pricing Configuration — Configurable prices per model
• Usage Statistics Per API Key — Request count and last-used timestamp per key
• Analytics Dashboard — Stat cards, model usage chart, provider table with success rates and latency

🐛 10. "I can't diagnose errors and problems in AI calls"

When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.

How OmniRoute solves it:

• Unified Logs Dashboard — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
• Console Log Viewer — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
• SQLite Proxy Logs — Persistent logs that survive server restarts
• Translator Playground — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
• Request Telemetry — p50/p95/p99 latency + X-Request-Id tracing
• File-Based Logging with Rotation — Console interceptor captures everything to JSON log with size-based rotation

🏗️ 11. "Deploying and maintaining the gateway is complex"

Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, EACCES on directories, port conflicts, and cross-platform builds add friction.

How OmniRoute solves it:

• npm global install — npm install -g omniroute && omniroute — done
• Docker Multi-Platform — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
• Docker Compose Profiles — base (no CLI tools) and cli (with Claude Code, Codex, OpenClaw)
• Electron Desktop App — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
• Split-Port Mode — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
• Cloud Sync — Config synchronization across devices via Cloudflare Workers
• DB Backups — Automatic backup, restore, export and import of all settings

🌍 12. "The interface is English-only and my team doesn't speak English"

Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.

How OmniRoute solves it:

• Dashboard i18n — 30 Languages — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
• RTL Support — Right-to-left support for Arabic and Hebrew
• Multi-Language READMEs — 30 complete documentation translations
• Language Selector — Globe icon in header for real-time switching

🔄 13. "I need more than chat — I need embeddings, images, audio"

AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.

How OmniRoute solves it:

• Embeddings — /v1/embeddings with 6 providers and 9+ models
• Image Generation — /v1/images/generations with 4 providers and 9+ models
• Audio Transcription — /v1/audio/transcriptions — Whisper-compatible
• Text-to-Speech — /v1/audio/speech — Multi-provider audio synthesis
• Moderations — /v1/moderations — Content safety checks
• Reranking — /v1/rerank — Document relevance reranking
• Responses API — Full /v1/responses support for Codex

🧪 14. "I have no way to test and compare quality across models"

Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.

How OmniRoute solves it:

• LLM Evaluations — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
• 4 Match Strategies — exact, contains, regex, custom (JS function)
• Translator Playground Test Bench — Batch testing with multiple inputs and expected outputs, cross-provider comparison
• Chat Tester — Full round-trip with visual response rendering
• Live Monitor — Real-time stream of all requests flowing through the proxy

📈 15. "I need to scale without losing performance"

As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.

How OmniRoute solves it:

• Semantic Cache — Two-tier cache (signature + semantic) reduces cost and latency
• Request Idempotency — 5s deduplication window for identical requests
• Rate Limit Detection — Per-provider RPM, min gap, and max concurrent tracking
• Editable Rate Limits — Configurable defaults in Settings → Resilience with persistence
• API Key Validation Cache — 3-tier cache for production performance
• Health Dashboard with Telemetry — p50/p95/p99 latency, cache stats, uptime

🤖 16. "I want to control model behavior globally"

Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.

How OmniRoute solves it:

• System Prompt Injection — Global prompt applied to all requests
• Thinking Budget Validation — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
• 6 Routing Strategies — Global strategies that determine how requests are distributed
• Wildcard Router — provider/* patterns route dynamically to any provider
• Combo Enable/Disable Toggle — Toggle combos directly from the dashboard
• Provider Toggle — Enable/disable all connections for a provider with one click
• Blocked Providers — Exclude specific providers from /v1/models listing

⚡ Mula Pantas

1. Pasang secara global:

npm install -g omniroute
omniroute

🎉 Papan pemuka dibuka pada http://localhost:20128

Perintah	Penerangan
omniroute	Mulakan pelayan (port lalai 20128)
omniroute --port 3000	Gunakan port tersuai
omniroute --no-open	Jangan auto buka penyemak imbas
omniroute --help	Tunjukkan bantuan

2. Sambungkan pembekal PERCUMA:

Papan pemuka → Pembekal → Sambung Kod Claude atau Antigraviti → Log masuk OAuth → Selesai!

3. Gunakan dalam alat CLI anda:

Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline Settings:
  Endpoint: http://localhost:20128/v1
  API Key: [copy from dashboard]
  Model: if/kimi-k2-thinking

Itu sahaja! Mulakan pengekodan dengan model AI PERCUMA.

Alternatif — dijalankan dari sumber:

cp .env.example .env
npm install
PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev

---

🐳 Docker

OmniRoute tersedia sebagai imej Docker awam pada Docker Hub.

Larian pantas:

docker run -d \
  --name omniroute \
  --restart unless-stopped \
  -p 20128:20128 \
  -v omniroute-data:/app/data \
  diegosouzapw/omniroute:latest

Dengan fail persekitaran:

# Copy and edit .env first
cp .env.example .env

docker run -d \
  --name omniroute \
  --restart unless-stopped \
  --env-file .env \
  -p 20128:20128 \
  -v omniroute-data:/app/data \
  diegosouzapw/omniroute:latest

Menggunakan Docker Compose:

# Base profile (no CLI tools)
docker compose --profile base up -d

# CLI profile (Claude Code, Codex, OpenClaw built-in)
docker compose --profile cli up -d

Imej	Tag	Saiz	Penerangan
diegosouzapw/omniroute	latest	~250MB	Keluaran stabil terkini
diegosouzapw/omniroute	1.0.3	~250MB	Versi semasa

---

---

🖥️ Desktop App — Offline & Always-On

🆕 NEW! OmniRoute is now available as a native desktop application for Windows, macOS, and Linux.

• 🖥️ Native Window — Dedicated app window with system tray integration
• 🔄 Auto-Start — Launch OmniRoute on system login
• 🔔 Native Notifications — Get alerts for quota exhaustion or provider issues
• ⚡ One-Click Install — NSIS (Windows), DMG (macOS), AppImage (Linux)
• 🌐 Offline Mode — Works fully offline with bundled server

npm run electron:dev           # Development mode
npm run electron:build         # Current platform
npm run electron:build:win     # Windows (.exe)
npm run electron:build:mac     # macOS (.dmg)
npm run electron:build:linux   # Linux (.AppImage)

📖 Full documentation: electron/README.md

---

💰 Sekilas Pandang Harga

Peringkat	Pembekal	Kos	Set Semula Kuota	Terbaik Untuk
💳 LANGGANAN	Kod Claude (Pro)	$20/bln	5j + mingguan	Sudah melanggan
	Codex (Plus/Pro)	$20-200/bln	5j + mingguan	Pengguna OpenAI
	Gemini CLI	PERCUMA	180K/bln + 1K/hari	Semua orang!
	GitHub Copilot	$10-19/bln	Bulanan	Pengguna GitHub
🔑 KUNCI API	NVIDIA NIM	PERCUMA (1000 kredit)	Satu kali	Ujian peringkat percuma
	DeepSeek	Bayar setiap penggunaan	Tiada	Harga/kualiti terbaik
	Groq	Peringkat percuma + berbayar	Kadar terhad	Inferens sangat pantas
	xAI (Grok)	Bayar setiap penggunaan	Tiada	Model Grok
	Mistral	Peringkat percuma + berbayar	Kadar terhad	AI Eropah
	OpenRouter	Bayar setiap penggunaan	Tiada	100+ model
💰 MURAH	GLM-4.7	$0.6/1J	Setiap hari 10AM	Sandaran belanjawan
	MiniMax M2.1	$0.2/1J	5 jam bergolek	Pilihan termurah
	Kimi K2	$9/bln flat	10 juta token/bln	Kos yang boleh diramal
🆓 PERCUMA	iFlow	$0	tanpa had	8 model percuma
	Qwen	$0	tanpa had	3 model percuma
	Kiro	$0	tanpa had	Claude percuma

💡 Petua Pro: Mulakan dengan Gemini CLI (180K percuma/bulan) + iFlow (percuma tanpa had) kombo = $0 kos!

---

💡 Ciri Utama

🧠 Penghalaan Teras & Kepintaran

Ciri	Apa yang Dilakukan
🎯 Smart 4-Tier Fallback	Laluan automatik: Langganan → Kunci API → Murah → Percuma
📊 Penjejakan Kuota Masa Nyata	Kiraan token langsung + tetapan semula kira detik setiap pembekal
🔄 Terjemahan Format	OpenAI ↔ Claude ↔ Gemini ↔ Kursor ↔ Kiro lancar + pembersihan tindak balas
👥 Sokongan Berbilang Akaun	Berbilang akaun bagi setiap pembekal dengan pemilihan pintar
🔄 Muat Semula Token Auto	Token OAuth dimuat semula secara automatik dengan cuba semula
🎨 Kombo Tersuai	6 strategi: isikan dahulu, round-robin, p2c, rawak, paling kurang digunakan, dioptimumkan kos
🧩 Model Tersuai	Tambahkan sebarang ID model pada mana-mana pembekal
🌐 Penghala Wildcard	Halakan corak provider/* kepada mana-mana pembekal secara dinamik
🧠 Anggaran Berfikir	Mod laluan, auto, tersuai dan adaptif untuk model penaakulan
🔀 Model Aliases	Auto-forward deprecated model IDs to current replacements (built-in + custom)
⚡ Background Degradation	Auto-route background tasks (titles, summaries) to cheaper models
💬 System Prompt Suntikan	Gesaan sistem global digunakan merentas semua permintaan
📄 API Respons	Sokongan OpenAI Responses API (/v1/responses) penuh untuk Codex

🎵 API Berbilang Modal

Ciri	Apa yang Dilakukan
🖼️ Penjanaan Imej	/v1/images/generations — 4 pembekal, 9+ model
📐 Pembenaman	/v1/embeddings — 6 pembekal, 9+ model
🎤 Transkripsi Audio	/v1/audio/transcriptions — Serasi dengan bisikan
🔊 Teks-ke-Ucapan	/v1/audio/speech — Sintesis audio berbilang pembekal
🛡️ Kesederhanaan	/v1/moderations — Pemeriksaan keselamatan kandungan
🔀 Penyusunan semula	/v1/rerank — Penarafan semula perkaitan dokumen

🛡️ Ketahanan & Keselamatan

Ciri	Apa yang Dilakukan
🔌 Pemutus Litar	Auto buka/tutup setiap pembekal dengan ambang boleh dikonfigurasikan
🛡️ Kawanan Anti Guruh	Had kadar Mutex + semaphore untuk pembekal kunci API
🧠 Cache Semantik	Cache dua peringkat (tandatangan + semantik) mengurangkan kos & kependaman
⚡ Minta Idepotency	Tetingkap pendua 5s untuk permintaan pendua
🔒 TLS Fingerprint Spoofing	Pintas pengesanan bot berasaskan TLS melalui wreq-js
🌐 Penapisan IP	Senarai kebenaran/senarai sekat untuk kawalan akses API
📊 Had Kadar Boleh Diedit	RPM boleh dikonfigurasikan, jurang min dan serentak maksimum pada tahap sistem
💾 Rate Limit Persistence	Learned limits survive restarts via SQLite with 60s debounce + 24h staleness
🔄 Token Refresh Resilience	Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt
🛡 Perlindungan Titik Akhir API	Gating pengesahan + penyekatan penyedia untuk titik akhir /models
🔒 Keterlihatan Proksi	Lencana berkod warna: 🟢 global, 🟡 pembekal, 🔵 setiap sambungan dengan paparan IP
🌐 Konfigurasi Proksi 3 Tahap	Konfigurasikan proksi pada peringkat global, setiap pembekal atau setiap sambungan

📊 Kebolehlihatan & Analitis

Ciri	Apa yang Dilakukan
📝 Minta Pembalakan	Mod nyahpepijat dengan log permintaan/tindak balas penuh
💾 Log Proksi SQLite	Log proksi berterusan bertahan dimulakan semula pelayan
📊 Papan Pemuka Analitik	Dikuasakan semula: kad statistik, carta penggunaan model, jadual pembekal
📈 Penjejakan Kemajuan	Ikut serta acara kemajuan SSE untuk penstriman
🧪 Penilaian LLM	Ujian set emas dengan 4 strategi perlawanan
🔍 Minta Telemetri	p50/p95/p99 pengagregatan kependaman + pengesanan X-Request-Id
📋 Papan Pemuka Log	Halaman 4 tab bersatu: Log Permintaan, Log Proksi, Log Audit, Konsol
🖥️ Pemapar Log Konsol	Pemapar gaya terminal masa nyata dengan penapis tahap, carian, tatal automatik
📑 Pengelogan Berasaskan Fail	Pemintas konsol menangkap semua output ke fail log JSON dengan putaran
🏥 Papan Pemuka Kesihatan	Masa beroperasi sistem, keadaan pemutus litar, sekatan keluar, statistik cache
💰 Penjejakan Kos	Pengurusan belanjawan + konfigurasi harga setiap model

☁️ Penyerahan & Penyegerakan

Ciri	Apa yang Dilakukan
💾 Penyegerakan Awan	Segerakkan konfigurasi merentas peranti melalui Cloudflare Workers
🌐 Kerahkan Di Mana-mana	Localhost, VPS, Docker, Pekerja Cloudflare
🔑 Pengurusan Kunci API	Jana, putar dan skop kunci API bagi setiap pembekal
🧙 Onboarding Wizard	Persediaan berpandu 4 langkah untuk pengguna kali pertama
🔧 Papan Pemuka Alat CLI	Konfigurasi satu klik Claude, Codex, Cline, OpenClaw, Kilo, Antigravity
🔄 Sandaran DB	Sandaran automatik, pulihkan, eksport & import untuk semua tetapan
🌐 Pengantarabangsaan	i18n penuh dengan next-intl — sokongan Inggeris + Portugis (Brazil)
🌍 Pemilih Bahasa	Ikon glob dalam pengepala untuk penukaran bahasa masa nyata (🇺🇸/🇧🇷)
📂 Direktori Data Tersuai	DATA_DIR env var untuk mengatasi laluan storan lalai ~/.omniroute

📖 Butiran Ciri

🎯 Kemunduran 4 Peringkat Pintar

Cipta gabungan dengan sandaran automatik:

Combo: "my-coding-stack"
  1. cc/claude-opus-4-6        (your subscription)
  2. nvidia/llama-3.3-70b      (free NVIDIA API)
  3. glm/glm-4.7               (cheap backup, $0.6/1M)
  4. if/kimi-k2-thinking       (free fallback)

→ Auto switches when quota runs out or errors occur

📊 Penjejakan Kuota Masa Nyata

• Penggunaan token setiap pembekal
• Tetapkan semula kira detik (5 jam, harian, mingguan)
• Anggaran kos untuk peringkat berbayar
• Laporan perbelanjaan bulanan

🔄 Terjemahan Format

Terjemahan lancar antara format:

• OpenAI ↔ Claude ↔ Gemini ↔ Respons OpenAI
• Alat CLI anda menghantar format OpenAI → OmniRoute menterjemah → Pembekal menerima format asli
• Berfungsi dengan mana-mana alat yang menyokong titik akhir OpenAI tersuai
• Pembersihan tindak balas — Menghapuskan medan bukan standard untuk keserasian OpenAI SDK yang ketat
• Penormalan peranan — developer → system untuk bukan OpenAI; system → user untuk model GLM/ERNIE
• Pengekstrakan teg Think — <think> blok → reasoning_content untuk model pemikiran
• Output berstruktur — json_schema → Gemini's responseMimeType/responseSchema

👥 Sokongan Berbilang Akaun

• Tambah berbilang akaun bagi setiap pembekal
• Auto round-robin atau penghalaan berasaskan keutamaan
• Berundur ke akaun seterusnya apabila seseorang mencapai kuota

🔄 Muat Semula Token Auto

• Token OAuth dimuat semula secara automatik sebelum tamat tempoh
• Tiada pengesahan semula manual diperlukan
• Pengalaman lancar merentas semua pembekal

🎨 Kombo Tersuai

• Buat kombinasi model tanpa had
• 6 strategi: isikan dahulu, round-robin, kuasa dua pilihan, rawak, paling kurang digunakan, dioptimumkan kos
• Kongsi gabungan merentas peranti dengan Cloud Sync

🏥 Papan Pemuka Kesihatan

• Status sistem (masa hidup, versi, penggunaan memori)
• Keadaan pemutus litar bagi setiap pembekal (Tertutup/Terbuka/Separuh Terbuka)
• Status had kadar dan sekatan aktif
• Statistik cache tandatangan
• Telemetri kependaman (p50/p95/p99) + cache segera
• Tetapkan semula status kesihatan dengan satu klik

🔧 Taman Permainan Penterjemah

OmniRoute termasuk Taman Permainan Penterjemah terbina dalam yang berkuasa dengan 4 mod untuk penyahpepijatan, ujian dan pemantauan terjemahan API:

Mod	Penerangan
💻 Taman permainan	Terjemahan format langsung — tampal mana-mana badan permintaan API dan lihat serta-merta cara OmniRoute menterjemahkannya antara format pembekal (OpenAI ↔ Claude ↔ Gemini ↔ Responses API). Termasuk templat contoh dan pengesanan automatik format.
💬 Penguji Sembang	Hantar permintaan sembang sebenar melalui OmniRoute dan lihat perjalanan pergi balik penuh: input anda, permintaan yang diterjemahkan, respons pembekal dan balasan yang diterjemahkan kembali. Tidak ternilai untuk mengesahkan penghalaan kombo.
🧪 Bangku Ujian	Mod ujian kelompok — tentukan berbilang kes ujian dengan input dan output yang dijangkakan berbeza, jalankan semuanya sekali gus dan bandingkan hasil merentas pembekal dan model.
📱 Pemantau Langsung	Pemantauan permintaan masa nyata — tonton permintaan masuk semasa ia mengalir melalui OmniRoute, lihat terjemahan format berlaku secara langsung dan kenal pasti isu serta-merta.

Akses: Papan Pemuka → Penterjemah (bar sisi)

💾 Penyegerakan Awan

• Penyegerakan penyedia, gabungan dan tetapan merentas peranti
• Penyegerakan latar belakang automatik
• Storan yang disulitkan selamat

---

🎯 Kes Penggunaan

Kes 1: "Saya mempunyai langganan Claude Pro"

Masalah: Kuota tamat tempoh tidak digunakan, had kadar semasa pengekodan berat

Combo: "maximize-claude"
  1. cc/claude-opus-4-6        (use subscription fully)
  2. glm/glm-4.7               (cheap backup when quota out)
  3. if/kimi-k2-thinking       (free emergency fallback)

Monthly cost: $20 (subscription) + ~$5 (backup) = $25 total
vs. $20 + hitting limits = frustration

Kes 2: "Saya mahu kos sifar"

Masalah: Tidak mampu membayar langganan, memerlukan pengekodan AI yang boleh dipercayai

Combo: "free-forever"
  1. gc/gemini-3-flash         (180K free/month)
  2. if/kimi-k2-thinking       (unlimited free)
  3. qw/qwen3-coder-plus       (unlimited free)

Monthly cost: $0
Quality: Production-ready models

Kes 3: "Saya memerlukan pengekodan 24/7, tiada gangguan"

Masalah: Tarikh akhir, tidak mampu membayar masa henti

Combo: "always-on"
  1. cc/claude-opus-4-6        (best quality)
  2. cx/gpt-5.2-codex          (second subscription)
  3. glm/glm-4.7               (cheap, resets daily)
  4. minimax/MiniMax-M2.1      (cheapest, 5h reset)
  5. if/kimi-k2-thinking       (free unlimited)

Result: 5 layers of fallback = zero downtime

Kes 4: "Saya mahukan AI PERCUMA dalam OpenClaw"

Masalah: Memerlukan pembantu AI dalam apl pemesejan, percuma sepenuhnya

Combo: "openclaw-free"
  1. if/glm-4.7                (unlimited free)
  2. if/minimax-m2.1           (unlimited free)
  3. if/kimi-k2-thinking       (unlimited free)

Monthly cost: $0
Access via: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...

---

📖 Panduan Persediaan

💳 Pembekal Langganan

Kod Claude (Pro/Max)

Dashboard → Providers → Connect Claude Code
→ OAuth login → Auto token refresh
→ 5-hour + weekly quota tracking

Models:
  cc/claude-opus-4-6
  cc/claude-sonnet-4-5-20250929
  cc/claude-haiku-4-5-20251001

Petua Pro: Gunakan Opus untuk tugas yang rumit, Sonnet untuk kelajuan. OmniRoute menjejaki kuota setiap model!

OpenAI Codex (Plus/Pro)

Dashboard → Providers → Connect Codex
→ OAuth login (port 1455)
→ 5-hour + weekly reset

Models:
  cx/gpt-5.2-codex
  cx/gpt-5.1-codex-max

Gemini CLI (PERCUMA 180K/bulan!)

Dashboard → Providers → Connect Gemini CLI
→ Google OAuth
→ 180K completions/month + 1K/day

Models:
  gc/gemini-3-flash-preview
  gc/gemini-2.5-pro

Nilai Terbaik: Peringkat percuma yang besar! Gunakan ini sebelum peringkat berbayar.

Copilot GitHub

Dashboard → Providers → Connect GitHub
→ OAuth via GitHub
→ Monthly reset (1st of month)

Models:
  gh/gpt-5
  gh/claude-4.5-sonnet
  gh/gemini-3-pro

🔑 Pembekal Kunci API

NVIDIA NIM (PERCUMA 1000 kredit!)

1. Daftar: build.nvidia.com
2. Dapatkan kunci API percuma (1000 kredit inferens disertakan)
3. Papan Pemuka → Tambah Pembekal → NVIDIA NIM:
   • Kunci API: nvapi-your-key

Model: nvidia/llama-3.3-70b-instruct, nvidia/mistral-7b-instruct dan 50+ lagi

Petua Pro: API serasi OpenAI — berfungsi dengan lancar dengan terjemahan format OmniRoute!

DeepSeek

1. Daftar: platform.deepseek.com
2. Dapatkan kunci API
3. Papan Pemuka → Tambah Pembekal → DeepSeek

Model: deepseek/deepseek-chat, deepseek/deepseek-coder

Groq (Tier Percuma Tersedia!)

1. Daftar: console.groq.com
2. Dapatkan kunci API (termasuk peringkat percuma)
3. Papan Pemuka → Tambah Pembekal → Groq

Model: groq/llama-3.3-70b, groq/mixtral-8x7b

Petua Pro: Inferens sangat pantas — terbaik untuk pengekodan masa nyata!

OpenRouter (100+ Model)

1. Daftar: openrouter.ai
2. Dapatkan kunci API
3. Papan Pemuka → Tambah Pembekal → OpenRouter

Model: Akses 100+ model daripada semua pembekal utama melalui kunci API tunggal.

💰 Penyedia Murah (Sandaran)

GLM-4.7 (Tetapan semula harian, $0.6/1J)

1. Daftar: Zhipu AI
2. Dapatkan kunci API daripada Pelan Pengekodan
3. Papan Pemuka → Tambah Kunci API:
   • Pembekal: glm
   • Kunci API: your-key

Gunakan: glm/glm-4.7

Petua Pro: Pelan Pengekodan menawarkan kuota 3× pada kos 1/7! Tetapkan semula setiap hari 10:00 AM.

MiniMax M2.1 (tetapan semula 5j, $0.20/1J)

1. Daftar: MiniMax
2. Dapatkan kunci API
3. Papan Pemuka → Tambah Kunci API

Gunakan: minimax/MiniMax-M2.1

Petua Pro: Pilihan termurah untuk konteks panjang (token 1M)!

Kimi K2 ($9/bulan rata)

1. Langgan: Moonshot AI
2. Dapatkan kunci API
3. Papan Pemuka → Tambah Kunci API

Gunakan: kimi/kimi-latest

Petua Pro: Tetap $9/bulan untuk 10J token = $0.90/1J kos efektif!

🆓 Pembekal PERCUMA (Sandaran Kecemasan)

iFlow (8 model PERCUMA)

Dashboard → Connect iFlow
→ iFlow OAuth login
→ Unlimited usage

Models:
  if/kimi-k2-thinking
  if/qwen3-coder-plus
  if/glm-4.7
  if/minimax-m2
  if/deepseek-r1

Qwen (3 model PERCUMA)

Dashboard → Connect Qwen
→ Device code authorization
→ Unlimited usage

Models:
  qw/qwen3-coder-plus
  qw/qwen3-coder-flash

Kiro (Claude PERCUMA)

Dashboard → Connect Kiro
→ AWS Builder ID or Google/GitHub
→ Unlimited usage

Models:
  kr/claude-sonnet-4.5
  kr/claude-haiku-4.5

🎨 Cipta Kombo

Contoh 1: Maksimumkan Langganan → Sandaran Murah

Dashboard → Combos → Create New

Name: premium-coding
Models:
  1. cc/claude-opus-4-6 (Subscription primary)
  2. glm/glm-4.7 (Cheap backup, $0.6/1M)
  3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)

Use in CLI: premium-coding

Contoh 2: Percuma-Sahaja (Kos Sifar)

Name: free-combo
Models:
  1. gc/gemini-3-flash-preview (180K free/month)
  2. if/kimi-k2-thinking (unlimited)
  3. qw/qwen3-coder-plus (unlimited)

Cost: $0 forever!

🔧 CLI Integrasi

IDE Kursor

Settings → Models → Advanced:
  OpenAI API Base URL: http://localhost:20128/v1
  OpenAI API Key: [from OmniRoute dashboard]
  Model: cc/claude-opus-4-6

Kod Claude

Gunakan halaman Alat CLI dalam papan pemuka untuk konfigurasi satu klik atau edit ~/.claude/settings.json secara manual.

Codex CLI

export OPENAI_BASE_URL="http://localhost:20128"
export OPENAI_API_KEY="your-omniroute-api-key"

codex "your prompt"

OpenClaw

Pilihan 1 — Papan Pemuka (disyorkan):

Dashboard → CLI Tools → OpenClaw → Select Model → Apply

Pilihan 2 — Manual: Edit ~/.openclaw/openclaw.json:

{
  "models": {
    "providers": {
      "omniroute": {
        "baseUrl": "http://127.0.0.1:20128/v1",
        "apiKey": "sk_omniroute",
        "api": "openai-completions"
      }
    }
  }
}

Nota: OpenClaw hanya berfungsi dengan OmniRoute tempatan. Gunakan 127.0.0.1 dan bukannya localhost untuk mengelakkan isu resolusi IPv6.

Cline / Teruskan / RooCode

Settings → API Configuration:
  Provider: OpenAI Compatible
  Base URL: http://localhost:20128/v1
  API Key: [from OmniRoute dashboard]
  Model: if/kimi-k2-thinking

---

🧪 Penilaian (Evals)

OmniRoute termasuk rangka kerja penilaian terbina dalam untuk menguji kualiti tindak balas LLM terhadap set emas. Aksesnya melalui Analytics → Evals dalam papan pemuka.

Set Emas Terbina dalam

"Set Emas OmniRoute" pra-muat mengandungi 10 kes ujian yang meliputi:

• Salam, matematik, geografi, penjanaan kod
• Pematuhan format JSON, terjemahan, penurunan harga
• Penolakan keselamatan (kandungan berbahaya), pengiraan, logik boolean

Strategi Penilaian

Strategi	Penerangan	Contoh
exact	Output mesti sepadan dengan tepat	"4"
contains	Output mesti mengandungi subrentetan (tidak peka huruf besar-besaran)	"Paris"
regex	Output mesti sepadan dengan corak regex	"1.*2.*3"
custom	Fungsi JS tersuai mengembalikan benar/salah	(output) => output.length > 10

---

🐛 Menyelesaikan masalah

Klik untuk mengembangkan panduan penyelesaian masalah

"Model bahasa tidak memberikan mesej"

• Kuota pembekal habis → Semak penjejak kuota papan pemuka
• Penyelesaian: Gunakan sandaran kombo atau tukar kepada peringkat yang lebih murah

Penghadan kadar

• Kuota langganan habis → Sandar kepada GLM/MiniMax
• Tambah kombo: cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking

Token OAuth tamat tempoh

• Dikemas semula secara automatik oleh OmniRoute
• Jika isu berterusan: Papan Pemuka → Pembekal → Sambung semula

Kos tinggi

• Semak statistik penggunaan dalam Papan Pemuka → Kos
• Tukar model utama kepada GLM/MiniMax
• Gunakan peringkat percuma (Gemini CLI, iFlow) untuk tugasan yang tidak kritikal

Papan pemuka dibuka pada port yang salah

• Tetapkan PORT=20128 dan NEXT_PUBLIC_BASE_URL=http://localhost:20128

Ralat penyegerakan awan

• Sahkan BASE_URL mata pada contoh larian anda
• Sahkan CLOUD_URL mata ke titik akhir awan anda yang dijangkakan
• Pastikan nilai NEXT_PUBLIC_* sejajar dengan nilai sebelah pelayan

Log masuk pertama tidak berfungsi

• Semak INITIAL_PASSWORD dalam .env
• Jika tidak ditetapkan, kata laluan sandaran ialah 123456

Tiada log permintaan

• Tetapkan ENABLE_REQUEST_LOGS=true dalam .env

Ujian sambungan menunjukkan "Tidak sah" untuk pembekal yang serasi dengan OpenAI

• Banyak pembekal tidak mendedahkan titik akhir /models
• OmniRoute v1.0.6+ termasuk pengesahan sandaran melalui pelengkapan sembang
• Pastikan URL asas mengandungi akhiran /v1

🔐 OAuth em Servidor Remoto (Persediaan OAuth Jauh)

⚠️ PENTING untuk biasa menggunakan OmniRoute em VPS/Docker/servidor remoto

Adakah OAuth melakukan Antigraviti / Gemini CLI tidak menggunakan perkhidmatan anda?

Ia membuktikan Antigraviti dan Gemini CLI menggunakan Google OAuth 2.0 untuk autenticação. O Google exige que a redirect_uri gunakan tiada fluks OAuth seja exatamente uma das URIs sebelum kadastrada tiada Google Cloud Console untuk aplicativo.

Sebagai credenciais OAuth embutidas no OmniRoute estão cadastradas apenas untuk localhost. Quando você acessa o OmniRoute em um servidor remoto (cth: https://omniroute.meuservidor.com), o Google rejeita a autenticação com:

Error 400: redirect_uri_mismatch

Penyelesaian: Konfigurasikan suas próprias credenciais OAuth

Você precisa criar um OAuth 2.0 Client ID no Google Cloud Console com a URI do seu servidor.

Passo a passo

1. Akses ke Konsol Awan Google

Abra: https://console.cloud.google.com/apis/credentials

2. Crie um novo ID Pelanggan OAuth 2.0

• Klik em "+ Cipta Bukti Kelayakan" → "ID klien OAuth"
• Tipo de aplicativo: "Aplikasi web"
• Nama: escolha qualquer nome (cth: OmniRoute Remote)

3. Tambah sebagai URI Ubah Hala Dibenarkan

Tiada "URI ubah hala yang dibenarkan", tambahan:

https://seu-servidor.com/callback

Gantikan seu-servidor.com pelo domínio ou IP do seu servidor (termasuk porta se necessário, cth: http://45.33.32.156:20128/callback).

4. Simpan dan salin sebagai kredensia

Após criar, o Google mostrará o ID Pelanggan e o Rahsia Pelanggan.

5. Konfigurasikan sebagai variáveis de ambiente

No seu .env (ou nas variáveis de ambiente do Docker):

# Para Antigravity:
ANTIGRAVITY_OAUTH_CLIENT_ID=seu-client-id.apps.googleusercontent.com
ANTIGRAVITY_OAUTH_CLIENT_SECRET=GOCSPX-seu-secret

# Para Gemini CLI:
GEMINI_OAUTH_CLIENT_ID=seu-client-id.apps.googleusercontent.com
GEMINI_OAUTH_CLIENT_SECRET=GOCSPX-seu-secret
GEMINI_CLI_OAUTH_CLIENT_SECRET=GOCSPX-seu-secret

6. Reinicie o OmniRoute

# Se usando npm:
npm run dev

# Se usando Docker:
docker restart omniroute

7. Tente conectar novamente

Papan pemuka → Pembekal → Antigraviti (ou Gemini CLI) → OAuth

Agora o Google redirectionará corretamente untuk https://seu-servidor.com/callback dan a autenticação funcionará.

---

Penyelesaian sementara (sem configurar credenciais próprias)

Jika anda ingin mendapatkan credenciais próprias agora, ada kemungkinan penggunaan atau fluks manual de URL:

1. OmniRoute abrirá a URL de authorização do Google
2. Após você authorizar, o Google tentará redirectionar para localhost (que falha no servidor remoto)
3. Salin URL lengkap pada penyemak imbas barra de endereço do seu (mesmo que a página não carregue)
4. Cole essa URL no campo que aparece no modal de conexão do OmniRoute
5. Klik em "Sambung"

Penyelesaian ini berfungsi sebagai kodigo de autorização na URL adalah bebas untuk mengubah hala mengikut arahan atau tidak.

---

🛠️ Timbunan Teknologi

• Waktu Jalan: Node.js 18–22 LTS (⚠️ Node.js 24+ tidak disokong — better-sqlite3 binari asli tidak serasi)
• Bahasa: TypeScript 5.9 — 100% TypeScript merentas src/ dan open-sse/ (v1.0.6)
• Kerangka: Next.js 16 + React 19 + Tailwind CSS 4
• Pangkalan Data: LowDB (JSON) + SQLite (keadaan domain + log proksi)
• Penstriman: Acara Dihantar Pelayan (SSE)
• Auth: OAuth 2.0 (PKCE) + JWT + Kunci API
• Ujian: Pelari ujian Node.js (368+ ujian unit)
• CI/CD: GitHub Actions (auto npm publish + Docker Hub pada keluaran)
• Laman web: omniroute.online
• Pakej: npmjs.com/package/omniroute
• Docker: hub.docker.com/r/diegosouzapw/omniroute
• Ketahanan: Pemutus litar, mundur eksponen, kumpulan anti gemuruh, penipuan TLS

---

📖 Dokumentasi

Dokumen	Penerangan
User Guide	Pembekal, kombo, penyepaduan CLI, penggunaan
API Reference	Semua titik akhir dengan contoh
Troubleshooting	Masalah dan penyelesaian biasa
Architecture	Seni bina sistem dan dalaman
Contributing	Persediaan pembangunan dan garis panduan
OpenAPI Spec	Spesifikasi OpenAPI 3.0
Security Policy	Pelaporan kerentanan dan amalan keselamatan
VM Deployment	Panduan lengkap: Persediaan VM + nginx + Cloudflare
Features Gallery	Lawatan papan pemuka visual dengan tangkapan skrin

📸 Pratonton Papan Pemuka

Klik untuk melihat tangkapan skrin papan pemuka

Halaman	Tangkapan skrin
Pembekal
Kombo
Analisis
Kesihatan
Penterjemah
Tetapan
Alat CLI
Log Penggunaan
Titik Akhir

---

🗺️ Pelan Hala Tuju

OmniRoute mempunyai 210+ ciri yang dirancang merentas berbilang fasa pembangunan. Berikut adalah bidang utama:

Kategori	Ciri Terancang	Sorotan
🧠 Penghalaan & Perisikan	25+	Penghalaan kependaman terendah, penghalaan berasaskan teg, kuota prapenerbangan, pemilihan akaun P2C
🔒 Keselamatan & Pematuhan	20+	Pengerasan SSRF, penyelubungan kelayakan, had kadar setiap titik akhir, skop kunci pengurusan
📊 Kebolehlihatan	15+	Penyepaduan OpenTelemetry, pemantauan kuota masa nyata, penjejakan kos setiap model
🔄 Integrasi Pembekal	20+	Pendaftaran model dinamik, penyejukan pembekal, Codex berbilang akaun, penghuraian kuota Copilot
⚡ Prestasi	15+	Lapisan cache dwi, ​​cache gesaan, cache respons, penstriman keepalive, API kelompok
🌐 Ekosistem	10+	API WebSocket, konfigurasi hot-reload, kedai konfigurasi teragih, mod komersial

🔜 Akan Datang

• 🔗 OpenCode Integration — Sokongan pembekal asli untuk IDE pengekodan AI OpenCode
• 🔗 Pengintegrasian TRAE — Sokongan penuh untuk rangka kerja pembangunan TRAE AI
• 📦 API Kelompok — Pemprosesan kelompok tak segerak untuk permintaan pukal
• 🎯 Penghalaan Berasaskan Teg — Permintaan laluan berdasarkan teg tersuai dan metadata
• 💰 Strategi Kos Terendah — Pilih pembekal yang tersedia paling murah secara automatik

📝 Spesifikasi ciri penuh tersedia dalam link (217 spesifikasi terperinci)

---

📧 Sokongan

💬 Sertai komuniti kami! WhatsApp Group — Dapatkan bantuan, kongsi petua dan kekal kemas kini.

• Laman web: omniroute.online
• GitHub: github.com/diegosouzapw/OmniRoute
• Isu: github.com/diegosouzapw/OmniRoute/issues
• WhatsApp: Community Group
• Projek Asal: 9router by decolua

---

👥 Penyumbang

Cara Menyumbang

1. Garpu repositori
2. Buat cawangan ciri anda (git checkout -b feature/amazing-feature)
3. Serahkan perubahan anda (git commit -m 'Add amazing feature')
4. Tolak ke cawangan (git push origin feature/amazing-feature)
5. Buka Permintaan Tarik

Lihat CONTRIBUTING.md untuk garis panduan terperinci.

Mengeluarkan Versi Baharu

# Create a release — npm publish happens automatically
gh release create v1.0.6 --title "v1.0.6" --generate-notes

---

📊 Sejarah Bintang

---

🙏 Ucapan terima kasih

Terima kasih khas kepada 9router oleh decolua — projek asal yang mengilhamkan garpu ini. OmniRoute membina asas yang luar biasa itu dengan ciri tambahan, API berbilang modal dan penulisan semula TypeScript penuh.

Terima kasih khas kepada CLIProxyAPI — pelaksanaan Go asal yang mengilhamkan port JavaScript ini.

---

📄 Lesen

Lesen MIT - lihat LICENSE untuk butiran.

---

_{Dibina dengan ❤️ untuk pembangun yang kod 24/7
omniroute.online}