---
title: "User Guide"
version: 3.8.40
lastUpdated: 2026-06-28
---
# User Guide
๐ **Languages:** ๐บ๐ธ [English](./USER_GUIDE.md) | ๐ง๐ท [Portuguรชs (Brasil)](../i18n/pt-BR/docs/guides/USER_GUIDE.md) | ๐ช๐ธ [Espaรฑol](../i18n/es/docs/guides/USER_GUIDE.md) | ๐ซ๐ท [Franรงais](../i18n/fr/docs/guides/USER_GUIDE.md) | ๐ฎ๐น [Italiano](../i18n/it/docs/guides/USER_GUIDE.md) | ๐ท๐บ [ะ ัััะบะธะน](../i18n/ru/docs/guides/USER_GUIDE.md) | ๐จ๐ณ [ไธญๆ (็ฎไฝ)](../i18n/zh-CN/docs/guides/USER_GUIDE.md) | ๐ฉ๐ช [Deutsch](../i18n/de/docs/guides/USER_GUIDE.md) | ๐ฎ๐ณ [เคนเคฟเคจเฅเคฆเฅ](../i18n/in/docs/guides/USER_GUIDE.md) | ๐น๐ญ [เนเธเธข](../i18n/th/docs/guides/USER_GUIDE.md) | ๐บ๐ฆ [ะฃะบัะฐัะฝััะบะฐ](../i18n/uk-UA/docs/guides/USER_GUIDE.md) | ๐ธ๐ฆ [ุงูุนุฑุจูุฉ](../i18n/ar/docs/guides/USER_GUIDE.md) | ๐ฏ๐ต [ๆฅๆฌ่ช](../i18n/ja/docs/guides/USER_GUIDE.md) | ๐ป๐ณ [Tiแบฟng Viแปt](../i18n/vi/docs/guides/USER_GUIDE.md) | ๐ง๐ฌ [ะัะปะณะฐััะบะธ](../i18n/bg/docs/guides/USER_GUIDE.md) | ๐ฉ๐ฐ [Dansk](../i18n/da/docs/guides/USER_GUIDE.md) | ๐ซ๐ฎ [Suomi](../i18n/fi/docs/guides/USER_GUIDE.md) | ๐ฎ๐ฑ [ืขืืจืืช](../i18n/he/docs/guides/USER_GUIDE.md) | ๐ญ๐บ [Magyar](../i18n/hu/docs/guides/USER_GUIDE.md) | ๐ฎ๐ฉ [Bahasa Indonesia](../i18n/id/docs/guides/USER_GUIDE.md) | ๐ฐ๐ท [ํ๊ตญ์ด](../i18n/ko/docs/guides/USER_GUIDE.md) | ๐ฒ๐พ [Bahasa Melayu](../i18n/ms/docs/guides/USER_GUIDE.md) | ๐ณ๐ฑ [Nederlands](../i18n/nl/docs/guides/USER_GUIDE.md) | ๐ณ๐ด [Norsk](../i18n/no/docs/guides/USER_GUIDE.md) | ๐ต๐น [Portuguรชs (Portugal)](../i18n/pt/docs/guides/USER_GUIDE.md) | ๐ท๐ด [Romรขnฤ](../i18n/ro/docs/guides/USER_GUIDE.md) | ๐ต๐ฑ [Polski](../i18n/pl/docs/guides/USER_GUIDE.md) | ๐ธ๐ฐ [Slovenฤina](../i18n/sk/docs/guides/USER_GUIDE.md) | ๐ธ๐ช [Svenska](../i18n/sv/docs/guides/USER_GUIDE.md) | ๐ต๐ญ [Filipino](../i18n/phi/docs/guides/USER_GUIDE.md) | ๐จ๐ฟ [ฤeลกtina](../i18n/cs/docs/guides/USER_GUIDE.md)
Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
---
## Table of Contents
- [Pricing at a Glance](#-pricing-at-a-glance)
- [Use Cases](#-use-cases)
- [Provider Setup](#-provider-setup)
- [CLI Integration](#-cli-integration)
- [Deployment](#-deployment)
- [Available Models](#-available-models)
- [Advanced Features](#-advanced-features)
- [Auto-Routing (Zero-config)](#-auto-routing-zero-config)
- [MCP & A2A Integration](#-mcp--a2a-integration)
- [Skills System](#-skills-system)
- [Memory System](#-memory-system)
- [Webhooks](#-webhooks)
- [Cloud Agents](#-cloud-agents)
- [Programmatic Management](#-programmatic-management)
- [Internal CLI](#-internal-cli)
- [Desktop Application (Electron)](#-desktop-application-electron)
---
## ๐ฐ Pricing at a Glance
| Tier | Provider | Cost | Quota Reset | Best For |
| ------------------- | ----------------- | ----------- | -------------- | -------------------- |
| **๐ณ SUBSCRIPTION** | Claude Code (Pro) | $20/mo | 5h + weekly | Already subscribed |
| | Codex (Plus/Pro) | $20-200/mo | 5h + weekly | OpenAI users |
| | GitHub Copilot | $10-19/mo | Monthly | GitHub users |
| **๐ API KEY** | DeepSeek | Pay per use | None | Cheap reasoning |
| | Groq | Pay per use | None | Ultra-fast inference |
| | xAI (Grok) | Pay per use | None | Grok 4 reasoning |
| | Mistral | Pay per use | None | EU-hosted models |
| | Perplexity | Pay per use | None | Search-augmented |
| | Together AI | Pay per use | None | Open-source models |
| | Fireworks AI | Pay per use | None | Fast FLUX images |
| | Cerebras | Pay per use | None | Wafer-scale speed |
| | Cohere | Pay per use | None | Command R+ RAG |
| | NVIDIA NIM | Pay per use | None | Enterprise models |
| | Baidu Qianfan | Pay per use | None | ERNIE models |
| **๐ฐ CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
| **๐ FREE** | Qoder | $0 | Unlimited | 8 models free |
| | Qwen | $0 | Unlimited | 3 models free |
| | Kiro | $0 | ~50 credits/mo | Claude free |
---
## ๐ฏ Use Cases
### Case 1: "I have Claude Pro subscription"
**Problem:** Quota expires unused, rate limits during heavy coding
```
Combo: "maximize-claude"
1. cc/claude-opus-4-7 (use subscription fully)
2. glm/glm-4.7 (cheap backup when quota out)
3. if/kimi-k2 (free emergency fallback)
Monthly cost: $20 (subscription) + ~$5 (backup) = $25 total
vs. $20 + hitting limits = frustration
```
### Case 2: "I want zero cost"
**Problem:** Can't afford subscriptions, need reliable AI coding
```
Combo: "free-forever"
1. if/kimi-k2 (unlimited free)
2. qw/qwen3-coder-plus (unlimited free)
Monthly cost: $0
Quality: Production-ready models
```
### Case 3: "I need 24/7 coding, no interruptions"
**Problem:** Deadlines, can't afford downtime
```
Combo: "always-on"
1. cc/claude-opus-4-7 (best quality)
2. cx/gpt-5.5 (second subscription)
3. glm/glm-4.7 (cheap, resets daily)
4. minimax/MiniMax-M2.1 (cheapest, 5h reset)
5. if/kimi-k2 (free unlimited)
Result: 5 layers of fallback = zero downtime
Monthly cost: $20-200 (subscriptions) + $10-20 (backup)
```
### Case 4: "I want FREE AI in OpenClaw"
**Problem:** Need AI assistant in messaging apps, completely free
```
Combo: "openclaw-free"
1. if/qwen3-coder-plus (unlimited free)
2. if/deepseek-r1 (unlimited free)
3. if/kimi-k2 (unlimited free)
Monthly cost: $0
Access via: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
```
---
## ๐ Provider Setup
### ๐ Subscription Providers
#### Claude Code (Pro/Max)
```bash
Dashboard โ Providers โ Connect Claude Code
โ OAuth login โ Auto token refresh
โ 5-hour + weekly quota tracking
Models:
cc/claude-opus-4-7
cc/claude-sonnet-4-6
cc/claude-haiku-4-5-20251001
```
**Pro Tip:** Use Opus for complex tasks, Sonnet for speed. OmniRoute tracks quota per model!
Claude and Claude Code-compatible routes preserve `max` thinking effort for Opus and Sonnet
models. Haiku models do not accept the `max` effort tier, so OmniRoute downgrades that
request to a high thinking budget before sending it upstream.
#### OpenAI Codex (Plus/Pro)
```bash
Dashboard โ Providers โ Connect Codex
โ OAuth login (port 1455)
โ 5-hour + weekly reset
Models:
cx/gpt-5.5
cx/gpt-5.4
cx/gpt-5.3-codex
cx/gpt-5.3-codex-spark
```
#### GitHub Copilot
```bash
Dashboard โ Providers โ Connect GitHub
โ OAuth via GitHub
โ Monthly reset (1st of month)
Models:
gh/gpt-5.5
gh/gpt-5.4
gh/claude-sonnet-4.6
gh/claude-opus-4.7
gh/gemini-3.1-pro-preview
```
### ๐ฐ Cheap Providers
#### GLM-4.7 (Daily reset, $0.6/1M)
1. Sign up: [Zhipu AI](https://open.bigmodel.cn)
2. Get API key from Coding Plan
3. Dashboard โ Add API Key: Provider: `glm`, API Key: `your-key`
**Use:** `glm/glm-4.7` โ **Pro Tip:** Coding Plan offers 3ร quota at 1/7 cost! Reset daily 10:00 AM.
#### MiniMax M2.1 (5h reset, $0.20/1M)
1. Sign up: [MiniMax](https://www.minimax.io)
2. Get API key โ Dashboard โ Add API Key
**Use:** `minimax/MiniMax-M2.1` โ **Pro Tip:** Cheapest option for long context (1M tokens)!
#### Kimi K2 ($9/month flat)
1. Subscribe: [Moonshot AI](https://platform.moonshot.ai)
2. Get API key โ Dashboard โ Add API Key
**Use:** `kimi/kimi-k2.5` โ **Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
#### Baidu Qianfan / ERNIE
1. Sign up: [Baidu AI Cloud Qianfan](https://cloud.baidu.com/product/wenxinworkshop)
2. Create a Qianfan API key โ Dashboard โ Add API Key: Provider: `qianfan`
**Use:** `qianfan/ernie-5.1`, `qianfan/ernie-x1.1`, or another Qianfan OpenAI-compatible model ID.
### ๐ FREE Providers
No-auth free providers have a switch beside **No authentication required** on their provider page.
Turning it off disables that provider, removes it from Providers configured/compact views, and
removes its models from `/v1/models`.
#### Qoder (8 FREE models)
```bash
Dashboard โ Connect Qoder โ OAuth login โ Unlimited usage
Models: if/kimi-k2, if/qwen3-coder-plus, if/qwen3-max, if/qwen3-235b, if/deepseek-r1, if/deepseek-v3.2
```
#### Kiro (Claude FREE)
```bash
Dashboard โ Connect Kiro โ AWS Builder ID or Google/GitHub โ ~50 credits/month
Models: kr/claude-sonnet-4.5, kr/claude-haiku-4.5
```
---
## ๐จ Combos
You can reorder combo cards directly in **Dashboard โ Combos** by dragging the handle on each card. The order is stored in SQLite and restored on reload.
### Example 1: Maximize Subscription โ Cheap Backup
```
Dashboard โ Combos โ Create New
Name: premium-coding
Models:
1. cc/claude-opus-4-7 (Subscription primary)
2. glm/glm-4.7 (Cheap backup, $0.6/1M)
3. minimax/MiniMax-M2.7 (Cheapest fallback, $0.3/1M)
Use in CLI: premium-coding
```
### Example 2: Free-Only (Zero Cost)
```
Name: free-combo
Models:
1. if/kimi-k2 (unlimited)
2. qw/coder-model (unlimited)
Cost: $0 forever!
```
---
## ๐ง CLI Integration
### Cursor IDE
```
Settings โ Models โ Advanced:
OpenAI API Base URL: http://localhost:20128/v1
OpenAI API Key: [from omniroute dashboard]
Model: cc/claude-opus-4-7
```
### Claude Code
Edit `~/.claude/settings.json`:
```json
{
"env": {
"ANTHROPIC_BASE_URL": "http://localhost:20128",
"ANTHROPIC_AUTH_TOKEN": "your-omniroute-api-key"
}
}
```
Use the Claude-compatible root endpoint here. Do not append `/v1` to `ANTHROPIC_BASE_URL`.
### Codex CLI
```bash
export OPENAI_BASE_URL="http://localhost:20128"
export OPENAI_API_KEY="your-omniroute-api-key"
codex "your prompt"
```
### OpenClaw
Edit `~/.openclaw/openclaw.json`:
```json
{
"agents": {
"defaults": {
"model": { "primary": "omniroute/if/kimi-k2" }
}
},
"models": {
"providers": {
"omniroute": {
"baseUrl": "http://localhost:20128/v1",
"apiKey": "your-omniroute-api-key",
"api": "openai-completions",
"models": [{ "id": "if/kimi-k2", "name": "kimi-k2" }]
}
}
}
}
```
**Or use Dashboard:** CLI Tools โ OpenClaw โ Auto-config
### Cline / Continue / RooCode
```
Provider: OpenAI Compatible
Base URL: http://localhost:20128/v1
API Key: [from dashboard]
Model: cc/claude-opus-4-7
```
---
## ๐ Deployment
### Global npm install (Recommended)
```bash
npm install -g omniroute
# Create config directory
mkdir -p ~/.omniroute
# Create .env file (see .env.example)
cp .env.example ~/.omniroute/.env
# Start server
omniroute
# Or with custom port:
omniroute --port 3000
```
The CLI automatically loads `.env` from `~/.omniroute/.env` or `./.env`.
### Uninstalling
When you no longer need OmniRoute, we provide two quick scripts for a clean removal:
| Command | Action |
| ------------------------ | ----------------------------------------------------------------------------------- |
| `npm run uninstall` | Removes the system app but **keeps your DB and configurations** in `~/.omniroute`. |
| `npm run uninstall:full` | Removes the app AND permanently **erases all configurations, keys, and databases**. |
> Note: To run these commands, navigate to the OmniRoute project folder (if you cloned it) and run them. Alternatively, if globally installed, you can simply run `npm uninstall -g omniroute`.
### VPS Deployment
```bash
git clone https://github.com/diegosouzapw/OmniRoute.git
cd OmniRoute && npm install && npm run build
export JWT_SECRET="your-secure-secret-change-this"
export INITIAL_PASSWORD="your-password"
export DATA_DIR="/var/lib/omniroute"
export PORT="20128"
export HOSTNAME="0.0.0.0"
export NODE_ENV="production"
export NEXT_PUBLIC_BASE_URL="http://localhost:20128"
export API_KEY_SECRET="endpoint-proxy-api-key-secret"
npm run start
# Or: pm2 start npm --name omniroute -- start
```
### PM2 Deployment (Low Memory)
For servers with limited RAM, use the memory limit option:
```bash
# With 512MB limit (default)
pm2 start npm --name omniroute -- start
# Or with custom memory limit
OMNIROUTE_MEMORY_MB=512 pm2 start npm --name omniroute -- start
# Or using ecosystem.config.js
pm2 start ecosystem.config.js
```
Create `ecosystem.config.js`:
```javascript
module.exports = {
apps: [
{
name: "omniroute",
script: "npm",
args: "start",
env: {
NODE_ENV: "production",
OMNIROUTE_MEMORY_MB: "512",
JWT_SECRET: "your-secret",
INITIAL_PASSWORD: "your-password",
},
node_args: "--max-old-space-size=512",
max_memory_restart: "300M",
},
],
};
```
### Docker
```bash
# Build image (default = runner-cli with codex/claude/droid preinstalled)
docker build -t omniroute:cli .
# Portable mode (recommended)
docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-data:/app/data omniroute:cli
```
For host-integrated mode with CLI binaries, see the Docker section in the main docs.
### Void Linux (xbps-src)
Void Linux users can package and install OmniRoute natively using the `xbps-src` cross-compilation framework. This automates the Node.js standalone build along with the required `better-sqlite3` native bindings.
View xbps-src template
```bash
# Template file for 'omniroute'
pkgname=omniroute
version=3.8.0
revision=1
hostmakedepends="nodejs python3 make"
depends="openssl"
short_desc="Universal AI gateway with smart routing for multiple LLM providers"
maintainer="zenobit "
license="MIT"
homepage="https://github.com/diegosouzapw/OmniRoute"
distfiles="https://github.com/diegosouzapw/OmniRoute/archive/refs/tags/v${version}.tar.gz"
checksum=009400afee90a9f32599d8fe734145cfd84098140b7287990183dde45ae2245b
system_accounts="_omniroute"
omniroute_homedir="/var/lib/omniroute"
export NODE_ENV=production
export npm_config_engine_strict=false
export npm_config_loglevel=error
export npm_config_fund=false
export npm_config_audit=false
do_build() {
# Determine target CPU arch for node-gyp
local _gyp_arch
case "$XBPS_TARGET_MACHINE" in
aarch64*) _gyp_arch=arm64 ;;
armv7*|armv6*) _gyp_arch=arm ;;
i686*) _gyp_arch=ia32 ;;
*) _gyp_arch=x64 ;;
esac
# 1) Install all deps โ skip scripts
NODE_ENV=development npm ci --ignore-scripts
# 2) Build the Next.js standalone bundle
npm run build
# 3) Copy static assets into standalone
cp -r .next/static .next/standalone/.next/static
[ -d public ] && cp -r public .next/standalone/public || true
# 4) Compile better-sqlite3 native binding
local _node_gyp=/usr/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js
(cd node_modules/better-sqlite3 && node "$_node_gyp" rebuild --arch="$_gyp_arch")
# 5) Place the compiled binding into the standalone bundle
local _bs3_release=.next/standalone/node_modules/better-sqlite3/build/Release
mkdir -p "$_bs3_release"
cp node_modules/better-sqlite3/build/Release/better_sqlite3.node "$_bs3_release/"
# 6) Remove arch-specific sharp bundles
rm -rf .next/standalone/node_modules/@img
# 7) Copy pino runtime deps omitted by Next.js static analysis:
for _mod in pino-abstract-transport split2 process-warning; do
cp -r "node_modules/$_mod" .next/standalone/node_modules/
done
}
do_check() {
npm run test:unit
}
do_install() {
vmkdir usr/lib/omniroute/.next
vcopy .next/standalone/. usr/lib/omniroute/.next/standalone
# Prevent removal of empty Next.js app router dirs by the post-install hook
for _d in \
.next/standalone/.next/server/app/dashboard \
.next/standalone/.next/server/app/dashboard/settings \
.next/standalone/.next/server/app/dashboard/providers; do
touch "${DESTDIR}/usr/lib/omniroute/${_d}/.keep"
done
cat > "${WRKDIR}/omniroute" <<'EOF'
#!/bin/sh
export PORT="${PORT:-20128}"
export DATA_DIR="${DATA_DIR:-${XDG_DATA_HOME:-${HOME}/.local/share}/omniroute}"
export APP_LOG_TO_FILE="${APP_LOG_TO_FILE:-false}"
mkdir -p "${DATA_DIR}"
exec node /usr/lib/omniroute/.next/standalone/server.js "$@"
EOF
vbin "${WRKDIR}/omniroute"
}
post_install() {
vlicense LICENSE
}
```
### Environment Variables
| Variable | Default | Description |
| --------------------------------------- | ------------------------------------ | --------------------------------------------------------------------------------------------------------- |
| `JWT_SECRET` | `omniroute-default-secret-change-me` | JWT signing secret (**change in production**) |
| `INITIAL_PASSWORD` | `CHANGEME` | First login password |
| `DATA_DIR` | `~/.omniroute` | Data directory (db, usage, logs) |
| `PORT` | framework default | Service port (`20128` in examples) |
| `HOSTNAME` | framework default | Bind host (Docker defaults to `0.0.0.0`) |
| `NODE_ENV` | runtime default | Set `production` for deploy |
| `NEXT_PUBLIC_BASE_URL` | `http://localhost:20128` | Public base URL surfaced to the dashboard and exposed to the server (replaces legacy `BASE_URL`) |
| `NEXT_PUBLIC_CLOUD_URL` | `https://omniroute.dev` | Cloud sync endpoint base URL (replaces legacy `CLOUD_URL`) |
| `API_KEY_SECRET` | `endpoint-proxy-api-key-secret` | HMAC secret for generated API keys |
| `REQUIRE_API_KEY` | `false` | Enforce Bearer API key on `/v1/*` |
| `ALLOW_API_KEY_REVEAL` | `false` | Allow authenticated dashboard users to reveal full stored API key values on demand |
| `PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES` | `70` | Server-side refresh cadence for cached Provider Limits data; UI refresh buttons still trigger manual sync |
| `DISABLE_SQLITE_AUTO_BACKUP` | `false` | Disable automatic SQLite snapshots before writes/import/restore; manual backups still work |
| `APP_LOG_TO_FILE` | `true` | Enables application and audit log output to disk |
| `AUTH_COOKIE_SECURE` | `false` | Force `Secure` auth cookie (behind HTTPS reverse proxy) |
| `CLOUDFLARED_BIN` | unset | Use an existing `cloudflared` binary instead of managed download |
| `CLOUDFLARED_PROTOCOL` | `http2` | Transport for managed Quick Tunnels (`http2`, `quic`, or `auto`) |
| `OMNIROUTE_MEMORY_MB` | `512` | Node.js heap limit in MB |
| `PROMPT_CACHE_MAX_SIZE` | `50` | Max prompt cache entries |
| `SEMANTIC_CACHE_MAX_SIZE` | `100` | Max semantic cache entries |
For the full environment variable reference, see the [README](../README.md).
---
## ๐ Available Models
View all available models
> The list below is curated from `open-sse/config/providerRegistry.ts` for v3.8.0. Cloud catalogs (Gemini, OpenRouter, etc.) are synced dynamically โ for the full live catalog open **Dashboard โ Providers โ [provider] โ Available Models** or call `GET /api/models/catalog`.
**Claude Code (`cc/`)** โ Pro/Max OAuth: `cc/claude-opus-4-8`, `cc/claude-opus-4-7`, `cc/claude-opus-4-6`, `cc/claude-opus-4-5-20251101`, `cc/claude-sonnet-4-6`, `cc/claude-sonnet-4-5-20250929`, `cc/claude-haiku-4-5-20251001`
**Codex (`cx/`)** โ Plus/Pro OAuth: `cx/gpt-5.5` (+ effort tiers: `gpt-5.5-xhigh`, `gpt-5.5-high`, `gpt-5.5-medium`, `gpt-5.5-low`), `cx/gpt-5.4`, `cx/gpt-5.4-mini`, `cx/gpt-5.3-codex`, `cx/gpt-5.3-codex-spark`
**GitHub Copilot (`gh/`)** โ OAuth: `gh/gpt-5.5`, `gh/gpt-5.4`, `gh/gpt-5.4-mini`, `gh/gpt-5-mini`, `gh/gpt-5.3-codex`, `gh/claude-opus-4.7`, `gh/claude-opus-4.6`, `gh/claude-opus-4-5-20251101`, `gh/claude-sonnet-4.6`, `gh/claude-sonnet-4.5`, `gh/claude-haiku-4.5`, `gh/gemini-3.1-pro-preview`, `gh/gemini-3-flash-preview`, `gh/oswe-vscode-prime`
**Kiro (`kr/`)** โ FREE OAuth: `kr/auto-kiro`, `kr/claude-opus-4.7`, `kr/claude-opus-4.6`, `kr/claude-sonnet-4.6`, `kr/claude-sonnet-4.5`, `kr/claude-haiku-4.5`, `kr/deepseek-3.2`, `kr/minimax-m2.5`, `kr/minimax-m2.1`, `kr/glm-5`, `kr/qwen3-coder-next`
**Qoder (`if/`)** โ FREE OAuth: `if/kimi-k2-0905`, `if/kimi-k2`, `if/qwen3-coder-plus`, `if/qwen3-max`, `if/qwen3-max-preview`, `if/qwen3-vl-plus`, `if/qwen3-32b`, `if/qwen3-235b-a22b-thinking-2507`, `if/qwen3-235b-a22b-instruct`, `if/qwen3-235b`, `if/deepseek-v3.2`, `if/deepseek-v3`, `if/deepseek-r1`, `if/qoder-rome-30ba3b`
**Qwen (`qw/`)** โ FREE OAuth (chat.qwen.ai): `qw/coder-model`, `qw/vision-model`
**GLM (`glm/`, `glm-cn/`, `zai/`, `glmt/`)** โ $0.2โ0.6/1M: `glm/glm-5.1`, `glm/glm-5`, `glm/glm-5-turbo`, `glm/glm-4.7`, `glm/glm-4.7-flash`, `glm/glm-4.6`, `glm/glm-4.6v`, `glm/glm-4.5`, `glm/glm-4.5v`, `glm/glm-4.5-air`
**MiniMax (`minimax/`, `minimax-cn/`)** โ $0.2/1M: `minimax/MiniMax-M2.7`, `minimax/MiniMax-M2.7-highspeed`, `minimax/MiniMax-M2.5`, `minimax/MiniMax-M2.5-highspeed`
**Kimi (`kimi/`, `kimi-coding/`, `kimi-coding-apikey/`)** โ $9/mo flat or per-use: `kimi/kimi-k2.6`, `kimi/kimi-k2.5`
**DeepSeek (`ds/`)** โ API key: `ds/deepseek-v4-pro`, `ds/deepseek-v4-flash`
**Groq (`groq/`)** โ Ultra-fast: `groq/llama-3.3-70b-versatile`, `groq/meta-llama/llama-4-maverick-17b-128e-instruct`, `groq/qwen/qwen3-32b`, `groq/openai/gpt-oss-120b`
**xAI (`xai/`)** โ Grok native: `xai/grok-4.3`, `xai/grok-4.20-multi-agent-0309`, `xai/grok-4.20-0309-reasoning`, `xai/grok-4.20-0309-non-reasoning`
**Mistral (`mistral/`)** โ EU-hosted: `mistral/mistral-large-latest`, `mistral/mistral-medium-3-5`, `mistral/mistral-small-latest`, `mistral/devstral-latest`, `mistral/codestral-latest`
**Perplexity (`pplx/`)** โ Search-augmented: `pplx/sonar-deep-research`, `pplx/sonar-reasoning-pro`, `pplx/sonar-pro`, `pplx/sonar`
**Together AI (`together/`)** โ Open-source: `together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free` (free), `together/meta-llama/Llama-Vision-Free`, `together/deepseek-ai/DeepSeek-R1-Distill-Llama-70B-Free`, `together/deepseek-ai/DeepSeek-R1`, `together/Qwen/Qwen3-235B-A22B`, `together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8`
**Fireworks AI (`fireworks/`)** โ Fast inference: `fireworks/accounts/fireworks/models/kimi-k2p6`, `fireworks/accounts/fireworks/models/minimax-m2p7`, `fireworks/accounts/fireworks/models/qwen3p6-plus`, `fireworks/accounts/fireworks/models/glm-5p1`, `fireworks/accounts/fireworks/models/deepseek-v4-pro`
**Cerebras (`cerebras/`)** โ Wafer-scale: `cerebras/zai-glm-4.7`, `cerebras/gpt-oss-120b`
**Cohere (`cohere/`)** โ RAG-focused: `cohere/command-a-reasoning-08-2025`, `cohere/command-a-vision-07-2025`, `cohere/command-a-03-2025`, `cohere/command-r-08-2024`
**NVIDIA NIM (`nvidia/`)** โ Enterprise: `nvidia/z-ai/glm-5.1`, `nvidia/minimaxai/minimax-m2.7`, `nvidia/google/gemma-4-31b-it`, `nvidia/mistralai/mistral-small-4-119b-2603`, `nvidia/mistralai/mistral-large-3-675b-instruct-2512`, `nvidia/qwen/qwen3.5-397b-a17b`, `nvidia/deepseek-ai/deepseek-v4-pro`, `nvidia/openai/gpt-oss-120b`, `nvidia/nvidia/nemotron-3-super-120b-a12b`
**Baidu Qianfan (`qianfan/`)** โ ERNIE: `qianfan/ernie-5.1`, `qianfan/ernie-5.0-thinking-latest`, `qianfan/ernie-x1.1`
**Ollama Cloud (`ollama-cloud/`)**: `ollama-cloud/deepseek-v4-pro`, `ollama-cloud/deepseek-v4-flash`, `ollama-cloud/kimi-k2.6`, `ollama-cloud/glm-5.1`, `ollama-cloud/minimax-m2.7`, `ollama-cloud/gemma4:31b`, `ollama-cloud/qwen3.5:397b`
**Gemini (Google Cloud `gemini/`)**: Synced live per API key from Google โ no static list. Connect a key in **Dashboard โ Providers** then use **Available Models** to import the current catalog (e.g. `gemini/gemini-3-pro`, `gemini/gemini-3-flash`).
**Other compatible providers** (selected): `cohere`, `databricks`, `snowflake`, `together`, `vertex`, `alibaba`, `alibaba-cn`, `bedrock` (via `aws-bedrock`), `azure-ai`, `openrouter` (passthrough catalog), `siliconflow`, `hyperbolic`, `huggingface`, `featherless-ai`, `cloudflare-ai`, `scaleway`, `deepinfra`, `vercel-ai-gateway`, `bazaarlink`, `friendliai`, `nous-research`, `reka`, `volcengine`, `ai21`, `gigachat`. Each maintains its own model list in `providerRegistry.ts` and can be auto-synced when the provider exposes a `/models` endpoint.
**Note on model IDs:** OmniRoute uses provider-native IDs (`claude-opus-4-8`, `gpt-5.5`, `glm-5.1`, `MiniMax-M2.7`, `kimi-k2.5`, `grok-4.20-0309-reasoning`). Some IDs include dotted versions because that is how the upstream API expects them. If a model is not listed above, run `omniroute models --search ` or hit `GET /api/models/catalog` to confirm availability.
---
## ๐งฉ Advanced Features
### Custom Models
Add any model ID to any provider without waiting for an app update:
```bash
# Via API
curl -X POST http://localhost:20128/api/provider-models \
-H "Content-Type: application/json" \
-d '{"provider": "openai", "modelId": "gpt-5.2", "modelName": "GPT-5.2"}'
# List: curl http://localhost:20128/api/provider-models?provider=openai
# Remove: curl -X DELETE "http://localhost:20128/api/provider-models?provider=openai&model=gpt-5.2"
```
Or use Dashboard: **Providers โ [Provider] โ Custom Models**.
Notes:
- OpenRouter and OpenAI/Anthropic-compatible providers are managed from **Available Models** only. Manual add, import, and auto-sync all land in the same available-model list, so there is no separate Custom Models section for those providers.
- The **Custom Models** section is intended for providers that do not expose managed available-model imports.
### Dedicated Provider Routes
Route requests directly to a specific provider with model validation:
```bash
POST http://localhost:20128/v1/providers/openai/chat/completions
POST http://localhost:20128/v1/providers/openai/embeddings
POST http://localhost:20128/v1/providers/fireworks/images/generations
```
The provider prefix is auto-added if missing. Mismatched models return `400`.
### Network Proxy Configuration
```bash
# Set global proxy
curl -X PUT http://localhost:20128/api/settings/proxy \
-d '{"global": {"type":"http","host":"proxy.example.com","port":"8080"}}'
# Per-provider proxy
curl -X PUT http://localhost:20128/api/settings/proxy \
-d '{"providers": {"openai": {"type":"socks5","host":"proxy.example.com","port":"1080"}}}'
# Test proxy
curl -X POST http://localhost:20128/api/settings/proxy/test \
-d '{"proxy":{"type":"socks5","host":"proxy.example.com","port":"1080"}}'
```
**Precedence:** Key-specific โ Combo-specific โ Provider-specific โ Global โ Environment.
### Model Catalog API
```bash
curl http://localhost:20128/api/models/catalog
```
Returns models grouped by provider with types (`chat`, `embedding`, `image`).
### Cloud Sync
- Sync providers, combos, and settings across devices
- Automatic background sync with timeout + fail-fast
- Prefer server-side `NEXT_PUBLIC_BASE_URL`/`NEXT_PUBLIC_CLOUD_URL` in production
### Cloudflare Quick Tunnel
- Available in **Dashboard โ Endpoints** for Docker and other self-hosted deployments
- Creates a temporary `https://*.trycloudflare.com` URL that forwards to your current OpenAI-compatible `/v1` endpoint
- First enable installs `cloudflared` only when needed; later restarts reuse the same managed binary
- Quick Tunnels are not auto-restored after an OmniRoute or container restart; re-enable them from the dashboard when needed
- Tunnel URLs are ephemeral and change every time you stop/start the tunnel
- Managed Quick Tunnels default to HTTP/2 transport to avoid noisy QUIC UDP buffer warnings in constrained containers
- Set `CLOUDFLARED_PROTOCOL=quic` or `auto` if you want to override the managed transport choice
- Set `CLOUDFLARED_BIN` if you prefer using a preinstalled `cloudflared` binary instead of the managed download
- Cloudflare Quick Tunnel, Tailscale Funnel, and ngrok Tunnel panels can be shown or hidden in **Settings โ Appearance**. Hiding a panel does not stop a running tunnel.
### LLM Gateway Intelligence (Phase 9)
- **Semantic Cache** โ Auto-caches non-streaming, temperature=0 responses (bypass with `X-OmniRoute-No-Cache: true`)
- **Request Idempotency** โ Deduplicates requests within 5s via `Idempotency-Key` or `X-Request-Id` header
- **Progress Tracking** โ Opt-in SSE `event: progress` events via `X-OmniRoute-Progress: true` header
---
### Translator Playground
Access via **Dashboard โ Translator**. Debug and visualize how OmniRoute translates API requests between providers.
| Mode | Purpose |
| ---------------- | -------------------------------------------------------------------------------------- |
| **Playground** | Select source/target formats, paste a request, and see the translated output instantly |
| **Chat Tester** | Send live chat messages through the proxy and inspect the full request/response cycle |
| **Test Bench** | Run batch tests across multiple format combinations to verify translation correctness |
| **Live Monitor** | Watch real-time translations as requests flow through the proxy |
**Use cases:**
- Debug why a specific client/provider combination fails
- Verify that thinking tags, tool calls, and system prompts translate correctly
- Compare format differences between OpenAI, Claude, Gemini, and Responses API formats
---
### Routing Strategies
Configure via **Dashboard โ Settings โ Routing**. The dashboard exposes the six most-used strategies; combos and the auto-router internally support a wider set.
**Dashboard-visible strategies (account-level routing):**
| Strategy | Description |
| ------------------------------ | ------------------------------------------------------------------------------------------------ |
| **Fill First** | Uses accounts in priority order โ primary account handles all requests until unavailable |
| **Round Robin** | Cycles through all accounts with a configurable sticky limit (default: 3 calls per account) |
| **P2C (Power of Two Choices)** | Picks 2 random accounts and routes to the healthier one โ balances load with awareness of health |
| **Random** | Randomly selects an account for each request using Fisher-Yates shuffle |
| **Least Used** | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly |
| **Cost Optimized** | Routes to the account with the lowest priority value, optimizing for lowest-cost providers |
**Advanced combo and auto strategies** (configurable per combo or via `auto/*` prefixes โ see [AUTO-COMBO.md](../routing/AUTO-COMBO.md)):
- `priority` โ strict order, never round-robins
- `weighted` โ proportional traffic split by per-model weights
- `fill-first` โ drain the first model until limits hit
- `round-robin` / `strict-random` / `random`
- `p2c` (Power of Two Choices)
- `least-used` and `cost-optimized`
- `auto` โ score-driven across all candidates
- `lkgp` (Last Known Good Provider) โ sticks to the last successful model per session
- `context-optimized` โ picks the model with the largest free context window
- `context-relay` โ chains long-context models for follow-up turns
#### External Sticky Session Header
For external session affinity (for example, Claude Code/Codex agents behind reverse proxies), send:
```http
X-Session-Id: your-session-key
```
OmniRoute also accepts `x_session_id` and returns the effective session key in `X-OmniRoute-Session-Id`.
If you use Nginx and send underscore-form headers, enable:
```nginx
underscores_in_headers on;
```
#### Wildcard Model Aliases
Create wildcard patterns to remap model names:
```
Pattern: claude-sonnet-* โ Target: cc/claude-sonnet-4-6
Pattern: gpt-* โ Target: gh/gpt-5.3-codex
```
Wildcards support `*` (any characters) and `?` (single character).
#### Fallback Chains
Define global fallback chains that apply across all requests:
```
Chain: production-fallback
1. cc/claude-opus-4-7
2. gh/gpt-5.3-codex
3. glm/glm-4.7
```
---
### Resilience & Circuit Breakers
Configure via **Dashboard โ Settings โ Resilience**.
OmniRoute implements provider-level resilience with five components:
1. **Request Queue & Pacing** โ System-level request shaping:
- **Requests Per Minute (RPM)** โ Maximum requests per minute per account
- **Min Time Between Requests** โ Minimum gap in milliseconds between requests
- **Max Concurrent Requests** โ Maximum simultaneous requests per account
2. **Connection Cooldown** โ Per-auth-type configuration for a single connection after retryable failures:
- **Base Cooldown** โ Default cooldown window for retryable upstream failures
- **Use Upstream Retry Hints** โ Honors authoritative `Retry-After` or reset hints when provided
- **Max Backoff Steps** โ Maximum exponential backoff level for repeated failures
3. **Provider Circuit Breaker** โ Tracks end-to-end provider failures, marks a provider degraded at the configured warning threshold, and opens the breaker when the configured failure threshold is reached:
- **Degradation Threshold** โ Consecutive provider failures before entering `DEGRADED`
- **Failure Threshold** โ Consecutive provider failures before entering `OPEN`
- **Reset Timeout** โ Time window before the provider is tested again
- **CLOSED** (Healthy) โ Requests flow normally
- **DEGRADED** โ Requests still flow while elevated failures are tracked
- **OPEN** โ Provider is temporarily blocked after repeated failures
- **HALF_OPEN** โ Testing if provider has recovered
Connection-scoped `429` rate limits stay in **Connection Cooldown** and do not count toward the provider breaker.
The provider breaker runtime state is shown on **Dashboard โ Health** only.
4. **Wait For Cooldown** โ If every candidate connection is already cooling down, OmniRoute can wait for the earliest cooldown and retry the same client request automatically.
5. **Rate Limit Auto-Detection** โ When upstream providers return explicit wait windows, those hints override the local connection cooldown when the setting is enabled.
**Pro Tip:** Use the **Health** page to inspect and reset live provider breakers after an outage. The Resilience page only changes configuration.
---
### Database Export / Import
Manage database backups in **Dashboard โ Settings โ System & Storage**.
| Action | Description |
| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Export Database** | Downloads the current SQLite database as a `.sqlite` file |
| **Export All (.tar.gz)** | Downloads a full backup archive including: database, settings, combos, provider connections (no credentials), API key metadata |
| **Import Database** | Upload a `.sqlite` file to replace the current database. A pre-import backup is automatically created unless `DISABLE_SQLITE_AUTO_BACKUP=true` |
```bash
# API: Export database
curl -o backup.sqlite http://localhost:20128/api/db-backups/export
# API: Export all (full archive)
curl -o backup.tar.gz http://localhost:20128/api/db-backups/exportAll
# API: Import database
curl -X POST http://localhost:20128/api/db-backups/import \
-F "file=@backup.sqlite"
```
**Import Validation:** The imported file is validated for integrity (SQLite pragma check), required tables (`provider_connections`, `provider_nodes`, `combos`, `api_keys`), and size (max 100MB).
**Use Cases:**
- Migrate OmniRoute between machines
- Create external backups for disaster recovery
- Share configurations between team members (export all โ share archive)
---
### Settings Dashboard
The settings page is organized into **7 tabs** for easy navigation:
| Tab | Contents |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **General** | System storage tools, default behavior, Endpoint tunnel visibility |
| **Appearance** | Theme controls (light/dark/system), sidebar visibility, panel toggles for Cloudflare/Tailscale/ngrok tunnel cards |
| **AI** | Thinking budget configuration, global system prompt injection, prompt cache stats |
| **Security** | Login/Password settings, IP Access Control, API auth for `/models`, Provider Blocking, prompt-injection guard |
| **Routing** | Global routing strategy (Fill First / Round Robin / P2C / Random / Least Used / Cost Optimized), wildcard model aliases, fallback chains, combo defaults |
| **Resilience** | Request queue, connection cooldown, provider breaker config, and wait-for-cooldown behavior |
| **Advanced** | Global proxy configuration (HTTP/SOCKS5), per-provider proxy overrides |
General no longer duplicates read-only logging and cache notes. Database retention and
optimization settings are persisted through `/api/settings/database`; manual cache clearing uses
`DELETE /api/cache`. Request and proxy log row caps are controlled by
`CALL_LOGS_TABLE_MAX_ROWS` and `PROXY_LOGS_TABLE_MAX_ROWS`.
---
### Costs & Budget Management
Access via **Dashboard โ Costs**.
| Tab | Purpose |
| ----------- | ---------------------------------------------------------------------------------------- |
| **Budget** | Set spending limits per API key with daily/weekly/monthly budgets and real-time tracking |
| **Pricing** | View and edit model pricing entries โ cost per 1K input/output tokens per provider |
```bash
# API: Set a budget
curl -X POST http://localhost:20128/api/usage/budget \
-H "Content-Type: application/json" \
-d '{"keyId": "key-123", "limit": 50.00, "period": "monthly"}'
# API: Get current budget status
curl http://localhost:20128/api/usage/budget
```
**Cost Tracking:** Every request logs token usage and calculates cost using the pricing table. View breakdowns in **Dashboard โ Usage** by provider, model, and API key.
---
### Audio Transcription
OmniRoute supports audio transcription via the OpenAI-compatible endpoint:
```bash
POST /v1/audio/transcriptions
Authorization: Bearer your-api-key
Content-Type: multipart/form-data
# Example with curl
curl -X POST http://localhost:20128/v1/audio/transcriptions \
-H "Authorization: Bearer your-api-key" \
-F "file=@audio.mp3" \
-F "model=deepgram/nova-3"
```
**Speech-to-Text (transcription)** providers:
- `openai/` (whisper-compatible)
- `groq/` (Groq Whisper Turbo)
- `deepgram/` (Nova family)
- `assemblyai/`
- `nvidia/` (Parakeet, Canary)
- `huggingface/` (whisper variants)
- `qwen/`
**Text-to-Speech (`POST /v1/audio/speech`)** providers:
- `openai/` (tts-1, tts-1-hd)
- `hyperbolic/`
- `deepgram/` (Aura)
- `nvidia/` (Magpie TTS)
- `elevenlabs/`
- `huggingface/`
- `inworld/`
- `cartesia/`
- `playht/`
- `kie/`
- `aws-polly/`
- `xiaomi-mimo/`
- `coqui/`, `tortoise/`
- `qwen/`
Supported audio formats for transcription: `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`. TTS output formats depend on the provider (mp3, wav, opus, pcm, mulaw).
---
### Combo Balancing Strategies
Configure per-combo balancing in **Dashboard โ Combos โ Create/Edit โ Strategy**.
| Strategy | Description |
| ------------------ | ------------------------------------------------------------------------ |
| **Round-Robin** | Rotates through models sequentially |
| **Priority** | Always tries the first model; falls back only on error |
| **Random** | Picks a random model from the combo for each request |
| **Weighted** | Routes proportionally based on assigned weights per model |
| **Least-Used** | Routes to the model with the fewest recent requests (uses combo metrics) |
| **Cost-Optimized** | Routes to the cheapest available model (uses pricing table) |
Global combo defaults can be set in **Dashboard โ Settings โ Routing โ Combo Defaults**.
Combo target timeouts inherit the current request timeout by default. Use **Target timeout
(seconds)** on combo defaults or an individual combo only when a shorter per-target limit should
trigger faster fallback.
Zero-latency combo optimizations are opt-in. Leave **Zero-latency optimizations** disabled to
prevent these latency features from racing fallback targets, skipping targets based on TTFT
history, or compressing fallback requests; enabling it allows configured hedging, predictive TTFT
skips, and proactive fallback compression to trade routing/request fidelity for lower tail
latency.
Disable **Reasoning token buffer** when upstream providers require strict
`max_tokens` / `maxOutputTokens` limits. When enabled, combo routing only adds reasoning-model
headroom for models with a known output cap and leaves the client token limit unchanged when the
safe buffered value would exceed that cap. If the client limit is already above a known cap,
OmniRoute clamps it down to that cap before sending the upstream request.
---
### Health Dashboard
Access via **Dashboard โ Health**. Real-time system health overview with 6 cards:
| Card | What It Shows |
| --------------------- | ----------------------------------------------------------- |
| **System Status** | Uptime, version, memory usage, data directory |
| **Provider Health** | Global provider circuit breaker runtime state |
| **Rate Limits** | Active connection cooldowns per account with remaining time |
| **Active Lockouts** | Active model-scoped lockouts and temporary exclusions |
| **Signature Cache** | Deduplication cache stats (active keys, hit rate) |
| **Latency Telemetry** | p50/p95/p99 latency aggregation per provider |
**Pro Tip:** The Health page auto-refreshes every 10 seconds. Use the circuit breaker card to identify which providers are experiencing issues.
---
## ๐ค Auto-Routing (Zero-config)
OmniRoute ships with a **score-driven auto-router** that picks the best model for each request across every connected provider โ no combo to maintain. Just send the request with one of the `auto/*` prefixes and OmniRoute will assemble a virtual combo on the fly, scoring candidates on latency, cost, success rate, context fit, model fitness for the task, recent failures, quota, and circuit-breaker state.
| Prefix | Optimizes for |
| -------------- | ----------------------------------------------------------------------------- |
| `auto` | Balanced default (latency ร cost ร success rate) |
| `auto/coding` | Coding tasks: prefers Claude, GPT-5, GLM, Kimi, Qwen Coder, DeepSeek coders |
| `auto/cheap` | Lowest $/token, accepts higher latency |
| `auto/fast` | Lowest latency, ignores cost |
| `auto/offline` | Local-only providers (Ollama, vLLM, llama.cpp) โ useful for air-gapped setups |
| `auto/smart` | Reasoning quality first (Opus, GPT-5 xhigh, R1, GLM 5.1 reasoning) |
| `auto/lkgp` | "Last Known Good Provider" โ sticky to the most recently successful target |
Example:
```bash
curl -X POST http://localhost:20128/v1/chat/completions \
-H "Authorization: Bearer $OMNIROUTE_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "auto/coding",
"messages": [{ "role": "user", "content": "Refactor this Python function" }],
"stream": true
}'
```
The auto-router is fully described in [AUTO-COMBO.md](../routing/AUTO-COMBO.md) โ including how to tune scoring weights, blacklist providers, and inspect routing decisions in **Dashboard โ Auto Combo**.
---
## ๐ MCP & A2A Integration
OmniRoute is both an **MCP server** (Model Context Protocol) and an **A2A server** (Agent-to-Agent JSON-RPC 2.0). Any MCP-compatible IDE or agent host can call OmniRoute tools directly โ no extra wrapper required.
### MCP transports
- **SSE**: `http://localhost:20128/api/mcp/sse`
- **Streamable HTTP**: `http://localhost:20128/api/mcp/stream`
- **stdio**: `omniroute --mcp` (for IDE plugins that prefer stdio)
### Connect Claude Desktop
Edit `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or the equivalent on Windows/Linux:
```json
{
"mcpServers": {
"omniroute": {
"command": "omniroute",
"args": ["--mcp"]
}
}
}
```
### Connect Cursor / Continue / VS Code MCP
Use the SSE URL `http://localhost:20128/api/mcp/sse` and a Bearer API key generated in **Dashboard โ API Keys**.
### Scopes
MCP tools are grouped into 10 scopes: `analytics`, `auth`, `billing`, `combos`, `health`, `keys`, `memory`, `models`, `providers`, `system`. Each Bearer key can be limited to specific scopes โ see [MCP-SERVER.md](../frameworks/MCP-SERVER.md) for the full tool catalog and [A2A-SERVER.md](../frameworks/A2A-SERVER.md) for the JSON-RPC schema.
---
## ๐ง Skills System
OmniRoute exposes an extensible **skill framework** (`src/lib/skills/`) so agents and the A2A endpoint can run domain-specific routines (e.g. `code-review`, `summarize`, `extract-facts`, `web-research`).
- **Marketplace UI** โ Browse and install skills from **Dashboard โ Skills**
- **Per-key scopes** โ Restrict which API keys can invoke which skills
- **Custom skills** โ Drop a TypeScript file in `src/lib/a2a/skills/`, register it, and it becomes immediately invocable over A2A
Full reference: [SKILLS.md](../frameworks/SKILLS.md).
---
## ๐พ Memory System
OmniRoute persists **long-term conversational memory** with hybrid retrieval:
- **SQLite FTS5** for keyword search across past turns
- **Qdrant vector store** (optional) for semantic recall
- **Automatic fact extraction** โ entities, preferences, and decisions are summarized after each session and stored in the `memory_facts` table
- Memories are scoped per API key and per session
Manage memories in **Dashboard โ Memory** (search, edit, export, purge). The HTTP surface (`/api/memory/*`) lets agents push and query facts programmatically โ see [MEMORY.md](../frameworks/MEMORY.md).
---
## ๐ Webhooks
Subscribe to OmniRoute events for real-time monitoring and automation.
- Create a webhook in **Dashboard โ Webhooks** with target URL and HMAC signing secret
- Available events: `request.completed`, `request.failed`, `provider.unavailable`, `budget.exceeded`, `combo.switched`, `circuit_breaker.opened`, `circuit_breaker.closed`
- Every payload includes `X-OmniRoute-Signature` (HMAC-SHA256) for verification
- Retries: 3 attempts with exponential backoff, then dead-letter queue
Full schema in [WEBHOOKS.md](../frameworks/WEBHOOKS.md).
---
## โ๏ธ Cloud Agents
OmniRoute integrates with cloud coding agents (**OpenAI Codex Cloud**, **Devin**, **Jules**, **Antigravity**) so you can dispatch long-running tasks from the same dashboard that handles your local routing.
- Create tasks in **Dashboard โ Cloud Agents** or via `POST /api/v1/agents/tasks`
- Track status, logs, and artifacts per task
- Bring-your-own API key per provider โ credentials never leave the OmniRoute instance
Full reference: [CLOUD_AGENT.md](../frameworks/CLOUD_AGENT.md).
---
## ๐ ๏ธ Programmatic Management
You can manage every OmniRoute resource (providers, combos, keys, settings) over HTTP using a **Bearer key with the `manage` scope**.
Generate the key in **Dashboard โ API Keys โ New Key โ Scope: manage**, then:
```bash
# List providers
curl http://localhost:20128/api/providers \
-H "Authorization: Bearer $OMNIROUTE_MANAGE_KEY"
# Add a provider connection
curl -X POST http://localhost:20128/api/providers \
-H "Authorization: Bearer $OMNIROUTE_MANAGE_KEY" \
-H "Content-Type: application/json" \
-d '{ "provider": "openai", "apiKey": "sk-...", "name": "main" }'
# Create a combo
curl -X POST http://localhost:20128/api/combos \
-H "Authorization: Bearer $OMNIROUTE_MANAGE_KEY" \
-H "Content-Type: application/json" \
-d '{ "name": "premium", "strategy": "priority", "models": [{ "model": "cc/claude-opus-4-7" }, { "model": "glm/glm-5.1" }] }'
# List/create API keys
curl http://localhost:20128/api/keys -H "Authorization: Bearer $OMNIROUTE_MANAGE_KEY"
curl -X POST http://localhost:20128/api/keys -H "Authorization: Bearer $OMNIROUTE_MANAGE_KEY" \
-d '{ "name": "ci-bot", "scopes": ["chat"] }'
```
See [API_REFERENCE.md](../reference/API_REFERENCE.md) for the full endpoint catalog and request/response schemas.
---
## ๐ป Internal CLI
OmniRoute ships an internal CLI (`omniroute โฆ`) for setup, diagnostics, and runtime control. This is **separate from the "CLI Tools" page in the dashboard**, which configures third-party CLIs (Claude Code, Cursor, Codex, Cline, โฆ) so they can talk to OmniRoute.
```bash
omniroute setup # Interactive wizard (password, providers, combos)
omniroute setup --non-interactive # CI-friendly
omniroute doctor # Health diagnostics (data dir, DB, providers, ports)
omniroute providers available # List supported providers
omniroute providers list # List configured connections
omniroute providers test # Live test a provider connection
omniroute combos list # List combos
omniroute combos switch # Set default combo
omniroute models # List available models (--json, --search)
omniroute keys add | list | remove # Manage API keys from the terminal
omniroute backup # Snapshot config + DB
omniroute restore [] # Restore from a snapshot
omniroute health # Detailed health (breakers, cache, memory)
omniroute quota # Provider quota usage
omniroute mcp status # MCP server status
omniroute a2a status # A2A server status
omniroute tunnel list|create|stop # Cloudflare/Tailscale/ngrok tunnels
omniroute reset-password # Reset the admin password
omniroute --mcp # Start MCP server over stdio
omniroute --port 3000 # Start the server on a custom port
```
Tip: pair `omniroute doctor --json` with your monitoring tool to alert on unhealthy provider connections.
---
## ๐ฅ๏ธ Desktop Application (Electron)
OmniRoute is available as a native desktop application for Windows, macOS, and Linux.
### Installation
```bash
# From the electron directory:
cd electron
npm install
# Development mode (connect to running Next.js dev server):
npm run dev
# Production mode (uses standalone build):
npm start
```
### Building Installers
```bash
cd electron
npm run build # Current platform
npm run build:win # Windows (.exe NSIS)
npm run build:mac # macOS (.dmg universal)
npm run build:linux # Linux (.AppImage)
```
Output โ `electron/dist-electron/`
### Key Features
| Feature | Description |
| --------------------------- | ---------------------------------------------------- |
| **Server Readiness** | Polls server before showing window (no blank screen) |
| **System Tray** | Minimize to tray, change port, quit from tray menu |
| **Port Management** | Change server port from tray (auto-restarts server) |
| **Content Security Policy** | Restrictive CSP via session headers |
| **Single Instance** | Only one app instance can run at a time |
| **Offline Mode** | Bundled Next.js server works without internet |
### Environment Variables
| Variable | Default | Description |
| --------------------- | ------- | -------------------------------- |
| `OMNIROUTE_PORT` | `20128` | Server port |
| `OMNIROUTE_MEMORY_MB` | `512` | Node.js heap limit (64โ16384 MB) |
๐ Full documentation: [`electron/README.md`](../../electron/README.md)