当前你家常用AI常用器

Critical requirements for a working restore

[<img src="docs/icons/quickstart.svg" width="20" height="20" style="vertical-align:middle;margin-right:6px;" alt=""> Deploy without Git](#-deploy-without-git)

No git clone needed. Create two files and go:

1. Create .env with your secrets:

```bash

Via Docker

docker exec -i postgres-container pg_restore --clean --if-exists -U user -d dbname < backup_file.dump ```

[<img src="docs/icons/quickstart.svg" width="20" height="20" style="vertical-align:middle;margin-right:6px;" alt=""> Quick Start](#-quick-start)

git clone <repository-url>
cd model-hotel

cp .env.example .env
nano .env          # set a strong MASTER_KEY and POSTGRES_PASSWORD

docker compose -f docker-compose.yml -f compose.dev.yml up --build -d

For development, use the dev compose override: docker compose -f docker-compose.yml -f compose.dev.yml up -d. To use the prebuilt image instead of building from source, edit docker-compose.yml: comment out build: . and uncomment the image: line.

The admin token is displayed once in the logs on first run and will never be shown again:

docker compose -f docker-compose.yml -f compose.dev.yml logs app | grep "ADMIN_TOKEN="

If you lose the token, delete .data/admin-token and restart to generate a new one.

You can also set a fixed admin token via the ADMIN_TOKEN environment variable.

Open http://localhost:8081, log in with that token, add your first provider, and start proxying.

[!TIP] The admin token appears only once in the logs on first run. If you lose it, delete .data/admin-token and restart to generate a new one, or set a fixed token via the ADMIN_TOKEN env var.

Security: The Docker socket is disabled by default in docker-compose.yml (production). The compose.dev.yml override enables it for local development. Only use the dev override in trusted environments.

API Example

```bash

[<img src="docs/icons/settings.svg" width="20" height="20" style="vertical-align:middle;margin-right:6px;" alt=""> Real-Time Events & System Status](#-real-time-events--system-status)

A live SSE event bus delivers toast notifications for discovery outcomes, model disabling events, token counting errors, circuit breaker state transitions, and stale-request alerts straight to the dashboard. Failover retries during proxying are logged but not pushed as SSE events. The sidebar polls system stats every 10 seconds, showing CPU, memory, disk I/O, and network throughput with color-coded warnings (orange at 75%, red at 90%). When running under Docker Compose, stats are aggregated across containers; otherwise, cgroup metrics are used. Goroutine count, database health (size, connections, cache hit ratio), API uptime, and process count are also displayed.

ADMIN_TOKEN: openssl rand -hex 16 (optional; auto-generated if empty)

MASTER_KEY=<your-master-key> POSTGRES_PASSWORD=<your-postgres-password> ADMIN_TOKEN=

**2.** Create `docker-compose.yml`:


<details>
<summary>docker-compose.yml (click to expand, then copy)</summary>

</details>


**3.** Deploy:

Note: The docker-compose.yml content above is the production compose (auto-synced by a GitHub Action). For development, layer the compose.dev.yml override: docker compose -f docker-compose.yml -f compose.dev.yml up -d. If you want the prebuilt image instead of building from source, uncomment the image: line and comment out build: . in the compose file.

[<img src="docs/icons/providers.svg" width="20" height="20" style="vertical-align:middle;margin-right:6px;" alt=""> One Endpoint, Many Providers](#-one-endpoint-many-providers)

Add any OpenAI-compatible provider (Anthropic, DeepSeek, KoboldCPP, LMStudio, NanoGPT, OpenRouter, Z.AI, x.ai, Google AI Studio, Cohere, Ollama, Ollama Cloud, OpenCode Go, OpenCode Zen, OpenAI, or your own), and call them all through the same /v1/chat/completions endpoint. The proxy handles model ID mapping and failover transparently. Provider API keys are encrypted with AES-256-GCM at rest using your MASTER_KEY; only the proxy ever sees the decrypted credentials. Keyless providers (e.g. OpenCode Zen free models, local Ollama) are also supported (no API key required).

[<img src="docs/icons/api.svg" width="20" height="20" style="vertical-align:middle;margin-right:6px;" alt=""> Interactive Chat & Arena](#-interactive-chat--arena)

The dashboard includes a built-in Chat interface for testing models interactively, with support for system personas (presets or custom prompts), generation parameters (temperature, top_p, max_tokens, min_p, top_k, frequency/presence penalties), and streaming responses with collapsible thinking-block rendering. Vision-capable models show an image upload button: attach a photo for the model to describe or analyze. Audio-capable models show an audio upload button for sending audio input. Attachments are sent as OpenAI-compatible multimodal content parts (image_url, input_audio). Switch to Conversation mode to watch two models talk to each other: enter a starter prompt, set the number of rounds and optional delay between turns, and observe the back-and-forth with per-message metrics (duration, tokens, chars/sec).

Arena mode offers two sub-modes: Competition runs bracket tournaments where models face off in pairwise matchups. Vote for winners, and the bracket auto-advances to the next round until a champion emerges. Compare places two or more models in a grid with the same prompt for parallel evaluation, with per-slot personas and voting. Both modes support per-model generation parameters, streaming with thinking-block rendering, and per-response metrics. Past sessions are saved to an arena history modal for review and restoration.