Smart AI Bridge

Smart AI Bridge v2.4.0

Config-driven multi-AI orchestration for Claude Code. Add any OpenAI-compatible provider, route intelligently, and let multiple AIs collaborate through the council system.

What It Does

Smart AI Bridge is an MCP server that sits between Claude Code and your AI backends. It provides 19 tools for token-saving file operations, multi-AI workflows, code quality checks, and intelligent routing -- all configured through a single JSON file.

• Any OpenAI-compatible provider works. Local models (vLLM, LM Studio, Ollama), cloud APIs, or a mix of both. The included presets cover common providers, but adding your own is just a config entry.
• Smart routing selects the best backend per task using a 4-tier system: forced selection, learned preferences, rule-based heuristics, and health-based fallback.
• Council system queries multiple backends on the same prompt and returns all responses for Claude to synthesize. Configurable strategies (parallel, sequential, debate, fallback) per topic.
• Web dashboard for managing backends and council configuration without editing JSON files.

Quick Start

1. Install

cd /path/to/smart-ai-bridge
npm install

2. Configure Backends

Backend configuration lives in src/config/backends.json. Set API keys for the providers you want to use:

# Examples -- set whichever keys apply to your backends
export NVIDIA_API_KEY="your-key"
export OPENAI_API_KEY="your-key"
export GEMINI_API_KEY="your-key"
export GROQ_API_KEY="your-key"

You only need at least one working backend (a local model or one cloud API key). See CONFIGURATION.md for the full config reference.

3. Add to Claude Code

{
  "mcpServers": {
    "smart-ai-bridge": {
      "command": "node",
      "args": ["src/server.js"],
      "cwd": "/path/to/smart-ai-bridge",
      "env": {
        "NVIDIA_API_KEY": "your-key",
        "OPENAI_API_KEY": "your-key",
        "GEMINI_API_KEY": "your-key",
        "GROQ_API_KEY": "your-key"
      }
    }
  }
}

4. Restart Claude Code

After restarting, all 19 tools will be available. Verify with:

@check_backend_health({ "backend": "local" })

Tools (19)

Token-Saving File Operations

Multi-AI Workflows

Code Quality

Infrastructure

Smart Routing

The router selects backends using a 4-tier priority system:

1. Forced -- explicit backend selection (model="my_backend")
2. Learning -- learned preferences from past outcomes (>0.7 confidence)
3. Rules -- complexity and task-type heuristics
4. Fallback -- health-based fallback through the priority chain

When a backend fails, requests automatically fall to the next healthy backend. Circuit breakers protect each backend (5 consecutive failures trigger a 30-second cooldown).

Response Reliability (v2.4.0)

All handlers use a unified response pipeline (extractResponseText) that correctly handles every known LLM response shape -- raw strings, OpenAI chat/completion formats, thinking model reasoning_content, array content parts, and Gemini candidates. Repetitive output from local models is automatically collapsed, and analysis findings are deduplicated and capped.

Council System

The council queries multiple backends on the same prompt and returns all responses for Claude to synthesize. Topics like coding, architecture, and security each map to a set of backends and a strategy (parallel, sequential, debate, or fallback).

See docs/COUNCIL.md for full documentation.

Dashboard

An optional web dashboard provides UI for backend management (enable/disable, priorities, health checks) and council configuration (strategies, topic mapping).

See docs/DASHBOARD.md for setup and API reference.

Adding a Backend

Via Dashboard (recommended): Start the server with SAB_DASHBOARD=true, then use the web UI at http://localhost:3000 to add, remove, enable/disable, and re-prioritize backends without editing JSON.

Via Config File: Any OpenAI-compatible provider can be added as a config entry in src/config/backends.json:

{
  "name": "my_provider",
  "type": "openai",
  "endpoint": "https://api.my-provider.com/v1",
  "model": "my-model",
  "apiKeyEnvVar": "MY_PROVIDER_API_KEY",
  "maxTokens": 8192,
  "priority": 7,
  "enabled": true
}

See EXTENDING.md for details on adding custom adapter types.

Documentation

Requirements

• Node.js >= 18.0.0
• At least one backend configured (local model or cloud API key)
• Claude Code or Claude Desktop for MCP integration

Testing

npm test              # Run 35 unit tests (Vitest)
npm run test:watch    # Watch mode
npm run test:bench    # Performance benchmarks (25 benchmarks, 6 categories)

Security Notes

• Never commit API keys to version control. Use environment variables exclusively.
• The Claude Code config examples above use placeholder values -- replace them with your actual keys or reference a .env file.
• Rotate any accidentally leaked keys immediately.

License

Apache-2.0