ARCANADA
← Autonomy / Model Connector
LIVE L1 · target L3

Model Connector

Unified API for AI CLI agents and cloud model providers.

A single OpenAI-compatible endpoint that bridges Cursor, Claude Code, Gemini CLI, Codex, and OpenRouter. NestJS + Fastify on port 3900, LIVE on connector.arcanada.ai. Public repo under MIT. An internal benchmark documented the hard tradeoff: CLI connectors lack json_schema and concurrency, so they cannot replace OpenAI API for frameworks like Graphiti, Cognee, or LangChain agents — use OpenRouter or direct API for structured-output workloads.

Capabilities

  • OpenAI-compatible /chat/completions endpoint (HTTP 201 on /execute)
  • Connectors: Claude CLI, Cursor, Gemini, Codex, OpenRouter
  • Per-tenant rate limits and quotas
  • Token accounting per request and per tenant
  • Public MIT-licensed repo (Arcanada-one/model-connector)
  • 104 tests covering all four CLI connectors
  • Documented capability matrix (json_schema / concurrency support per connector)

Current autonomy level

L1
What levels mean →

Weakest link

CLI connectors are inherently brittle — agents may exit 0 on logical error, structured output is not supported, concurrency is 1-at-a-time. No automatic fallback chain between providers; if Claude CLI hangs, the request hangs.

Roadmap to L3

  1. L3 lift — connector self-test on startup, schema-validated outputs via Zod, structured failure classification per connector.
  2. L4 lift — provider fallback chain (Claude → OpenRouter → OpenAI) with circuit breaker per connector; hard cost CB per tenant.
  3. L5 candidate — automatic provider routing based on task complexity, budget, and structured-output requirement.

Links