Skip to content

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).

Document the hosted-gateway use of the LOCAL_* provider settings

Claude852ba665babe
diff --git a/.env.example b/.env.example
index c446a86c..068ac926 100644
--- a/.env.example
+++ b/.env.example
@@ -65,6 +65,9 @@ OPENROUTER_API_KEY=
# Route selected model slugs to a local OpenAI-compatible server (Ollama,
# LM Studio, vLLM, llama.cpp, …) instead of the Anthropic API. Off by default;
# a fresh checkout behaves identically to before.
+# Also works with HOSTED OpenAI-compatible gateways: point LOCAL_BASE_URL at
+# the gateway's /v1 endpoint, set LOCAL_API_KEY, and list its model slugs in
+# LOCAL_MODELS. See README → "Using a hosted OpenAI-compatible gateway".
LOCAL_MODELS_ENABLED=false
# Base URL of the local server, INCLUDING the version path. Required when
# LOCAL_MODELS_ENABLED=true.
diff --git a/README.md b/README.md
index 32bb020c..b7d6a1e9 100644
--- a/README.md
+++ b/README.md
@@ -353,6 +353,31 @@ pick a model that's strong at it (e.g. Llama 3.3 70B, Qwen2.5) — small models
may route poorly. `LOCAL_API_KEY` is only needed if your server (vLLM, or a
gateway) requires a bearer token; Ollama and LM Studio need none.
+### Using a hosted OpenAI-compatible gateway
+
+The `LOCAL_*` settings are not limited to localhost — the same recipe works with
+any **hosted** OpenAI-compatible endpoint (an aggregator or inference gateway):
+
+```bash
+LOCAL_MODELS_ENABLED=true
+LOCAL_BASE_URL=https://gateway.example.com/v1
+LOCAL_API_KEY=your-gateway-key
+LOCAL_MODELS=vendor/model-a,vendor/model-b
+```
+
+The listed slugs are sent to the gateway verbatim and appear in the Council UI
+dropdown, exactly like local slugs. Gateways that speak OpenRouter's request
+format and model namespace can alternatively be used through the OpenRouter
+path (`OPENROUTER_ENABLED=true` + `OPENROUTER_API_KEY` +
+`OPENROUTER_BASE_URL=https://gateway.example.com/v1`), which keeps that path's
+Claude-name translation and feature handling.
+
+The local-model caveats above apply to the `LOCAL_*` path unchanged, plus one
+that matters more for hosted endpoints: everything the Executive processes —
+company profile, documents, conversations — is sent to whichever endpoint you
+configure here. Point these settings only at a provider you trust with that
+data.
+
## Adding a New Specialist Agent
1. Create `packages/core/openexecutive/agents/your_agent.py` extending `BaseAgent`