bdibranding Help

Models & providers

Connect a model account, API key, or local endpoint.

Bring your own key (BYOK)

bdibranding talks to models through your credentials. The simplest path is an OpenRouter API key: one key, hundreds of models, transparent per-token pricing. Paste it once in Settings and every agent can use any model you allow.

Supported providers

The provider picker is a first-class roster, not one generic endpoint wearing different labels:

Release note: these docs track current source, which can run ahead of the build you are using.

Local models (Ollama, LM Studio)

A model on your own computer has a much smaller context window than a hosted one, so the station sends it a compact prompt with only the everyday tools; every other tool you granted is found with a tool search the moment the agent needs it. Background learning from your replies waits until the local model has been idle for a minute, then runs one pass at a time, so it stays out of the way while you are working. A message you send while a pass is running waits for that one pass to finish, and the reply says so.

A task request still needs a few thousand tokens, and a server whose context window is smaller cuts the start of the request, where the instructions and tools are. Ollama's default window is small on many setups. The station reads the window the server reports (or allows for Ollama's 4,096-token default when it reports none) and sizes the request to it: a small window gets five everyday tools and a shorter prompt. When even that does not fit, the station says so before the request goes out. To raise it:

Where keys live

Keys are stored locally in your OS keychain via the desktop shell — never in plain project files, never sent anywhere except the provider they belong to. Requests that carry your key or your prompts leave your machine only when an agent actually runs (or when you test a key). An agent's web searches and page reads also go out without asking: the search engine sees the query and the site sees the request. At startup the station fetches two public model and price lists, which carry nothing of yours. The privacy page lists every outside contact.

Service keys (SAVED API CONNECTIONS)

Beyond model providers, agents sometimes need platform keys to do real work — a Stripe test key, a GitHub token, a search API key. ABILITIES › SAVED API CONNECTIONS lets you paste any service key; bdibranding exposes it to agent runs as an environment variable and tells the agent only the name of what's available, never the value. The key itself never enters the model prompt.

3D models (Meshy)

Paste a Meshy API key in ABILITIES › SAVED API CONNECTIONS and any agent with a STUDIO in its room can build 3D models from a description or a picture. Each model is saved to the agent's workspace as a .glb file. Place a HOLO BAY on your station and click it to turn the models over, zoom in, and switch between solid, hologram and wireframe views. Every generation spends your Meshy credits: the run reports the exact credits Meshy charged, and scheduled or Night Shift runs can only use the key once you approve it for unattended use.

Cost honesty

Every run records what it actually cost, from the provider's own usage numbers. The ledger shows real spend per agent and per task — there is no abstraction layer marking up your tokens, and no meter that guesses.