buildwithnexusv0.12.2
Menu

Models & providers

Two wire protocols cover everything — pick a provider during setup or re-run bwn init. Environment variables override stored keys, so CI just works.

ProviderKindKey
Anthropic (Claude)remoteANTHROPIC_API_KEY
OpenAIremoteOPENAI_API_KEY
OpenRouterremoteOPENROUTER_API_KEY
GroqremoteGROQ_API_KEY
Hugging FaceremoteHF_TOKEN
Ollamalocal
llama.cpp serverlocal
LM Studiolocal

Local models

The native Ollama path probes each model's real context window and sets num_ctx so long prompts aren't silently truncated. Tool calls emitted as tagged text by small coder models (Qwen2.5-Coder, Gemma) are parsed reliably — a 1.5B model actually writes files.

Vision

Image and video attachments are gated per model: every current Claude model accepts images; OpenAI-compatible and Ollama models are detected by name (gpt-4o/o3/gemini, llava, qwen-vl, gemma3, llama3.2-vision, moondream, …). Text-only models get an explicit notice instead of silently dropped attachments. See Multimodal input.

Keys live in ~/.buildwithnexus/.env.keys (0600).