[drvt69talati]

Description

Adds a provider page for llamay, a local LLM runtime for macOS, Windows and Linux, under Model providers → More, next to llama.cpp and Llama Stack.

No code change: llamay serves Ollama's API on localhost:11435, so Continue's existing ollama provider works with apiBase: http://localhost:11435. The page covers chat/edit/apply/autocomplete with one model, and embeddings via llamay serve -embed.

Checklist

• I've read the contributing guide
• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created (docs only)

Tests

Docs only; docs/docs.json still parses. The configuration was checked by replaying the requests core/llm/llms/Ollama.ts sends (/api/show with name, /api/chat streaming with think, tools, num_ctx and keep_alive, /api/generate raw and with suffix) against llamay 0.4.15 and Ollama 0.40.11 on the same models; the responses match. Embeddings return 404 "no encoder loaded" unless -embed is given, which is why the page shows it.

🤖 Generated with Claude Code

[github-actions]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[drvt69talati]

I have read the CLA Document and I hereby sign the CLA

[drvt69talati]

recheck

[drvt69talati]

recheck