{"slug": "llama-dash-local-llm-ops", "title": "llama-dash - Local LLM Ops", "summary": "A developer built llama-dash, a dashboard and logging proxy for self-hosted local LLM inference stacks. It proxies OpenAI/Anthropic-compatible endpoints, logs requests with token counts and cost estimates, and adds API key management, rate limits, model allow-lists, and UI-based model control. The tool ships as a Docker Compose stack and can be used with tools like Claude Code.", "body_md": "I've been building llama-dash, a single-pane dashboard and logging proxy for a self-hosted local inference stack.\n\nI run llama-swap + llama.cpp on a box at home and got tired of having zero visibility — no request log, no idea which model was loaded when, no way to hand out scoped access without exposing the raw backend.\n\nSo llama-dash sits in front as one public port: it proxies the OpenAI/Anthropic-compatible /v1/* endpoints unchanged (streaming SSE passes straight through), logs every request with token counts and cost estimates, and adds the stuff llama-swap doesn't have — hashed API keys, per-key rate limits and model allow-lists, routing rules, and model load/unload from the UI.\n\nThe bit I like most is that you can point Claude Code at it via ANTHROPIC_BASE_URL and watch your own usage flow through. It ships as a Docker Compose stack with the backend hidden internally.", "url": "https://wpnews.pro/news/llama-dash-local-llm-ops", "canonical_source": "https://dev.to/ndom91/llama-dash-local-llm-ops-901", "published_at": "2026-06-19 09:02:23+00:00", "updated_at": "2026-06-19 09:06:51.872361+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools", "ai-infrastructure", "mlops"], "entities": ["llama-dash", "llama-swap", "llama.cpp", "OpenAI", "Anthropic", "Claude Code", "Docker Compose"], "alternates": {"html": "https://wpnews.pro/news/llama-dash-local-llm-ops", "markdown": "https://wpnews.pro/news/llama-dash-local-llm-ops.md", "text": "https://wpnews.pro/news/llama-dash-local-llm-ops.txt", "jsonld": "https://wpnews.pro/news/llama-dash-local-llm-ops.jsonld"}}