{"id":"osaurus","name":"Osaurus","homepage":"https://github.com/osaurus-ai/osaurus","repo_url":"https://github.com/osaurus-ai/osaurus","category":"ai-infrastructure","subcategories":["local-ai","mcp-server","ai-runtime","macos"],"tags":["macos","apple-silicon","mlx","local-inference","mcp","openai-compatible","anthropic-compatible","edge-ai","agents"],"what_it_does":"Osaurus is an always-on AI edge runtime for macOS that runs local models via MLX on Apple Silicon or routes to cloud providers (Anthropic, OpenAI, xAI, Ollama), exposing both OpenAI-compatible and Anthropic-compatible APIs alongside a built-in MCP server for agent tool access.","use_cases":["Running local LLM inference on Apple Silicon without cloud costs using MLX-optimized models","Providing a unified API endpoint that proxies to local or cloud models interchangeably","Building custom AI agents with persistent memory, voice input, and file-monitoring triggers","Using MCP tools from a local always-on server across multiple AI applications"],"not_for":["Non-macOS or non-Apple Silicon machines","Teams needing centralized multi-user AI infrastructure","Production server deployments (designed as a personal workstation runtime)"],"best_when":"A macOS developer wants a local-first AI runtime that works with both local models and cloud APIs through a single OpenAI/Anthropic-compatible interface, with MCP tools always available.","avoid_when":"Running on Linux/Windows, or when centralized cloud AI infrastructure is preferred over local edge compute.","alternatives":["ollama","lm-studio","jan-ai","msty"],"af_score":71.8,"security_score":78.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:06.042209+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}