{"data":{"slug":"ddalcu-mlx-serve","name":"mlx-serve","tagline":"Native LLM inference server for Apple Silicon","github_url":"https://github.com/ddalcu/mlx-serve","owner":"ddalcu","repo":"mlx-serve","owner_avatar_url":"https://avatars.githubusercontent.com/u/869085?v=4","primary_language":"Zig","stars":1418,"forks":130,"topics":["agent","anthropic-api","apple-silicon","claude-code","deepseek-v4","diffusion","gguf","image-generation","inference","llm","local-llm","macos","macos-app","mlx","openai-api","tool-calling","video-generation","voice-agent","voice-cloning","zig"],"archived":false,"github_pushed_at":"2026-09-19T22:08:35+00:00","maintenance_label":"Very active","stars_delta_30d":1135,"url":"https://www.graphcanon.com/tools/ddalcu-mlx-serve","markdown_url":"https://www.graphcanon.com/tools/ddalcu-mlx-serve.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ddalcu-mlx-serve","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ddalcu-mlx-serve","description":"Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.","homepage_url":"http://mlxserve.com/","license":"MIT","open_issues":54,"watchers":9,"ai_summary":"Offers an OpenAI and Anthropic API-compatible inference server built in Zig for macOS devices with Apple Silicon chips, featuring an MLX Core app for chat and agent functionalities","readme_excerpt":"### Install via Homebrew\n\n```bash\nbrew tap ddalcu/mlx-serve https://github.com/ddalcu/mlx-serve\nbrew install --cask mlx-core   # the app (recommended)\nbrew install mlx-serve         # CLI + server only, no GUI\n```\n\n---\n\n## License\n\nMIT, see [LICENSE](LICENSE).\n\nmlx-serve bundles third-party code that stays under its own license, including some Apache-2.0 Metal kernels and the Jinja engine that renders chat templates. [NOTICE](NOTICE) lists all of it with the required attributions, and [LICENSE-APACHE-2.0](LICENSE-APACHE-2.0) is the Apache License text.\n\n---\n\n★ **Found this useful? [Star the repo](https://github.com/ddalcu/mlx-serve/), [subscribe on YouTube](https://www.youtube.com/@DavidDalcu), [follow on X](https://x.com/ddalcu). It really does help others discover it.**","github_created_at":"2026-02-17T01:55:20+00:00","created_at":"2026-07-15T11:00:11.092644+00:00","updated_at":"2026-09-20T05:04:28.023835+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"anthropic-api","name":"anthropic-api"},{"slug":"apple-silicon","name":"apple-silicon"},{"slug":"deepseek-v4","name":"deepseek-v4"},{"slug":"gguf","name":"gguf"},{"slug":"image-generation","name":"image-generation"},{"slug":"local-llm","name":"local-llm"},{"slug":"macos","name":"macos"}],"trust":{"provenance":{"is_fork":false,"github_id":1159656889,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:04:25.975Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-18T17:44:01Z","stars_delta_30d":1135,"open_issues_delta_30d":51},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:00:12.268Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:04:26.995Z"},"languages":{"value":["zig"],"source":"github.language","observed_at":"2026-09-20T05:04:26.995Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T05:04:26.995Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Apple Silicon-powered macOS devices to ensure optimal performance and compatibility."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["Use when your project requires running large language model (LLM) inferencing natively on Apple Silicon hardware.","Prefer this tool if your development environment is restricted to macOS systems and you aim for high performance.","Ideal for scenarios where an OpenAI or Anthropic API-compatible experience without Python dependency is desired."],"when_not_to_use":["Avoid if your infrastructure does not include devices with Apple Silicon chips, as it is specifically optimized for this architecture.","Do not use if you require cross-platform compatibility as mlx-serve targets macOS exclusively.","This tool might not be suitable if Python integration is crucial in your project."],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:25:26.233Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Apple Silicon-powered macOS devices to ensure optimal performance and compatibility."},{"label":"Adopt for","value":"Focused on supporting Apple Silicon-powered macOS devices, mlx-serve provides a native and API-compatible inference service without requiring Python."}]}}