4 phút đọc
RunanywhereAI/RCLI: Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG – Repository RunanywhereAI/RCLI. Mô tả: Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG. 1542 stars, 85 forks, ngôn ngữ chính C++, cập nhật 2026-09-02.
1. Repository làm gì?
Run open models on your machine.
Chat, vision, speech, and embeddings — all local. Nothing leaves the device.
Models you have pulled run on this machine and need no account. To use a hosted model instead, sign in to a RunAnywhere console:
The terminal never asks for a password. It shows a code, you approve it in the browser, and it collects an API key with your credit behind it. That key appears on the console's Cloud keys page and can be revoked there at any time.
Against a console running on your own machine:
Then hand a hosted model to a coding session:
2. Dữ liệu và cấu trúc đáng chú ý
For the Open Frontier hosted path, make the choice explicit and pass any OpenCode arguments after –:
–cloud never falls back to a local model. The existing rcli opencode -m form remains available for the parent PR's local-or-upstream harness flow.
If the model is on this machine, rcli serves it locally. If it is not, the request goes to the console you are signed in to, is checked against your balance before it runs, and is metered.
Needs a built SDK kit, not SDK source:
build/rcli is the full binary. build/rcli-cxx is the same CLI without MLX, and is what you get if RCLI_SDK_SWIFT_PATH is unset.
MLX loads its Metal shaders from mlx-swift_Cmlx.bundle next to the executable, so install the pair together:
Copy the binary on its own and MLX will not register.
3. Khả năng ứng dụng và giới hạn
No Linux release asset is currently published. Use the source build below; install.sh intentionally fails instead of claiming that an unavailable bottle was installed.
rcli models list –all is the full catalog. Short names work everywhere (qwen3, llama3.2, whisper-tiny, piper, …). Any Hugging Face GGUF works too:
One rcli binary. Catalog models already name their engine (GGUF → llama.cpp, mlx-* → MLX, Core ML → NeuRT, QNN-context → QHexRT). You normally do not pick one.
Override only when you mean it:
–engine accepts mlx, llamacpp, sherpa, onnx, neurt / coreml / ane, and qhexrt / qnn / npu / hexagon. If you omit it, commons picks the highest-priority registered backend that implements that primitive:
rcli backends is the source of truth for this binary. Public bottles never list neurt or qhexrt. Those engines are private overlays, never Homebrew / GitHub Release assets.
Public Windows ARM64 kits are commons-only (no llama.cpp / ONNX / Sherpa on MSVC ARM64). Snapdragon NPU is overlay-only. x64 Windows has no Hexagon path.
Yes = this engine implements the primitive. Try = a catalog id that rcli pull / a local path can run. Overlay engines still need the matching on-disk bundle (compiled .mlmodelc tree, or *_HNPU / v81/ QNN-context dir) — a Hugging Face repo page is HTML, not a model.
MLX registers with a one-line -811 then Swift callbacks install it — that warning is expected. image generate is compiled only when NeuRT is linked; –prompt and –out are required (not a positional prompt). –steps 4 is enough for a smoke PNG.
Số liệu repository có thể thay đổi; nên mở liên kết nguồn để kiểm tra README, giấy phép và trạng thái phát hành.
Nguồn tham khảo: Xem bài gốc
