RunanywhereAI

Set up and use RunAnywhere Wally from the terminal — install wally, sign in, pick a coding harness, run a model, check spend. Use when the user wants to get started with RunAnywhere or Wally, run a harness like opencode against a hosted or on-device model, or…

Verify a built wally binary against a pinned C++ desktop kit on macOS and Windows. Use when CI smoke/e2e is red, backends are missing, DLLs fail to load, or the Apple MLX host fails to link.

Cut an Wally product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles. Use when shipping wally after a published SDK kit, or when Homebrew / notarization / private overlays must not leak into public bottles.

Where Wally logic belongs — command layering, proto as SOT, kit vs CLI ownership, Apple MLX host vs wally-cxx. Use when adding a command, moving inference logic, or deciding whether a bug is SDK or CLI.

Run wally's LLM e2e on Apple Neural Engine (NeuRT) and Snapdragon Hexagon NPU (QHexRT) devices. Use when adding overlay backends, proving LLM inference on device, or when a PC only has one backend's bundles on disk. Non-LLM modalities…

Bump cmake/sdk-pin.cmake to a new published SDK C++ desktop kit (version + SHA-256 + IDL lock). Use after an SDK GitHub Release is published (not draft), when fetch-kit.sh 404s, or when SCHEMA_LOCK mismatches.

Set up and use RunAnywhere from the terminal — install rcli, sign in, pick a coding harness, run a model, check spend. Use when the user wants to get started with RunAnywhere, run a harness like opencode against a hosted or on-device model, or asks what their…

Verify a built rcli binary against a pinned C++ desktop kit on macOS and Windows. Use when CI smoke/e2e is red, backends are missing, DLLs fail to load, or the Apple MLX host fails to link.

Run engine-agnostic rcli modality e2e on Apple Neural Engine (NeuRT) and Snapdragon Hexagon NPU (QHexRT) devices. Use when adding overlay backends, proving LLM/STT/TTS/VLM/embed/diffusion on device, or when a PC only has one modality's bundles on disk.

Where RCLI logic belongs — command layering, proto as SOT, kit vs CLI ownership, Apple MLX host vs rcli-cxx. Use when adding a command, moving inference logic, or deciding whether a bug is SDK or CLI.

Bump cmake/sdk-pin.cmake to a new published SDK C++ desktop kit (version + SHA-256 + IDL lock). Use after an SDK GitHub Release is published (not draft), when fetch-kit.sh 404s, or when SCHEMA_LOCK mismatches.

Cut an RCLI product release (independent of SDK version) — version bump, release:patch label, merge, auto-tag, bottles. Use when shipping rcli after a published SDK kit, or when Homebrew / notarization / private overlays must not leak into public bottles.

Step-by-step recipe for adding a new engine plugin under runanywhere-sdks/engines/, or adding a modality (e.g. TTS) to an existing engine (llamacpp, sherpa, onnx, cloud, mlx, neurt, qhexrt). Use when the task is "add engine X", "wire up backend Y", or "make…

Manually publish an already-tagged, already-released (non-draft GitHub Release) RunAnywhere SDK version to every package registry (npm, Maven Central, pub.dev, Swift SPM dist repo) plus macOS rcli notarization, with heavy verification that nothing…

Cut a new RunAnywhere SDK release end-to-end in RunanywhereAI/runanywhere-sdks — version bump through a fully green, tagged, drafted-then-published GitHub Release. Stops BEFORE publishing to package registries (npm/Maven/pub.dev/SwiftPM dist) — that is the…

Run a REAL end-to-end inference smoke test (model download + load + generate, with visible output) on every RunAnywhere starter app — iOS, macOS/Swift, Android, Web, Electron — after a runanywhere-sdks release. Build success alone is never sufficient evidence.

Prove that what an SDK binding EMITS on the telemetry wire is correct and that it actually arrives — vocabulary compliance, presence/absence semantics, device-id stability, and a received request body / stored row as evidence. Use when touching…

Integrate RunAnywhere on-device AI (LLMs, STT, TTS, voice agents, VLM) into applications. Use when implementing offline AI features, local LLM inference, on-device speech processing, privacy-first AI, vision language models, or when mentions of…