mere.run Docs

Appearance

mere.runLocal inference from one machine to a portable fleet

A public Swift package and CLI for multimodal inference, persistent worlds, typed workflow graphs, local APIs, an optional macOS studio, and headless Linux executors.

Get Started
CLI Reference
Portable Workflows
Linux QuickStart
docs.mere.rundocs online
Multimodal inference, portable graphs, and persistent local runtimes.mere.run
mere.run CLIComplete command tree, setup paths, and practical cookbooksCommandsCookbooksSetupPortable workflowsImmutable bundles across local, SSH, and relay executorsGraphsExecutorsRunsRuntime familiesImage, text, audio, vision, video, 3D, and persistent worldsMultimodalResidentLocalCompanion pluginsVerified external tools and typed graph providersCatalogDoctorProviders

Multimodal by design

Run image, text, speech, vision, 3D, music, sound-effect, video, and persistent-world workloads from one typed CLI.

Portable workflow graphs

Validate once, materialize immutable job bundles, and run the same graph locally, over SSH, or through a relay executor.

Live and resident runtimes

Stream microphone transcription, keep text and video models warm, and preserve causal world state across requests.

Managed models and adapters

Inspect machine capabilities, pull pinned model snapshots and verified LoRAs, configure runtimes, and run deterministic quality gates.

Local APIs and companions

Serve OpenAI-compatible chat, embeddings, images, speech, and transcription; connect Open WebUI or install official companion plugins.

Mac-first, headless when needed

Use the native macOS studio on Apple Silicon or install CLI-only Linux packages for compatible CPU and CUDA hosts.

Current public command surface ​

This inventory is generated from the CLI configuration. Each command links to the page that owns its public documentation.

CommandPurpose
mere.run guideRead offline mere.run command cookbooks.
mere.run imageGenerate and validate image models.
mere.run textRun local chat, code, embedding, and anonymization workflows.
mere.run speechSynthesize, transcribe, and manage voice profiles.
mere.run visionCaption, inspect, face-analyze, segment, track, pose, depth, geometry, optical flow, and OCR visual media.
mere.run musicGenerate music locally.
mere.run sfxGenerate sound effects locally.
mere.run videoGenerate and understand video with native Swift/MLX pipelines.
mere.run worldRun persistent local conditioned-video world sessions.
mere.run graphValidate, materialize, run, and submit portable workflow graphs.
mere.run executorManage local, SSH, and relay workflow executors.
mere.run runInspect durable mere.run workflow reports and run directories.
mere.run modelList, pull, remove, inspect, and clean up models.
mere.run adapterList and pull verified LoRA adapters.
mere.run statusShow local server, loaded model, and installed model status.
mere.run gateRun the end-to-end quality gate against installed models.
mere.run configGet and set persisted mere.run configuration (e.g. Hugging Face token).
mere.run apiServe local models through API surfaces.
mere.run open-webuiStart the optional Open WebUI companion against a local mere.run API.
mere.run pluginDiscover and install official mere.run companion plugins.
mere.run setupChoose a guided, BYOA, or manual mere.run setup path.
mere.run agentInstall and start the optional guided local setup agent.

Choose a path ​

Install and run locally ​

Automate and operate ​

Explore runtime families ​

Contribute to the repo ​

Released under the MIT License.

Copyright © 2026 Sawfwair Inc. and mere.run contributors