spb/tools-spboucher-ai

1{2  "slug": "exo",3  "name": "exo",4  "aliases": ["exo-explore", "exo labs"],5  "vendor": { "name": "Exo Labs", "slug": "exo-labs", "website": "https://exolabs.net/" },6  "homepage_url": "https://github.com/exo-explore/exo",7  "docs_url": "https://github.com/exo-explore/exo",8  "repo_url": "https://github.com/exo-explore/exo",9  "license_url": "https://github.com/exo-explore/exo/blob/main/LICENSE",10  "product_type": "application",11  "product_status": "active",12  "summary": "Open-source software that pools several Apple Silicon Macs (and Linux hosts) into one local inference cluster, sharding large models across devices with MLX",13  "description": "exo is an open-source project from Exo Labs (Apache 2.0) that connects multiple everyday devices into a single cluster for running large language models locally. Devices on the same network, or linked by Thunderbolt cables, discover each other automatically; exo builds a live view of the topology, including memory, link latency and bandwidth, and splits a model across nodes so that models too large for any one machine can still run. It supports tensor parallelism across devices and, on recent macOS versions, RDMA over Thunderbolt 5 to cut inter-node latency.\n\nThe inference backend is MLX with MLX distributed for communication, so Apple Silicon Macs are the primary target; Linux hosts currently run on CPU, with GPU support described as in development. A macOS app and a web dashboard manage the cluster and offer a chat interface, models load from the Hugging Face Hub, and the server exposes OpenAI Chat Completions, OpenAI Responses, Claude Messages and Ollama-compatible endpoints so existing clients work unchanged. Published examples run very large open-weight models across four Mac Studios.\n\nexo is under rapid development: the repository is active daily, all nodes must run the same version, and APIs and installation steps change often. It is well suited to experimenters with several Macs who want to run models beyond a single machine's memory, less so to teams needing a stable, supported serving stack.",14  "capabilities": ["Automatic device discovery over LAN or Thunderbolt", "Topology-aware model sharding and tensor parallelism", "MLX inference backend with MLX distributed communication", "OpenAI-, Claude- and Ollama-compatible API endpoints", "Web dashboard and macOS app for cluster management", "Model loading from the Hugging Face Hub"],15  "workflows": ["Run a model larger than one Mac's memory across several Macs", "Point an OpenAI-compatible client at a home cluster", "Benchmark Thunderbolt versus Ethernet interconnects"],16  "advantages": ["Uses hardware already owned instead of a GPU server", "Open source with a permissive license", "Drop-in API compatibility with common clients"],17  "limitations": ["Apple Silicon-centric; Linux is CPU-only for now", "Fast-moving project with frequent breaking changes", "All nodes must run identical versions", "No long-term support or stability guarantees"],18  "prerequisites": ["Two or more Apple Silicon Macs on one network (macOS 15.1 or later for the app)", "Fast interconnect for good performance"],19  "audiences": ["Experimenters with several Macs", "Researchers exploring distributed local inference"],20  "alternatives": ["mlx-lm", "ollama", "vllm", "llama-cpp"],21  "categories": [{ "slug": "distributed-computing", "primary": true }, { "slug": "apple-silicon-ml" }, { "slug": "local-inference" }],22  "tags": ["apple-silicon", "llm", "distributed-inference", "open-source", "macos", "python"],23  "use_cases": ["run-local-models", "serve-models", "distribute-computation"],24  "operating_systems": ["macos", "linux"],25  "execution_modes": ["local", "self-hosted"],26  "interfaces": ["desktop", "web", "api", "cli"],27  "deployment_models": ["on-premises"],28  "integrations": ["MLX", "Hugging Face Hub", "OpenAI-compatible clients", "Ollama-compatible clients"],29  "data_formats": ["safetensors / MLX weights"],30  "languages": ["Python", "Swift"],31  "source_model": "open-source",32  "license_spdx": "Apache-2.0",33  "pricing_model": ["open-source", "free"],34  "self_hostable": true,35  "sources": [36    { "url": "https://github.com/exo-explore/exo", "type": "official_site", "title": "exo-explore/exo README", "supports": ["name", "summary", "capabilities", "limitations", "prerequisites"], "checked_at": "2026-11-02" },37    { "url": "https://exolabs.net/", "type": "official_site", "title": "Exo Labs", "supports": ["vendor", "description"], "checked_at": "2026-11-02" },38    { "url": "https://github.com/exo-explore/exo/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }39  ],40  "confidence": "medium",41  "uncertainty_note": "The project is pre-1.0 in its source tree and changes quickly; capabilities described reflect the README on 2026-11-02 and may shift. Exo Labs also lists a business offering but publishes no pricing.",42  "discovery_method": "editorial-research",43  "depth": "standard",44  "editorial_status": "reviewed",45  "visibility": "public",46  "featured": false,47  "author": "batch-C"48}49