HomeSolutions › AI / ML workstation & cluster

AI / ML workstation & cluster

Local LLMs, agent platforms, GPU infra and the data pipeline around them.

The AI / ML preset reveals local LLM runtimes (Ollama, vLLM, LM Studio), agent platforms (OpenClaw, Hermes, DeerFlow, LangGraph, CrewAI), vector databases, GPU infrastructure and ML-workbench tools — monitored together, with the guarded AI Administrator on top and your secrets kept local.

Services we install or monitor for this

157 services across 13 categories that FrontierStack can install, connect and monitor for this use-case — revealed together when you pick this preset in the app.

Browse by category (13)
AI / LLMs24
  • AnythingLLMAll-in-one self-hosted RAG chat app
  • CerebrasVery fast hosted inference on wafer-scale hardware
  • ChatLLM TeamsAbacus.AI's multi-model team chat & agent workspace (cloud)
  • CrewAI (open source)Multi-agent crews — Python framework + CLI (local)
  • DyadLocal open-source AI app builder (desktop)
  • Hugging FaceModel hub, Inference API & local tooling
  • IBM watsonx.aiIBM's enterprise AI platform — Granite + third-party models (cloud/on-prem)
  • JanPrivate, offline AI desktop app (OpenAI-compatible)
  • LibreChatSelf-hosted multi-provider AI chat UI
  • LiteLLMProxy/gateway for 100+ LLM APIs (OpenAI-compatible)
  • llama.cpp ServerLightweight local LLM server (OpenAI-compatible)
  • LocalAISelf-hosted, OpenAI-compatible inference server
  • Mem0Memory layer for AI agents — self-hosted (Docker) or cloud
  • MLXApple-silicon model serving via MLX — CLI server or the oMLX menu-bar app
  • MLX (Apple)Apple's ML framework for Apple Silicon
  • Mojo (Modular MAX)Modular's AI language + MAX inference server (OpenAI-compatible)
  • NotebookLMGoogle's source-grounded research notebook (cloud)
  • Open ComputerVirtual OS for AI agents — QEMU VM per agent (Mintplex Labs)
  • Open NotebookOpen-source, self-hosted NotebookLM alternative
  • OpenCodeOpen-source AI coding agent (terminal)
  • PrivateGPTAsk questions of your documents, 100% offline (RAG)
  • Tetrate Agent RouterHosted LLM router — one OpenAI-compatible API (cloud)
  • TurboFieldfareGemma 4 26B-A4B on Apple Silicon in ~2 GB of RAM
  • vLLMHigh-throughput LLM inference server (OpenAI-compatible)
Knowledge & Memory22
  • AFFiNEDocs + whiteboard + database (Notion/Miro alt.)
  • AppFlowyOpen-source Notion alternative (docs/boards/DBs)
  • BookStackSelf-hosted docs/wiki organised as books (PHP)
  • DocmostOpen-source collaborative wiki & docs (Confluence/Notion alt.)
  • DokuWikiFlat-file PHP wiki — the closest macOS Server “Wiki” replacement
  • GraphifyTurn a codebase into a queryable knowledge graph (AI coding-assistant skill)
  • GraphRAGGraph-based retrieval-augmented generation (Microsoft)
  • Joplin ServerSync server for Joplin notes (E2EE)
  • KarakeepAI bookmark/read-it-later (formerly Hoarder)
  • LinkdingMinimal, fast self-hosted bookmark manager
  • LogseqLocal-first outliner & PKM (Markdown/Org)
  • MediaWikiThe wiki engine behind Wikipedia (PHP/MySQL)
  • MemosLightweight, privacy-first notes/memo hub
  • NotionAll-in-one workspace — docs, wikis, databases (cloud)
  • OutlineSelf-hosted team knowledge base (real-time)
  • ReadwiseHighlights sync & read-later (cloud API)
  • ShioriSimple self-hosted bookmark manager (Go)
  • SurfSenseSelf-hosted NotebookLM/Perplexity alternative
  • Trilium NotesHierarchical personal notes (self-hosted server + app)
  • WallabagSelf-hosted read-it-later (Pocket alternative)
  • Wiki.jsModern self-hosted wiki (Node.js)
  • ZoteroReference & research manager (app + API)
AI Governance & Safety16
  • Arize PhoenixOpen-source LLM tracing & evaluation (self-hosted)
  • Credo AIAI governance, risk & compliance platform (cloud)
  • Fiddler AIAI observability & model monitoring with explainability (cloud)
  • garakLLM vulnerability scanner / red-teaming (self-hosted CLI)
  • Guardrails AIInput/output validation guardrails for LLMs (Python)
  • HeliconeLLM observability & gateway — logs, costs, caching (self-hosted / cloud)
  • Holistic AIAI governance, risk & audit platform (cloud + OSS)
  • Lakera GuardReal-time GenAI security — prompt-injection firewall (cloud / self-host)
  • LangfuseOpen-source LLM observability & tracing (self-hosted / cloud)
  • NeMo GuardrailsProgrammable guardrails for LLM conversations (NVIDIA, Python)
  • OpenLLMetryOpenTelemetry instrumentation for LLM apps (SDK)
  • PromptfooPrompt/RAG testing, evals & LLM red-teaming (self-hosted CLI)
  • Protect AIAI/ML security — model scanning & ML supply chain (cloud + OSS)
  • RagasEvaluation framework for RAG pipelines (Python)
  • TruLensEvaluation & tracking for LLM apps — feedback functions (Python)
  • WhyLabsAI observability & data/LLM monitoring (cloud + whylogs)
Databases16
  • Apache CassandraDistributed wide-column database
  • Apache CouchDBDocument database with HTTP API and sync
  • CockroachDBDistributed SQL database
  • Couchbase ServerDistributed document, key-value and search database
  • FirebaseGoogle's backend-as-a-service — Firestore, Auth, Storage, Functions (cloud)
  • Microsoft SQL ServerMicrosoft relational database for Windows and Linux
  • MongoDBDocument (NoSQL) database
  • Neo4jGraph database with Cypher query language
  • NeonServerless Postgres — autoscaling & branching (cloud API)
  • Oracle DatabaseEnterprise relational database
  • PatroniHA PostgreSQL — automatic failover
  • PlanetScaleHosted MySQL with database branching (cloud API)
  • PocketBaseOpen-source backend in one file (SQLite + auth + realtime)
  • PostgRESTInstant REST API over a PostgreSQL database
  • ScyllaDBHigh-performance Cassandra-compatible database
  • TursoDistributed SQLite (libSQL) at the edge (cloud API)
Agent Platforms13
  • BrowserbaseHeadless browser infrastructure for AI agents (cloud sessions)
  • ChatGPT Work SitesOpenAI's work agent + published Sites/web apps (alpha)
  • DevinCognition's AI software engineer (cloud API)
  • E2BSecure cloud sandboxes for AI agents (spin up / clone / kill)
  • GitHub CopilotAI pair programmer — live org seat/usage monitor
  • HerdrAgent multiplexer — tmux for AI coding agents (terminal)
  • HyperagentAirtable's fleet-of-agents platform (cloud)
  • LakebedAgent-native runtime for full-stack TypeScript capsules (alpha)
  • ManusAutonomous general AI agent (cloud API)
  • OpenAI OperatorOpenAI's browser-using agent (cloud)
  • OpenHands (OpenDevin)Open-source autonomous AI software engineer (self-hosted)
  • SandcastleOrchestrate sandboxed coding agents (isolated containers)
  • SuperAGIOpen-source autonomous-agent framework (self-hosted)
Runtimes13
  • .NET (ASP.NET Core)Run ASP.NET Core & Blazor apps (Kestrel)
  • AstroContent-first framework — zero JS by default; popular headless-WordPress front end
  • code-serverVS Code in the browser (self-hosted)
  • Fermyon SpinServerless WebAssembly apps & HTTP microservices
  • Next.jsReact framework served by a Node process (SSR/SSG)
  • Nuxt (Vue)Vue framework served by a Node process (SSR/SSG)
  • Supabase Edge FunctionsDeno serverless functions on the edge
  • SvelteKit (Svelte)Svelte app framework served by a Node process (SSR/SSG)
  • Tailwind CSSUtility-first CSS — standalone build CLI (no Node)
  • wasmCloudDistributed WebAssembly platform (CNCF)
  • WasmEdgeLightweight WASM runtime for cloud/edge & AI (CNCF)
  • WasmerWebAssembly runtime with a package registry
  • WasmtimeBytecode Alliance WebAssembly runtime (WASI)
ML Workbench11
  • ClearMLExperiment tracking, orchestration & MLOps (self-hostable)
  • DVC StudioData/model version control + experiment dashboard
  • KaggleDatasets, notebooks & competitions (CLI)
  • KubeflowML toolkit & pipelines on Kubernetes
  • MLflowML experiment tracking & model registry (self-hosted)
  • pandasThe standard Python DataFrame library
  • PolarsFast multicore DataFrame library (Rust core)
  • PyTorchDeep-learning framework (GPU/MPS accelerated)
  • scikit-learnClassic machine-learning library for Python
  • Weights & Biases (Local)Self-hosted experiment tracking & dashboards
  • XGBoostGradient-boosted decision trees (high-accuracy tabular ML)
Speech AI11
  • Coqui TTSOpen-source text-to-speech & voice cloning
  • Faster WhisperCTranslate2 Whisper — up to 4× faster
  • HandyFree local push-to-talk speech-to-text (Whisper)
  • Kokoro TTSSmall, fast, high-quality open-weight TTS (82M)
  • MeetilyLocal AI meeting notetaker (desktop app)
  • Piper TTSFast, local neural text-to-speech
  • VibeVoiceMicrosoft's long-form, multi-speaker TTS
  • VoiceboxOpen-source local voice-to-text for macOS
  • WhisperOpenAI's speech-to-text model (Python)
  • Whisper.cppFast C/C++ Whisper inference (CPU/Metal)
  • Wispr FlowAI voice dictation that types into any app
AI Clusters9
  • Apache SparkDistributed big-data processing engine
  • DaskParallel computing for Python (scales pandas/NumPy)
  • Distributed LlamaTensor-parallel Llama across cheap nodes (root + workers)
  • JupyterLabInteractive notebooks for data & AI (Python)
  • NVIDIA Base Command ManagerGPU/HPC cluster provisioning & management (ex-Bright)
  • PetalsBitTorrent-style distributed inference of big models
  • RayDistributed compute for AI (training/serving/tuning)
  • Run:aiGPU orchestration & fractional GPUs on Kubernetes (NVIDIA)
  • SlurmHPC workload manager / job scheduler
Data Pipelines & ETL8
  • AirbyteOpen-source ELT with 300+ connectors (self-hosted / cloud)
  • DagsterAsset-oriented data orchestrator (self-hosted / cloud)
  • dbtSQL-based data transformation & modeling (self-hosted / cloud)
  • KestraEvent-driven orchestration & scheduling, YAML flows (self-hosted)
  • MeltanoOpen-source ELT built on Singer taps & targets (CLI)
  • NATS JetStream PipelinesPersistent streams & consumers for event pipelines (self-hosted)
  • PrefectModern Python workflow orchestration (self-hosted / cloud)
  • Redpanda Connect (Benthos)Declarative stream-processing & connectors (self-hosted CLI)
Image & Video AI6
  • AUTOMATIC1111 WebUIStable Diffusion web UI (txt2img/img2img)
  • AutoShortsLocal video → 9:16 short-clip finder (desktop)
  • ComfyUINode-graph Stable Diffusion / video workflows
  • FooocusSimplest Stable Diffusion — type a prompt, get art
  • InvokeAIPro Stable Diffusion studio (Unified Canvas)
  • Opus ClipAI viral-clip generator (cloud SaaS + API)
Vector Databases6
  • ChromaDeveloper-friendly embedding database (self-hosted)
  • FAISSFast in-process vector similarity search (library)
  • MilvusScalable, distributed vector database (self-hosted)
  • pgvectorVector search inside PostgreSQL (extension)
  • QdrantFast vector DB for embeddings & RAG (self-hosted)
  • WeaviateVector DB with built-in vectorizers & hybrid search (self-hosted)
GPU Infrastructure2
  • DCGM ExporterExport NVIDIA GPU metrics to Prometheus
  • NVIDIA DCGMNVIDIA Data Center GPU Manager — telemetry & health

Browse all services →

Run it all from one Mac app.

FrontierStack installs, monitors and secures the whole stack — locally and across your fleet — from a single native macOS app.

Download FrontierStack