All Projects

bareai

See what your bare-metal machine is doing — right now.

Developer Tools / AI InfrastructureActive — v0.1.2v0.1.21.25+MITLinux · macOS · Windowsread-onlyHomebrew · APT · curl
19
Binary downloads
GitHub Releases
Go
Language
5
Collectors
6
MCP Tools
v0.1.2
Release

Overview

Problem

One machine, five separate tools

Checking a self-hosted AI box usually means switching between nvidia-smi, docker ps, and manual curl calls to different ports — each with its own output format and no shared context.

bareai reads all of it in one pass: host, GPUs, Docker, local LLM runtimes, and local databases. It only reads state — it never starts, stops, or changes anything.

How it works

Collectors run independently

Each collector below can fail on its own without breaking the rest. A missing GPU or database isn't an error — it's marked skipped, and the command still exits 0.

Host
CPU, RAM, disks, load, uptime
GPU
NVIDIA, AMD, Apple Silicon
Docker
Containers, images, volumes
LLM
Ollama, vLLM, SGLang, Triton
DB
Postgres, Redis, Mongo, MySQL, Qdrant, Elasticsearch
Interface

One snapshot, four views

The TUI, the --json output, and the MCP server all read the same snapshot struct — the correlation logic exists in exactly one place.

On a TTY, `bareai` opens a live dashboard with six tabs and sparklines for load, VRAM, and LLM latency. In a script or CI, it just prints and exits.

Agents

MCP for coding agents

`bareai mcp` starts a stdio MCP server that exposes the same snapshot as six tools, so an agent like Cursor or Claude Code can read real GPU, Docker, and LLM state instead of shelling out to nvidia-smi and docker ps itself.

How it works

Five collectors gather facts about the machine. A correlation layer merges them into one snapshot. Four renderers display that same snapshot.

Collectors
host, gpu, docker, llm, db — each optional
Snapshot
one correlated data model
Renderers
CLI, TUI, JSON, MCP

In the terminal

bareai status
$ bareai status
Collected: 2026-07-22T12:00:00Z

Host
  Hostname:  ai-box
  OS:        linux 24.04 (ubuntu)
  CPU:       AMD EPYC (64 cores)
  Memory:    128.0 GiB / 512.0 GiB
  Load:      2.10 1.80 1.50

GPUs:
  [0] NVIDIA A100-SXM4-80GB (nvidia)  util=45%  mem=4.0 GiB/80.0 GiB

Docker:      2 running / 4 total  (Engine 27.5.1)
LLM:         2 discovered (ollama, vllm)
bareai mcp
$ bareai mcp
bareai mcp: stdio server ready (version 0.1.2, 6 tools)
bareai mcp: stdout=MCP protocol · stderr=logs · waiting for client on stdin…
bareai mcp: ← initialize client="cursor"
bareai mcp: → initialize ok (1ms)
bareai mcp: ← tools/call tool="bareai_snapshot"
bareai mcp: → tools/call ok (420ms)

Install & use

macOS / Linux (no sudo)
$ curl -fsSL https://raw.githubusercontent.com/baselhusam/bareai-cli/main/scripts/install.sh | bash
$ source ~/.zshrc && bareai version
Homebrew
$ brew tap baselhusam/tap
$ brew trust baselhusam/tap
$ brew install bareai
$ bareai version
Windows (PowerShell)
$ irm https://raw.githubusercontent.com/baselhusam/bareai-cli/main/scripts/install.ps1 | iex
$ bareai version
quick start
$ bareai status # one-screen summary
$ bareai inspect # full correlated report
$ bareai inspect --json | jq . # machine-readable snapshot
$ bareai doctor --share # paste-friendly report for issues/chat
$ bareai mcp # MCP server for Cursor / Claude (stdio)

Commands

(none) / watchLive TUI dashboard
statusHost + infrastructure summary
gpuGPU inventory and metrics
dockerContainers, images, volumes
llmDiscovered inference servers
dbLocal databases (Postgres, Redis, Mongo, …)
probeOne-hit smoke tests
inspectFull correlated report
doctorRanked diagnostics + read-only suggestions
mcpMCP server for coding agents (stdio)
config pathResolved config file path
versionBuild metadata

Agent / MCP tools

bareai_snapshot

What is on this box? — full correlated snapshot

bareai_correlations

Which model runs on which GPU or container?

bareai_doctor

What's wrong, and what's safe to try?

bareai_probe

Is inference actually healthy right now?

bareai_llms

Runtime, endpoint, PID, health, models

bareai_databases

Local database engines, addresses, health

Built with

Go 1.25
core language
Bubble Tea
Charm TUI framework
Cobra
CLI command tree
Docker Engine API
container discovery
NVML / ROCm / Metal
GPU probes per vendor
MCP (stdio)
agent tool contract
GoReleaser
cross-platform release builds
Homebrew tap + APT (Cloudsmith)
packaging