npm install -g lmstudio-ollama-mcp
lmstudio-ollama-mcp doctor   # or: forge doctor
lmstudio-ollama-mcp "add unit tests for src/utils/logger.ts"

# 1 — Diagnose
lmstudio-ollama-mcp doctor
# Hardware: Apple M3 (8 cores / 16GB) • Recommended: 8 agents
# ● lmstudio (LM Studio) http://localhost:1234/v1  available
#   models: gemma-3-12b-qat, qwen3-27b-ud-iq2_s …

lmstudio-ollama-mcp models
# ● lmstudio  ▸ gemma-3-12b-qat 6.5GB Q4_0
#             ▸ qwen3-27b 7.8GB IQ2_S

# 2 — One-shot
lmstudio-ollama-mcp "refactor src/providers into a registry + add tests. keep public API stable"

# 3 — Parallel (auto-splits into sub-agents)
lmstudio-ollama-mcp --parallel 4 "implement auth module, write tests, and update docs"
# forge alias also works:
forge --parallel 4 "implement auth module, write tests, and update docs"

# 4 — Force a specific model
lmstudio-ollama-mcp --model ollama:qwen2.5-coder:14b "explain this repo's error handling"
lmstudio-ollama-mcp --provider lmstudio --model gemma-3-12b "fix the failing test in tests/tools.test.ts"

# 5 — Interactive
lmstudio-ollama-mcp
# lmstudio-ollama-mcp> add dark mode to docs/index.html

npm install -g lmstudio-ollama-mcp
# aliases also available: forge, forgecode
# or one-off
npx lmstudio-ollama-mcp doctor

git clone https://github.com/your-org/your-project && cd your-project
lmstudio-ollama-mcp init   # creates lmstudio-ollama-mcp.json (also reads forgecode.json for compat)
lmstudio-ollama-mcp doctor # verify providers + hardware
lmstudio-ollama-mcp "list the codebase structure and suggest 3 small improvements"

export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...

┌─────────────────────────────────────────────────────────┐
│  CLI  lmstudio-ollama-mcp "task"  •  doctor  •  models   │
│       aliases: forge, forgecode                         │
├─────────────────────────────────────────────────────────┤
│  Router  (strategy: auto | local-first | frontier-first)│
│  ├─ classify(prompt) → trivial | small | medium | large │
│  └─ thresholds.preferLocalFor: lint/format/test/search  │
├─────────────────────────────────────────────────────────┤
│  Orchestrator  (decompose → batch by deps → schedule)   │
│  ├─ Planner LLM decomposes goal → SubTasks[]            │
│  └─ Scheduler (hardware-aware p-limit, preserves order) │
├─────────────────────────────────────────────────────────┤
│  Agent Loop  (provider.chat ↔ tool executor)            │
│  ├─ Tools: read_file, write_file, edit_file, bash,      │
│  │        glob, grep, list_dir                           │
│  └─ Max 25 tool turns, exact-string edits               │
├─────────────────────────────────────────────────────────┤
│  Providers  (OpenAI-compatible)                         │
│  ├─ LM Studio  http://localhost:1234/v1  (+ fs scan)    │
│  ├─ Ollama     http://localhost:11434 (+ /api/tags)     │
│  ├─ llama.cpp  http://localhost:8080/v1                 │
│  └─ Frontier   OpenAI / Anthropic (optional)            │
├─────────────────────────────────────────────────────────┤
│  Hardware Detector  •  Scheduler                        │
│  cores × overcommit, free mem / perAgent → maxParallel │
│  Apple Silicon bonus, clamp 1..16                       │
└─────────────────────────────────────────────────────────┘

User prompt
  → Router.classify → pick provider+model (local for small, frontier for large)
  → If parallel & non-trivial: Orchestrator.decompose → 2-6 SubTasks
  → Scheduler.runAll(SubTasks) with maxParallel = f(cores, RAM)
  → Each SubTask → Agent(provider, model, ToolExecutor) → tool loop
  → Synthesis agent merges results
  → Final summary

// lmstudio-ollama-mcp.json
{
  "providers": {
    "my-local": { "type": "openai", "baseUrl": "http://192.168.1.10:1234/v1", "enabled": true }
  }
}

// hardware/detector.ts — recommendParallelism()
cpuLimit = floor(cores * overcommit) - 1
memLimit = floor((totalGb*1024 - 2048) / perAgentMb)
maxParallel = min(cpuLimit, memLimit) + appleSiliconBonus
// clamp: 1..8 default, up to 16 on 64GB machines

lmstudio-ollama-mcp --parallel 8 "migrate codebase from Jest to Vitest"
# Decomposed:
#  t1 Explore & plan  →  search (routed to local 7B)
#  t2 Implement       →  code   (routed to local or frontier)
#  t3 Verify          →  test   (routed to local)
# Runner: Scheduler.runAll with p-limit = 8

lmstudio-ollama-mcp config --show   # resolved JSON
lmstudio-ollama-mcp config --path   # file locations
lmstudio-ollama-mcp init            # scaffold lmstudio-ollama-mcp.json

{
  "version": 1,
  "providers": {
    "lmstudio": { "type": "lmstudio", "baseUrl": "http://localhost:1234/v1", "enabled": true },
    "ollama":   { "type": "ollama",   "baseUrl": "http://localhost:11434",      "enabled": true },
    "llamacpp": { "type": "llamacpp", "baseUrl": "http://localhost:8080",       "enabled": true },
    "openai":   { "type": "openai",   "baseUrl": "https://api.openai.com/v1",   "apiKey": "sk-..." }
  },
  "router": {
    "strategy": "auto", // auto | local-first | frontier-first | local-only
    "frontierProvider": "openai",
    "frontierModel": "gpt-4o-mini",
    "thresholds": {
      "smallTaskMaxTokens": 2000,
      "preferLocalFor": ["lint","format","test","search","summarize","explain"]
    }
  },
  "hardware": {
    "maxParallelAgents": 4,      // auto if omitted
    "maxMemoryPerAgentMb": 1200,
    "cpuOvercommit": 1
  },
  "permissions": {
    "allowBash": true,
    "allowWriteOutsideWorkspace": false,
    "allowNetwork": true
  }
}

npm install
npm run build        # tsc
npm test             # vitest
npm run dev -- doctor

src/
  cli/            commander CLI + commands (doctor, models, config, init)
  config/         Zod schema + layered store (global ↔ project)
  hardware/       detector (cores/RAM/GPU) + p-limit scheduler
  providers/      base + openai-compatible + lmstudio/ollama/llamacpp + registry + router
  core/           Agent (tool loop) + Orchestrator (decompose + parallel)
  tools/          definitions + executor (fs/glob/grep/bash)
  utils/          logger, format
tests/            vitest suites (hardware, tools, router, config, providers)
docs/             GitHub Pages landing (WizardZ-inspired, lime/black)

npm run build && npm test