Harbor saves you dozens of hours configuring your local AI stack.
One command spins up LLM backends, chat frontends, web search, voice, image gen, fine-tuning, agent tools - all pre-configured to talk to each other. Manage your downloaded models, create config profiles, use agentic coding tools with your local LLMs, and much more.
Your AI coding tools keep traces. Skilled reads them.
Live TUI dashboard that aggregates skill usage across Claude Code, OpenCode, Codex, Grok, and Droid. Reads local history files only. Zero network, zero telemetry.
Frequency counts, weekly trends, hourly distribution, per-project breakdowns, and audit heuristics (rising = 50%+ increase over 4 weeks, stale = unused 30+ days, etc.).
No data leaves your machine. No accounts, no config files, no API keys.
mi is an autonomous coding agent that fits in a single JavaScript file. no framework, no dependencies beyond Node builtins, works with any OpenAI-compatible API — OpenAI, Ollama, local models, whatever you have.
the core is a loop: call the llm, check if it wants to use tools, execute them, feed results back, repeat. two built-in tools — bash (full system access) and skills (markdown playbooks loaded on demand) — are enough for it to read repos, write code, run tests, and debug failures.
