ShellClaw
Local LLM autocomplete for your terminal
Type a Zsh command. See a useful suffix in gray. Accept it with Ctrl+Space. The model and your command memory stay on your Mac.
~ shellclaw status
shellclaw: running
Ctrl+Space accepts the gray suffix
From install to first suggestion
Homebrew installs the binary and hook, downloads the local model, and starts the daemon. Open a new terminal when setup finishes.
Official repository and source code: GitHub - Edwardd02/Shell-Claw.
- InstallRun three Homebrew commands.
- TypeStart a command you actually use.
- AcceptPress Ctrl+Space when the suffix is useful.
brew tap edwardd02/shellclawbrew trust edwardd02/shellclawbrew install shellclaw
A short path from keystroke to ghost text
Memory handles familiar commands quickly. The local model takes over when recall has no valid match.
Zsh hook
Captures the current line, cursor, directory, and response deadline.
Local daemon
Checks SQLite memory first, then uses Qwen2.5-Coder through llama.cpp.
POSTDISPLAY
Renders only the validated suffix and ignores stale responses.
Personal without a hosted profile
Executed commands are stored in a local SQLite database so future suggestions can match your habits and current working directory.
- InferenceRuns on your Mac with no hosted API.
- MemoryLives in
~/.shellclaw/memory.db. - TelemetryNone. Persistent file logs are off by default.
- ControlDelete
~/.shellclawto erase local data.
Small model, narrow job
Terminal autocomplete rewards low latency, short output, local context, and fast correction. It does not require a general chat system.
Built for Apple Silicon and Zsh
Bash support is experimental. Linux and Intel macOS are not released yet.