A standalone CLI assistant with voice input/output, persistent memory, tool calling, and live voice conversation — all from your terminal.
Python 3.9+ · macOS, Linux, Windows · One-command setup
Auto-installs Python deps, Ollama, DeepAgent sidecar, pulls default model, and starts all services.
$ curl -fsSL https://raw.githubusercontent.com/astromanish/aishe-cli/main/setup.sh | bashSix core capabilities. No filler.
One-shot, streaming, or REPL. Tools fire automatically.
Press Enter. Speak. Hear the answer back.
Remembers facts across sessions. Searches before answering.
Parallel conversations. Full history. Exportable.
Transcribe any file. Synthesize any text. 10 voices.
One command checks everything. Roundtrip tests included.
Five tools, loaded by default. Add your own in tools.py.
VAD detects speech boundaries. Records, transcribes, thinks, speaks back — automatically.
Everything runs on your machine. No cloud, no API keys, no data leaving your computer.
Your terminal
LangGraph + tools
LLM inference
Speech → text
Text → speech
LangGraph + tools
LLM inference
Speech → text
Text → speech
15 subcommands. Shell completions for bash, zsh, and fish.
aishe statusaishe chat "What is 15 * 4?"aishe stream "Tell me a joke"aishe replaishe liveaishe memory add "User prefers Hindi"aishe memory search "Hindi"aishe threads --newaishe voice transcribe recording.wavaishe voice speak "Namaste"aishe ollama modelsaishe doctoraishe search "pizza"aishe exportaishe config set voice.default_voice M1aishe completions zshOpen source under MIT. Clone it, run it, break it, improve it.
Get started