Skip to main content

Multi-Agent AI Terminal Assistant

Project description

🐾 NC Claw — Local Multi-Agent AI Terminal Assistant

A lightweight, offline-first, multi-role AI assistant built for Linux ARM64 terminals (like CM5) — no cloud lock-in, no telemetry, zero dependencies beyond Python 3.8+.

✨ Run it. Talk to it. Command it. All inside your terminal — or via web UI.


🔑 Core Principles

  • Local-first: All logic, config (~/.claw_config.json), history (~/.claw_history), and agents run on your machine.

  • Multi-Agent Native: Built-in roles (@coder, @artist, @chat, @lawyer) collaborate in group chat mode — each with dedicated skills and persona.

  • Terminal-Native Commands: Execute shell, read/write files, inspect system, or run Python — all via clean // syntax:

    //exec ls -la //read ~/Desktop/notes.txt //tree /home/ncstudio/Desktop --depth 2 //time //ip

  • CM5 Optimized: Tested on Raspberry Pi OS (aarch64); low memory footprint, no GPU required.


🚀 Quick Start

  1. Clone & enter project

    cd ~/Desktop && git clone https://github.com/NCstudio/nc-claw.git && cd nc-claw

  2. Launch Claw

    python3 nc_claw/claw.py

  3. Open Web UI
    → Visit http://localhost:8000 in your browser
    (Terminal stays active as real-time log dashboard)

  4. Try your first command
    In the web chat or terminal input:

    @all Hello! What can you do?

✅ Done. You’re now running a full local AI assistant — no sign-up, no API key needed.


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nc_claw-0.8.7.tar.gz (36.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nc_claw-0.8.7-py3-none-any.whl (35.8 kB view details)

Uploaded Python 3

File details

Details for the file nc_claw-0.8.7.tar.gz.

File metadata

  • Download URL: nc_claw-0.8.7.tar.gz
  • Upload date:
  • Size: 36.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for nc_claw-0.8.7.tar.gz
Algorithm Hash digest
SHA256 4f4443d5cac7ccfa8618756b9c51aaa6d1b66da14132beb2758e8efd04daacaa
MD5 dea6cdf38a401653c2aeacfe0ad6366c
BLAKE2b-256 43333a853b8d5c08031f46a7765a6833326bba85b53055b00a9e87a99eb19c4e

See more details on using hashes here.

File details

Details for the file nc_claw-0.8.7-py3-none-any.whl.

File metadata

  • Download URL: nc_claw-0.8.7-py3-none-any.whl
  • Upload date:
  • Size: 35.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for nc_claw-0.8.7-py3-none-any.whl
Algorithm Hash digest
SHA256 596613e13aba09281fb142698727b17512de69e97b7c48b36ae09384a3437075
MD5 3585c0fbec5a5f77f7d680099b989ce3
BLAKE2b-256 9fbdcba5c854c2d4fc33c8e1ec2644dc18146295e1e3495b70b28c06417abb27

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page