Files
env-ansible/tasks/workstation/linux/software/zeroclaw.yml
T

63 lines
2.0 KiB
YAML

---
# 2026-10-05 Hyperling
# Install a local LLM for use offline.
# - https://zeroclaw.net/blog/install-zeroclaw
# - https://zeroclaw.net/blog/set-up-zeroclaw-bot-ollama-telegram
#
# Packages Details
# - https://archlinux.org/packages/extra/x86_64/zeroclaw/
# - https://archlinux.org/packages/extra/x86_64/ollama/
#
# Individual Guides
# - https://github.com/zeroclaw-labs/zeroclaw
# - https://wiki.archlinux.org/title/Ollama
# Currently only testing this on Arch based distros (pacman).
- name: Workstation | Linux | Software | ZeroClaw
block:
- name: Workstation | Linux | Software | ZeroClaw | Facts 01
ansible.builtin.set_fact:
zeroclaw: zeroclaw
ollama: ollama
# 1. Install
- name: Workstation | Linux | Software | ZeroClaw | 01 | Install
ansible.builtin.package:
name:
- "{{ zeroclaw }}"
- "{{ ollama }}"
state: present
- name: Workstation | Linux | Software | ZeroClaw | 02 | Pull Model
ansible.builtin.debug:
msg: TBD
### ollama serve & # start Ollama server
### ollama pull llama3.2 # ~2GB, or a smaller model for less RAM
- name: Workstation | Linux | Software | ZeroClaw | 03 | Config
ansible.builtin.debug:
msg: TBD
### ~/.zeroclaw/config.toml`
### `default_provider = "ollama"` pointing at `http://127.0.0.1:11434`
- name: Workstation | Linux | Software | ZeroClaw | 04 | Test
ansible.builtin.debug:
msg: TBD
### zeroclaw agent -m "Hello!" # quick test
- name: Workstation | Linux | Software | ZeroClaw | 05 | Init Scripts | zeroclaw
ansible.builtin.debug:
msg: TBD
### `/run/runit/zeroclaw/run`
### `zeroclaw daemon`
- name: Workstation | Linux | Software | ZeroClaw | 05 | Init Scripts | ollama
ansible.builtin.debug:
msg: TBD
when: ansible_service_mgr == "runit"
### `/run/runit/ollama/run`
### `ollama serve`
when: ansible_pkg_mgr == "pacman"