Skip to main content

Self-Hosted AI Companion Platform

Project description

🤝 Familiar

Self-hosted AI agent with Signal-grade encryption

Version Python License


Quick Start

Unzip, then run the script for your OS:

Linux / macOS / Raspberry Pi

cd familiar
./run.sh

Windows

Double-click run.bat, or from Command Prompt:

cd familiar
run.bat

Familiar auto-detects your setup. If you have Ollama installed, it uses local AI (free, private). If you set an API key, it uses Claude or GPT instead:

export ANTHROPIC_API_KEY="sk-ant-..."   # Claude
# or
export OPENAI_API_KEY="sk-..."          # GPT
./run.sh

That's it. No Docker, no databases, no config files needed.


What Is Familiar?

A self-hosted AI agent that runs on your machine — from a Raspberry Pi to a workstation. Talk to it through CLI, Telegram, Discord, or the web dashboard. It remembers context, executes tools, manages your calendar, reads your email, controls GPIO pins, and browses the web.

Everything is encrypted locally. Your conversations never leave your hardware unless you choose a cloud LLM provider.

Features

  • Multi-provider LLM — Claude, GPT, or local models via Ollama
  • 36 skills — email, calendar, browser, knowledge base, tasks, GPIO, voice, and more
  • Signal-grade encryption — sessions, memory, and data encrypted at rest
  • Multi-channel — CLI, Telegram, Discord, web dashboard, SMS, Signal
  • Raspberry Pi optimized — runs on 4GB Pi with local Ollama models
  • Multi-device mesh — connect multiple Familiar instances across devices
  • HIPAA-ready — compliance mode with audit logging and PHI detection

GUI Launcher

For a graphical interface (recommended on desktop):

python3 FamiliarLauncher.py

This opens a window for managing Ollama models, starting/stopping the agent, and viewing logs. Requires tkinter (sudo apt install python3-tk on Linux).


Advanced Installation

For running as a system daemon, Pi optimization, or full dependency install:

# Full install with venv + systemd service (Linux)
./scripts/install.sh

# Pi-specific with swap, GPU memory, and Ollama optimization
./scripts/install-pi.sh --with-ollama

# Windows full install with venv
scripts\install.bat

See docs/INSTALL.md for detailed options.


Configuration

Copy and edit the sample config:

cp config.sample.yaml ~/.familiar/config.yaml

Key settings:

llm:
  default_provider: anthropic     # or openai, ollama
  anthropic_model: claude-sonnet-4-20250514
  ollama_model: llama3.2

agent:
  name: Familiar
  memory_enabled: true
  skills_enabled: true

security:
  encrypt_sessions: true
  encrypt_memory: true

Project Structure

familiar/
├── run.sh / run.bat         # Start here
├── FamiliarLauncher.py       # GUI launcher
├── __main__.py              # CLI entry point
├── core/                    # Agent, providers, memory, tools
├── channels/                # CLI, Telegram, Discord, etc.
├── skills/                  # 21 built-in skills
├── launcher/                # GUI + hardware detection
├── dashboard/               # Web dashboard
├── admin/                   # Admin panel
├── pwa/                     # Progressive web app
├── docs/                    # Documentation
└── scripts/                 # Install scripts + dev tools

License

MIT — Copyright (c) 2026 George Scott Foley

See LICENSE for full text.

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

familiar_agent-1.4.0-py3-none-any.whl (1.4 MB view details)

Uploaded Python 3

File details

Details for the file familiar_agent-1.4.0-py3-none-any.whl.

File metadata

  • Download URL: familiar_agent-1.4.0-py3-none-any.whl
  • Upload date:
  • Size: 1.4 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for familiar_agent-1.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c8ae18ea05f44520bdeee561a079f2584156e83bd65a8b125511cb2f8f19114b
MD5 55cf4442d22eac829045dcc4c376ded8
BLAKE2b-256 fb408475c5fa546817cea79e2e6a06ad2b6987fafebb2ace90ccdb3d4e5db1c3

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