๐“Ÿ

Meet Thoth

Personal AI Sovereignty

A local-first AI assistant with 20 integrated tools, long-term memory, voice, vision, health tracking, and messaging channels โ€” all running on your machine. Your models, your data, your rules.

โฌ‡ Download for Windows โ˜† View on GitHub
๐Ÿ–ฅ๏ธ Windows 10/11 ๐Ÿ†“ Free & open source ๐Ÿ“œ MIT License ๐ŸŽ macOS coming soon
Governments are investing billions to keep AI infrastructure within their borders. Thoth applies the same principle to the individual โ€” your compute, your data, your choice of model, accountable to no one but you.

Everything runs locally

No cloud dependencies. No subscriptions. No data leaving your machine.

๐Ÿ”’

100% Local AI

Every LLM call, every voice transcription, every memory lookup runs on your hardware. No data is sent to any cloud AI provider โ€” ever. External APIs are opt-in and individually toggleable.

Core Principle
๐Ÿค–

Autonomous ReAct Agent

The agent reasons about your question, decides which of 20 tools to use, chains multiple lookups, and assembles a complete answer โ€” all autonomously. Smart context trimming keeps multi-tool workflows within window limits. Live token counter tracks usage in real time.

๐Ÿง 

Long-Term Memory

Thoth remembers what matters โ€” names, birthdays, preferences, projects โ€” across every conversation. FAISS semantic search with automatic recall injects relevant memories before every response. Background extraction periodically scans past chats for personal facts you mentioned in passing.

๐Ÿ“‹

Habit & Health Tracker

Track medications, symptoms, exercise, periods, mood, sleep โ€” through natural conversation. "I took my Lexapro" โ†’ logged. 7 built-in analyses: adherence, streaks, trends, co-occurrence. Results auto-export to CSV and chain to interactive Plotly charts.

New in v3.0
๐Ÿ“ฌ

Messaging Channels

Connect a Telegram bot or email channel so the agent meets you where you are. Every message is processed by the full ReAct agent with all tools available. Each chat gets its own conversation thread.

New in v3.0
๐ŸŽค

Voice & Text-to-Speech

Local speech-to-text via faster-whisper (CPU, int8 quantized) and neural TTS via Piper with 8 voice options. Mic auto-mutes during playback. Fully hands-free, fully offline โ€” no cloud APIs touch your voice data.

๐Ÿ‘๏ธ

Vision & Screen Capture

Capture images from your webcam or take screenshots and ask questions about them. Local vision model analysis โ€” multi-camera support, inline image display in chat.

โšก

Workflows & Scheduling

Build reusable multi-step prompt sequences that chain research โ†’ summarisation โ†’ action. Run manually or schedule daily/weekly. Template variables, background execution, desktop notifications, and 4 built-in templates to start.

๐Ÿ–ฅ๏ธ

Native Desktop App

One-click installer, native OS window via pywebview, system tray with status indicator, branded splash screen, and a first-launch setup wizard that walks you through model selection. No Docker, no YAML, no terminal needed.

๐Ÿงฉ

39 Curated Models

Switch freely between Qwen, Llama, Gemma, Mistral, DeepSeek, Phi, Nemotron, and more โ€” only models verified for tool calling are included. Download buttons with live progress. Configurable context windows up to 256K tokens with automatic model-max capping.

๐Ÿ“ง

Gmail & Calendar

Search emails, read threads, draft and send messages. View, create, update, and manage calendar events โ€” all through natural language. Tiered permissions let you control read, write, and destructive access independently.

๐Ÿ“

Files, Charts & Data

Sandboxed file operations with PDF, CSV, Excel, JSON support. Structured files return schema + stats + preview via pandas. Interactive Plotly charts rendered inline โ€” bar, line, scatter, pie, heatmap, and more. Destructive actions require confirmation.

20 Tools ยท 45 Operations

The agent autonomously decides which tools to use based on your question

Search & Knowledge

๐Ÿ”
Web Search
Tavily live search
API Key
๐Ÿฆ†
DuckDuckGo
Free search, no key
Free
๐ŸŒ
Wikipedia
Encyclopedic knowledge
Free
๐Ÿ“š
Arxiv
Academic papers
Free
โ–ถ๏ธ
YouTube
Search + transcripts
Free
๐Ÿ”—
URL Reader
Extract web content
Free
๐Ÿ“„
Documents
FAISS vector search
Free

Productivity

๐Ÿ“ง
Gmail
Search, read, draft, send
OAuth
๐Ÿ“…
Calendar
Events & scheduling
OAuth
๐Ÿ“
Filesystem
Sandboxed file ops
Free
โฐ
Timer
Desktop notifications
Free
๐Ÿ“‹
Tracker
Habits & health
Free

Computation & Analysis

๐Ÿงฎ
Calculator
Safe math evaluation
Free
๐Ÿ”ข
Wolfram Alpha
Advanced computation
API Key
๐ŸŒค๏ธ
Weather
Forecasts via Open-Meteo
Free
๐Ÿ‘๏ธ
Vision
Camera & screen analysis
Free
๐Ÿง 
Memory
Persistent knowledge
Free
๐Ÿ”
Conversation Search
Search past threads
Free
๐Ÿ–ฅ๏ธ
System Info
OS, CPU, RAM, disk
Free
๐Ÿ“Š
Chart
Interactive Plotly charts
Free

Why not just use ChatGPT?

Cloud AI rents you access to someone else's system. Thoth gives you ownership.

Cloud AI (ChatGPT, Claude, Gemini) ๐“Ÿ Thoth
Your data Sent to cloud servers, used for training Stays on your machine โ€” always
Conversations Owned by the provider, can be leaked Local SQLite, fully yours
Cost $20+/month per subscription Free forever โ€” your hardware
Memory Limited, opaque, provider-controlled You control what's remembered
Tools Sandboxed plugins, limited access Gmail, Calendar, filesystem, webcam
Voice Cloud-processed speech Local Whisper + Piper TTS
Health tracking None Conversational tracker + analysis
Availability Requires internet, subject to outages Works offline, no throttling

Up and running in minutes

1

Download & install

Run the one-click Windows installer โ€” it sets up Ollama, Python, and all dependencies automatically. Or clone the repo and run from source in 5 commands.

2

Choose your models

On first launch, a setup wizard walks you through selecting and downloading a brain model and vision model. The default (qwen3:14b) is recommended for the best balance of speed and capability.

3

Start talking

Ask anything in natural language โ€” the agent figures out which tools to use. Search the web, check your email, analyze your screen, track a medication, set a timer. Just ask.

๐Ÿ”’ Privacy by architecture

Thoth doesn't just promise privacy โ€” it enforces it structurally. All LLM inference, voice processing, memory storage, and conversation history runs entirely on your machine. External network calls only happen when you explicitly use an online tool โ€” and each one can be individually disabled.

๐Ÿ–ฅ๏ธ Local inference
๐Ÿ’พ Local storage
๐ŸŽค Local voice
๐Ÿšซ No telemetry
๐Ÿ”ง Opt-in APIs
๐Ÿ“œ MIT License

Take back your AI sovereignty

Free, open source, and yours to keep. No accounts. No subscriptions. No data harvesting.

โฌ‡ Download for Windows โ˜† Star on GitHub