Skip to main content

Self-improving · Postgres-native · Yours to run

The agent with a cognitive substrate

Thoth is a self-improving AI agent built on a five-layer memory substrate that consolidates rather than accumulates. It creates skills from experience, sharpens them in use, and builds a deepening model of who you are across every session — instead of forgetting when the context window closes.

The five-layer substrate · L0 → L4

L0Perceptionevery event, captured
L1Entitiesfacts & relationships
L2Associationsa weighted graph
L3Patternsgeneralizations
L4Self-modelwhat it knows it knows

An MIT-licensed fork of Hermes by Nous Research, maintained by 519lab — rebuilt around the cognitive substrate.

Install

Linux / macOS / WSL2

curl -fsSL https://raw.githubusercontent.com/519lab/thoth-agent/main/scripts/install.sh | bash

Windows (native, PowerShell)early beta, details →

iex (irm https://raw.githubusercontent.com/519lab/thoth-agent/main/scripts/install.ps1)

Android (Termux) — same curl one-liner as Linux; the installer auto-detects Termux.

See the full Installation Guide for what the installer does, the per-user vs root layout, and Windows-specific notes.

What is Thoth Agent?

It's not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. It's an autonomous agent that gets more capable the longer it runs. It lives wherever you put it — a $5 VPS, a GPU cluster, or serverless infrastructure (Daytona, Modal) that costs nearly nothing when idle. Talk to it from Telegram while it works on a cloud VM you never SSH into yourself. It's not tied to your laptop.

🚀 InstallationInstall in 60 seconds on Linux, macOS, WSL2, or native Windows (early beta)
📖 Quickstart TutorialYour first conversation and key features to try
🗺️ Learning PathFind the right docs for your experience level
⚙️ ConfigurationConfig file, providers, models, and options
💬 Messaging GatewaySet up Telegram, Discord, Slack, WhatsApp, Teams, or more
🔧 Tools & Toolsets70+ built-in tools and how to configure them
🧠 Memory SystemPersistent memory that grows across sessions
📚 Skills SystemProcedural memory the agent creates and reuses
🔌 MCP IntegrationConnect to MCP servers, filter their tools, and extend Thoth safely
🧭 Use MCP with ThothPractical MCP setup patterns, examples, and tutorials
🎙️ Voice ModeReal-time voice interaction in CLI, Telegram, Discord, and Discord VC
🗣️ Use Voice Mode with ThothHands-on setup and usage patterns for Thoth voice workflows
🎭 Personality & SOUL.mdDefine Thoth's default voice with a global SOUL.md
📄 Context FilesProject context files that shape every conversation
🔒 SecurityCommand approval, authorization, container isolation
💡 Tips & Best PracticesQuick wins to get the most out of Thoth
🏗️ ArchitectureHow it works under the hood
FAQ & TroubleshootingCommon questions and solutions

Key Features

🔄
A closed learning loop

Agent-curated memory with periodic nudges, autonomous skill creation, skill self-improvement during use, Postgres full-text cross-session recall with LLM summarization, and Honcho dialectic user modeling.

🧠
A five-layer substrate

Perception → entities → associations → patterns → self-model on Postgres + pgvector, maintained by a roster of always-on sub-agents. Memory that consolidates, not accumulates.

🌍
Runs anywhere

Six terminal backends — local, Docker, SSH, Daytona, Singularity, Modal. Daytona and Modal hibernate when idle, costing nearly nothing.

💬
Lives where you do

20+ platforms from one gateway — Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, SMS, Microsoft Teams, Home Assistant, and more.

⏱️
Scheduled automations

Built-in cron that delivers results to any connected platform on a schedule you set.

⛓️
Delegates & parallelizes

Spawn isolated subagents for parallel workstreams. Programmatic Tool Calling via execute_code collapses multi-step pipelines into single inference calls.

🧩
Open-standard skills

Compatible with agentskills.io — skills are portable, shareable, and community-contributed through the Skills Hub.

🔌
MCP & full web control

Connect any MCP server, and search, extract, browse, see (vision), generate images, and speak (TTS) across the open web.

🔬
Research-ready

Batch processing, trajectory export, and RL training with Atropos — built by model trainers, forked from Hermes by Nous Research (the lab behind the Hermes, Nomos, and Psyche models).

For LLMs and coding agents

Machine-readable entry points to this documentation:

  • /llms.txt — curated index of every doc page with short descriptions. ~17 KB, safe to load into an LLM context.
  • /llms-full.txt — every doc page concatenated into a single markdown file for one-shot ingestion. ~1.8 MB.

Both files also resolve at /docs/llms.txt and /docs/llms-full.txt. Generated fresh on every deploy.