The Intelligence Layer:
A Mind for Your Machine.
A source-available agentic system that turns your machine from an inanimate silo into something conversational, proactive, autonomous.
Model-independent by design — it dynamically loads every model tied to your API keys, runs entirely offline via your preferred model library, or takes a hybrid approach with both.
It learns your patterns and remembers your context, adapting into a uniquely tuned agent specific to each user.
One foundational substrate, infinite potential outcomes.
You are what makes your agent truly unique.
$ substrate
Substrate v1.2.0 — Agent ready.
you: Find all PDFs on my desktop, summarize each, and save a report to Obsidian.
agent: On it. Found 4 PDFs. Reading and summarizing...
▸ exec Get-ChildItem ~\Desktop -Filter *.pdf
▸ read_file quarterly_report.pdf
▸ obsidian create_note "PDF Summaries"
agent: Done. Summaries saved to your Obsidian vault.
$ |
Capabilities
Persistent memory, autonomous scheduling, and full OS control — model-independent architecture that adapts to each user.
Shell commands, file operations, process management, mouse/keyboard control, and native Windows UI automation.
Dynamically loads all available models from your API keys, runs entirely offline via your preferred model library, or takes a hybrid approach with both. Any OpenAI-compatible endpoint works too. Hot-swap mid-conversation.
Full Chrome DevTools Protocol control. Navigate, click, type, submit forms, execute JavaScript, and capture screenshots of any page.
Local TTS via Kokoro-82M or cloud via ElevenLabs. Speech recognition input. The agent can speak every response aloud.
Unified SQLite with FTS5 full-text search and vector embeddings. Hybrid keyword + semantic retrieval across sessions.
File-driven task scheduling via CIRCUITS.md. Recurring tasks, startup routines, and a system tray daemon that runs even when the UI is closed.
Generate images via DALL-E 3 or Google Imagen. Results render inline in the chat with click-to-zoom and download.
Hook-based plugin architecture. Connect external MCP tool servers for any custom integration — the agent discovers and calls their tools automatically.
Electron desktop app with animated avatar, plus a PWA-capable WebUI accessible from any phone, tablet, or browser on your network.
Configurable screen observation, camera/computer vision, and autonomous context building. Control how often the agent watches your screen, sees through your camera, and learns your workflows — all with adjustable intervals and toggles per channel.
A living, animated avatar with idle breathing, talking animations, bounce, wiggle, and squish reactions. Customize your agent's personality via editable markdown files — SUBSTRATE.md defines its core identity, PRIME.md sets startup behavior, and CIRCUITS.md schedules recurring tasks. Upload any image as the avatar face through the radial config panel.
Access your agent from any device on your ZeroTier network — phone, tablet, or another PC. The built-in WebUI and mobile PWA connect securely over your private overlay network without exposing anything to the public internet. Chat, use voice, and control your desktop remotely.
Every awareness channel is independently configurable — enable/disable, set intervals, customize prompts
Periodic screenshots let the agent see what you're working on and build context about your workflow.
See through your phone's camera via the mobile WebUI. The agent reacts naturally to what it sees — with a special "first look" prompt when vision connects.
Background system monitoring on a timer. The agent checks for events, alerts, and scheduled tasks — responds silently unless something needs attention.
Periodic conversational check-ins. The agent proactively comments on your work, offers suggestions, or shares observations.
Automatically creates Obsidian notes summarizing key conversation points, decisions, and action items.
Periodically generates image prompts inspired by the conversation context using DALL-E or Imagen. Creative visual companion.
All channels have independent enable/disable toggles, configurable min/max intervals, and custom prompts. The agent builds a richer understanding of your workflow over time.
The Interface
Just your avatar, a text field, and a transparent canvas. Designed to fit into whatever workflow you have without being intrusive or distracting.
Right-click the avatar to open the radial menu — settings, prompts, profiles, models, and autonomy controls all live here.
Upload any image as the agent face. It animates with idle breathing, talking lips, and reactive expressions like happy, angry, or searching.
Type or speak. The agent responds in text and can read every reply aloud with local or cloud TTS voices.
Architecture
A hybrid Electron + Python architecture with bidirectional IPC, a Flask API layer, and pluggable LLM backends.
Tool Ecosystem
Every tool the agent needs to control your desktop, automate workflows, and interact with the world.
Core tools (highlighted) are always loaded. On-demand tools load automatically when relevant keywords are detected.
Tools load on-demand based on conversation context — no wasted tokens.
The agent doesn't just use tools — it creates new ones.
When the agent encounters a complex multi-step workflow, it can autonomously write scripts, save them as reusable skills, and invoke them in future tasks. Your toolset grows organically from real usage — no manual configuration needed.
Agent encounters a complex task and writes a multi-step script or automation to solve it.
Saves the solution as an emergent skill in workspace/emergent/ with trigger words and documentation.
After user confirmation, the skill is promoted to the permanent skills/ directory — available forever.
Press F9 to record your UI actions (clicks, keystrokes, navigation). The recording is saved and can be turned into a reusable skill the agent can replay.
Each skill is a Markdown file with name, description, triggers, and step-by-step instructions. Easy to read, edit, and share.
Skills are scanned at prompt build time and matched to user requests via trigger keywords. The agent checks skills before improvising.
Download
One-click installer for Windows. Python dependencies are installed automatically on first launch.
macOS & Linux builds coming soon. In the meantime, use the developer setup.
Developer Setup
For contributors and developers who want to modify, extend, or build Substrate from the repository.
Substrate is free for personal use, source-available, and runs entirely on your machine. Your data stays local. Your agent stays yours.