Give it a goal. Get finished work.
Sophon reasons through complex requests, remembers people and projects across every conversation, and runs real workflows — the same assistant on Slack, mobile, and the dashboard. Self-hosted and model-agnostic, enterprise-ready when you are.
The intelligence core
One brain behind every answer.
Memory, reasoning, and orchestration working as one intelligence core — so Sophon recalls what matters, thinks through the steps, and carries them out. Channels are how you talk to it; the Brain is what actually thinks.
What the mind can do
Four faculties, one assistant.
Everything Sophon does flows from the same core — here's what that looks like in practice.
It remembers — and keeps its memory clean.
A self-maintaining graph of the people, projects, and dates in your world. New facts supersede old ones, everything stays searchable, and every entry is yours to inspect.
- Entity graph of people, projects, places, and dates
- Temporal supersession keeps facts current
- Hybrid semantic + keyword search
- User- and agent-scoped, fully inspectable
Automations you can see.
Drag-and-drop a workflow, or just describe it and let Sophon draft it. Triggers, logic, approvals, sub-workflows — 20+ node types on an infinite canvas.
- 8 trigger types, 20+ node types
- AI-authored from natural language
- Human approval gates for sensitive steps
- Versioning and sub-workflows
One request. Many steps. Zero micromanagement.
Sophon plans the work, runs independent steps in parallel, checks with you on anything sensitive, and recovers when a step fails — while you watch in real time.
- 12-stage middleware pipeline per message
- Parallel execution of independent steps
- Smart retries and cascades on failure
- Approval gates on anything sensitive
When one opinion isn't enough.
Put three agents with different perspectives in a room, let them argue, and get a judge's structured verdict — a decision, not a decision tree.
- Three agents, distinct perspectives
- A judge renders a structured verdict
- Streams live, end to end
Ship it — the upside is real.
Not until we cover the edge cases.
Phase it: pilot, then roll out.
Pilot with two teams, then decide on the full rollout.
The rest of the platform
Everything else you'd expect — and then some.
A modular monolith built for personal use, professional workflows, and enterprise scale.
Agent Runtime
Multi-agent architecture with LLM-based routing, tool pipelines, and scheduled heartbeat checklists that work unattended. Any model provider, switchable per session.
Skills & Plugins
Marketplace skills with sandboxed execution and self-authoring — plus out-of-process plugins that add custom channels and document formats to the core.
Security & Control
Approval gates, an audited credential firewall, and a published MITRE ATLAS threat model. Nothing happens without your say.
Code Sandbox
Secure code execution in isolated containers. C# .NET 10 and Python 3.13 with resource limits and network isolation.
Native Mobile
Approve actions, check in, and chat from a native app in your pocket.
10 Channels
One universal message format across WhatsApp, Telegram, Slack, Discord, Teams, Email, Signal, Matrix, SMS, and WebChat.
Up and running in minutes
For one, or for all
Personal enough for one. Accountable enough for a company.
The same platform, one config change apart.
For you
Your own assistant, on your own hardware — running the moment you are.
- Free forever on the Personal tier
- Self-host with one Docker command
- Bring any model — Claude, GPT, or local
- Your data never leaves your machine
For your organization
The assistant your security team will actually approve — on your infrastructure, under your controls.
- SSO / OIDC / SAML and RBAC
- Audit logging and multi-tenancy
- Kubernetes + Helm, Vault-backed secrets
- Dedicated support and custom SLA
Your keys never reach the model.
Every sensitive action passes an approval gate, and credentials live behind a firewall the model can use but never see. Timeout means reject — silence is never consent.
See the security modelChannels
Workflow node types
Trigger types
Pipeline stages
Trusted by design
Run on your terms. Built to be trusted.
Self-hosted from day one, model-agnostic by design, and accountable end to end. Join the community, browse the marketplace, and follow every release.
Morning briefing
Pulls your calendar and inbox in parallel, drafts a briefing, and asks before it sends.
Inbox triage
Reads new mail, flags what's urgent, and files the rest — on a schedule you set once.
Release deck
Give it a topic and three competitors; it researches, positions, and returns a draft.
Your assistant is one command away.
Launch with Docker Compose, connect a model, add a channel. The Personal tier is free, forever.