docs/sint-os.mdx at main · sint-ai/docs

title	SINT OS
description	The first secure, Jarvis-style personal AI operating system — agentic, multimodal, and physically safe.
sidebarTitle	SINT OS

SINT OS is what happens when you combine OpenClaw (the agent runtime), SINT Protocol (the governance engine), SINT Avatar (the face), and multimodal AI (the senses) into a single operating system for autonomous agents.

SINT OS is not a separate product — it's the unified stack. Each component already exists and runs independently. SINT OS is the integration layer that makes them work as one system.

Architecture

┌─────────────────────────────────────────────────────────────┐
│                         SINT OS                              │
│                                                              │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌─────────────┐ │
│  │  Avatar   │  │ Console  │  │ Outreach │  │  CMO        │ │
│  │  (Face)   │  │ (Brain)  │  │ (Hands)  │  │ (Content)   │ │
│  │  3D+Voice │  │ 31 mods  │  │ LinkedIn │  │ 18 skills   │ │
│  └────┬──────┘  └────┬─────┘  └────┬─────┘  └─────┬───────┘ │
│       │              │             │               │         │
│       └──────────────┼─────────────┼───────────────┘         │
│                      │             │                          │
│          ┌───────────┴─────────────┴───────────┐             │
│          │     @sint/os-core (Orchestrator)     │             │
│          │  Boot → Govern → React → Evidence    │             │
│          └───────────┬─────────────────────────┘             │
│                      │                                        │
│     ┌────────────────┼────────────────────┐                  │
│     │                │                    │                   │
│  ┌──┴──────────┐  ┌──┴──────────┐  ┌─────┴──────────┐      │
│  │  OpenClaw    │  │  SINT       │  │  Evidence      │      │
│  │  Adapter     │  │  Protocol   │  │  HUD           │      │
│  │  (T0-T3)    │  │  (Gateway)  │  │  (Ledger View) │      │
│  └──┬──────────┘  └──┬──────────┘  └────────────────┘      │
│     │                │                                       │
│     │   ┌────────────┴─────────────────────┐                │
│     │   │     SINT Protocol Core            │                │
│     │   │  • Capability Tokens (Ed25519)    │                │
│     │   │  • Policy Gateway (32 endpoints)  │                │
│     │   │  • Evidence Ledger (SHA-256)       │                │
│     │   │  • 12 Protocol Bridges            │                │
│     │   └───────────────────────────────────┘                │
│     │                                                        │
│  ┌──┴──────────────────────────────────┐                    │
│  │     OpenClaw Runtime                 │                    │
│  │  • WebSocket Gateway (port 18789)    │                    │
│  │  • 20+ Channel Plugins              │                    │
│  │  • MCP Tool Router                   │                    │
│  │  • Session Manager                   │                    │
│  │  • Cron Scheduler                    │                    │
│  │  • Docker Sandbox                    │                    │
│  └──────────────────────────────────────┘                    │
└──────────────────────────────────────────────────────────────┘

The Stack

Layer	Component	What It Does	Repo
Face	SINT Avatar	3D WebGL avatar, ElevenLabs TTS, Conversation Compiler, 18 widget types	`sint-ai/sint-avatars`
Brain	SINT Console	31 features, visual workflow builder, agent orchestration, Web3	`sint-ai/sint-agents`
Hands	SINT Outreach	LinkedIn automation, auto-send engine, sequence engine, A/B testing	`sint-ai/sint-outreach`
Content	CMO Operator	18-skill video→content pipeline, multi-channel publish	`sint-ai/sint-cmo-operator`
Spine	SINT Protocol	Governance: capability tokens, policy gateway, evidence ledger, 12 bridges	`sint-ai/sint-protocol`
OS	OpenClaw	Agent runtime: gateway, channels, MCP, sessions, cron, sandbox	`openclaw/openclaw`

Core Packages

@sint/os-core

The main entrypoint. Boots all components, orchestrates governance, connects avatar reactions to policy events.

import { SintOS } from "@sint/os-core";

const os = new SintOS({
  gatewayUrl: "http://localhost:4100",   // SINT Protocol gateway
  agentId: "my-agent-pubkey",
  openclawWsUrl: "ws://127.0.0.1:18789", // OpenClaw gateway
  avatar: {
    serverUrl: "http://localhost:3005",   // SINT Avatar
  },
  evidenceHud: { enabled: true },
  crossSystemPolicies: DEFAULT_PHYSICAL_POLICIES,
});

await os.boot();

What boot() does:

Connects to SINT Protocol gateway → verifies health
Initializes OpenClaw adapter → maps all tools to T0-T3 tiers
Connects to Avatar server → verifies 3D face is running
Starts Evidence HUD → begins ledger stream
Activates cross-system policy engine

@sint/openclaw-adapter

The governance choke-point. Every OpenClaw action passes through here before execution.

const adapter = os.getAdapter();

// Govern a tool call
const result = await adapter.governToolCall({
  tool: "exec",
  params: { command: "rm -rf /tmp/data" },
  elevated: true,
});
// result.tier === "T3"
// result.outcome === "escalate"
// result.approvalId === "apr-123"

Tier Classification

Every OpenClaw tool, MCP server, and node action is classified into a safety tier:

Tier	Description	OpenClaw Examples	Governance
T0	Observe only	`read`, `web_search`, `web_fetch`, `image`, `pdf`, `memory_search`, `session_status`, `sessions_list`	Auto-approved, no gateway call
T1	Reversible digital	`write`, `edit`	Gateway validates, auto-approved with valid token
T2	Requires governance	`message.send`, `tts`, `image_generate`, `sessions_spawn`, `cron.add`, `exec` (non-elevated)	Gateway validates + may require approval
T3	Physical / irreversible	`exec` (elevated), `canvas.eval`, `nodes.camera_snap`, `nodes.invoke`, `nodes.screen_record`	Gateway validates + human approval required

T0 calls never hit the network — they're approved locally in microseconds. This means governance adds zero latency to read operations.

Cross-System Policies

The key differentiator from basic sandbox. These policies span multiple subsystems:

Policy	When Active	Denied Actions	Why
`no-fs-while-moving`	`robot.moving`	File writes, edits	Prevents controller corruption during motion
`no-exec-while-moving`	`robot.moving`	Shell execution	Prevents control interference
`no-deploy-while-active`	`cmd_vel`	Deploy, restart	Can't restart while velocity commands are active
`no-network-while-armed`	`drone.armed`	Network, exec	Safety critical — no external access while armed

// Activate a system state
adapter.getStateTracker().activate("robot.moving");

// Now file writes are automatically denied
const result = await adapter.governToolCall({
  tool: "write",
  params: { path: "/robot/config.yaml" },
});
// result.allowed === false
// result.reason === "[Cross-System Policy: no-fs-while-moving] ..."

Custom policies are supported:

const os = new SintOS({
  // ...
  crossSystemPolicies: [
    {
      name: "no-reboot-during-surgery",
      whenActive: "patient.connected",
      denyActions: ["system:reboot*", "deploy:*"],
      reason: "Cannot disrupt systems during active patient monitoring",
    },
  ],
});

Avatar Bridge

Connects governance events to visual avatar reactions. When SINT denies an action, the avatar shakes its head and spawns a status widget. When it escalates, the avatar looks surprised and spawns an approval widget.

Governance Event	Avatar Expression	Animation	Widget
T0 approve	`default`	—	—
T1 approve	`default`	`Head-Nod-Yes`	✅ Status (3s)
T2 deny	`thinking`	`Thoughtful-Head-Shake`	🔴 Status (8s)
T3 escalate	`surprised`	`Thinking`	⚠️ Approval action (30s)

Evidence HUD

Real-time viewer of the SHA-256 evidence ledger. Displays a rolling window of governance decisions with chain integrity verification.

const hud = os.getEvidenceHUD();
hud.onEntry((entry) => {
  console.log(`${entry.tier} ${entry.outcome}: ${entry.resource}`);
});

// Verify chain integrity
const { valid, brokenAt } = hud.verifyChainIntegrity();

SINT Avatar — The Face

The avatar is a full 3D experience (React + Three.js + @react-three/fiber) with:

Conversation Compiler

A neural rewriter (gpt-4.1-nano) that sits between the AI agent and the TTS pipeline. It:

Takes raw agent output (markdown, JSON, technical text)
Rewrites it for spoken delivery (contractions, rounding, natural language)
Infers emotion and animation
Spawns contextual UI widgets

Agent output: "Deployed to Railway. Build 47 passed. 3 of 5 tests green."
    ↓ Conversation Compiler
Spoken: "Deploy's live. Build passed, three of five tests green."
Emotion: smile
Animation: Head-Nod-Yes
Widgets: [status: "Deploy" → success, progress: "Tests" → 60%]

Widget System (18 Types)

The avatar spawns contextual widgets during conversation:

Widget	Description
`status`	Success/error/pending indicator
`code`	Syntax-highlighted code block
`metric`	KPI with trend arrow
`progress`	Progress bar with percentage
`list`	Ordered/unordered list
`chart`	Bar, line, or pie chart
`terminal`	Terminal output display
`link`	Clickable link
`table`	Data table with headers
`diff`	Code diff (additions/deletions)
`action`	Actionable button (approve, run, etc.)
`image`	Image with caption
`github`	Live GitHub repo status (PRs, issues, stars)
`dashboard`	Full dashboard with KPIs (live from Paperclip API)
`goals`	Agent goals/objectives
`tasks`	Task list with status
`agents`	Active agents display
`activity`	Activity timeline

How It All Fits Together

Example: "Jarvis, deploy the staging build"

1. Voice input → Qwen3.5-Omni / OpenClaw Voice Wake → text
2. Text → OpenClaw Gateway → SINT agent session
3. Agent decides: tool call "exec" { command: "railway up --environment staging" }
4. @sint/openclaw-adapter classifies → T2 (deploy)
5. Cross-system check → is robot.moving? No → continue
6. SINT Policy Gateway → intercept → check capability token scope
7. Gateway: outcome = "approve" (token has deploy:staging scope)
8. Evidence ledger: logs SHA-256 entry
9. OpenClaw executes the command
10. Result → Conversation Compiler → "Staging deploy is live."
11. Avatar: smile + Head-Nod-Yes + [status: "Staging" → success] widget
12. Evidence HUD: new entry appears in real-time feed

Example: "Jarvis, move the robot 2m forward"

1. Voice → text: "move the robot 2 meters forward"
2. Agent decides: node action "invoke" { command: "move_forward", distance: 2 }
3. @sint/openclaw-adapter classifies → T3 (physical)
4. Cross-system check → all clear
5. SINT Policy Gateway → intercept → T3 requires human approval
6. Gateway: outcome = "escalate", approvalId = "apr-456"
7. Avatar: surprised + Thinking + [action: "Approve 2m forward?"] widget
8. Human clicks "Approve" on widget
9. Gateway resolves approval → "approved"
10. Node action executes: robot moves 2m forward
11. State tracker: activate("robot.moving") → deactivate when done
12. Evidence ledger: full chain — request → approval → execution → completion

Quick Start

# Clone all repos
git clone https://github.com/sint-ai/sint-protocol.git
git clone https://github.com/sint-ai/sint-avatars.git

# Start SINT Protocol gateway
cd sint-protocol && pnpm install && pnpm dev

# Start SINT Avatar
cd sint-avatars && pnpm install && pnpm dev

# SINT OS connects them
import { SintOS } from "@sint/os-core";
const os = new SintOS({
  gatewayUrl: "http://localhost:4100",
  agentId: "your-agent",
  avatar: { serverUrl: "http://localhost:3005" },
  evidenceHud: { enabled: true },
});
await os.boot();

Packages

Package	Description	Tests
`@sint/os-core`	Main entrypoint, lifecycle, orchestration	9
`@sint/openclaw-adapter`	OpenClaw governance middleware, tier classifier, cross-system policies	42
`@sint/integration-langchain`	LangChain callback handler + tool wrapper	14
`@sint/gate-capability-tokens`	Ed25519 capability tokens	—
`@sint/gate-policy-gateway`	32-endpoint policy gateway	—
`@sint/gate-evidence-ledger`	SHA-256 hash chain evidence	—
12 bridges	ROS2, MCP, gRPC, MAVLink, A2A, MQTT, OPC-UA, IoT, OpenRMF, Economy, Swarm, HAL	—
Total	30 packages	1,400+

SINT Protocol governance engine Visual control center System architecture and package map Development roadmap

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Architecture

The Stack

Core Packages

@sint/os-core

@sint/openclaw-adapter

Tier Classification

Cross-System Policies

Avatar Bridge

Evidence HUD

SINT Avatar — The Face

Conversation Compiler

Widget System (18 Types)

How It All Fits Together

Example: "Jarvis, deploy the staging build"

Example: "Jarvis, move the robot 2m forward"

Quick Start

Packages

FilesExpand file tree

sint-os.mdx

Latest commit

History

sint-os.mdx

File metadata and controls

Architecture

The Stack

Core Packages

@sint/os-core

@sint/openclaw-adapter

Tier Classification

Cross-System Policies

Avatar Bridge

Evidence HUD

SINT Avatar — The Face

Conversation Compiler

Widget System (18 Types)

How It All Fits Together

Example: "Jarvis, deploy the staging build"

Example: "Jarvis, move the robot 2m forward"

Quick Start

Packages