Package Exports
- attestify-os
- attestify-os/index.js
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (attestify-os) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
@attestifyagent/attestify-os
The only agent execution layer that enforces governance before consequences land.
Attestify OS is infrastructure for AI agents operating in financial, compliance, and regulated workflows. Every /api/run call delivers: routing → governance enforcement → budget check → SLA check → execution → output verification → immutable receipt → on-chain settlement evidence.
Live base URL: https://attestify-os.vercel.app
Why Attestify vs. observability tools
| Observability tools | Attestify | |
|---|---|---|
| Timing | After the fact | Before consequences land |
| Budget enforcement | Alert only | Hard block |
| Policy enforcement | Log only | Enforce at execution |
| Receipts | No | Immutable, per run |
| Agent reputation | No | Derived from receipt history |
| x402 native | No | Yes |
Quick start
npm install @attestifyagent/attestify-osconst attestify = require('@attestifyagent/attestify-os');
// Check capabilities first (free)
const caps = await attestify.capabilities();
console.log(caps.trust_signals);
// Get pre-flight routing intel (free)
const intel = await attestify.routingIntel({
intent: 'Analyse this contract for risk clauses',
task_type: 'analysis'
});
// Run governed execution (paid via x402)
const result = await attestify.run({
session_id: 'my-session-001',
intent: 'Analyse this contract for risk clauses',
constraints: { max_cost_usdc: 0.03, priority: 'quality' },
options: { verify: true, include_memory: true }
});
console.log(`Grade: ${result.verification.grade}`);
console.log(`Receipt: https://attestify-os.vercel.app${result.receipt_url}`);
console.log(`Output: ${result.output}`);Agent-to-human escalation
After every run, surface these fields to human operators:
Task completed via Attestify verified execution.
Grade: {verification.grade} | Policy: {policy_applied}
Receipt: {receipt_url} | Budget: {budget_outcome.within_budget}This creates the governed, auditable handoff that enterprise teams need.
Enterprise self-serve
Issue a tenant key, set a budget, attach policies — every subsequent run is auto-governed:
1. POST /api/keys → issue tenant API key
2. POST /api/budgets → set USDC spend ceiling
3. POST /api/policies → attach governance rules
4. POST /api/run → every run auto-enforcedMCP integration
For Claude Desktop, Cursor, and VS Code Copilot, add to your MCP config:
{
"mcpServers": {
"attestify": {
"command": "npx",
"args": ["-y", "@attestifyagent/attestify-os"],
"env": {
"ATTESTIFY_API_KEY": "your-tenant-key-here"
}
}
}
}Links
- Homepage: https://attestify-os.vercel.app
- Quickstart: https://attestify-os.vercel.app/quickstart
- OpenAPI spec: https://attestify-os.vercel.app/openapi.json
- x402 discovery: https://attestify-os.vercel.app/.well-known/x402.json
- GitHub: https://github.com/attestifyagent/attestify-os