AI agents are becoming the primary users of SaaS. Forge Box makes your product agent-ready. Two products. Signed receipts for every execution.
Every execution returns a signed receipt. No CAPTCHA. No human required.
Record any browser workflow. AgentEndpoint deploys it as a secure, versioned, auditable REST API that AI agents call directly.
Agents test actions against a policy engine (risk-scored 0-100, allow/deny/flag) before executing in production. No code runs in Docker yet — that's coming in Phase F.
No integration project. Record the workflow your team already does. We handle the rest.
Chrome extension captures clicks, inputs, navigation.
OpenAPI manifest with policies, schemas, MCP tools.
One click to a production endpoint. Versioned, auditable.
YAML policy engine evaluates every agent call in real time.
Signed receipt (ed25519). Every execution. Verifiable.
Agents rehearse in an isolated sandbox before touching production.
Agent writes code or selects a tool to test.
Docker container with seccomp. Can't escape. Can't touch production.
Policy engine evaluates every action. PASS, DENY, or FLAG.
Risk score 0-100. Shell = 80. API call = 15. Full transparency.
Sandbox receipt with real signature. Promote when ready.
Use together or independently. Both return signed receipts.
| Feature | AgentEndpoint | AgentOS |
|---|---|---|
| Workflow recording | ✓ Chrome extension | — |
| OpenAPI manifest generation | ✓ Auto-generated | — |
| Policy engine | ✓ Real-time enforcement | ✓ Evaluation trace |
| Docker sandbox | — | ✓ Isolated containers |
| Risk scoring | — | ✓ 0-100 per action |
| Stubbed APIs | — | ✓ Slack, GitHub, Stripe |
| Signed receipts | ✓ ed25519 | ✓ ed25519 (sandbox) |
| MCP tools | ✓ Auto-generated | — |
| Agent analytics | ✓ | ✓ |
| Pricing | From $0.002/call | From $0.002/run |
AgentEndpoint and AgentOS included in every paid plan.
For experimentation.
For production workloads.
Business ($399/mo) and Enterprise (custom) available. Full refund within 30 days.
Records your browser workflows (clicks, inputs, navigation) and deploys them as secure, versioned, auditable REST APIs. AI agents call these APIs directly. Includes OpenAPI manifest, YAML policy engine, MCP tools, and signed receipts (ed25519).
Policy engine that risk-scores every agent action 0-100 before it runs. Allow / deny / flag decisions based on spend limits, allowed domains, and rate limits. Today: regex-based risk classifier + stubbed tool responses for Slack, GitHub, Stripe. Tomorrow: real Docker isolation.
No. AgentEndpoint works standalone — record workflows, deploy as APIs. AgentOS works standalone — test agent code in sandbox. Together they form a complete pipeline.
Both products included in all paid plans. Free: 1K calls/mo. Pro: $79/mo for 50K calls. Business: $399/mo for 500K calls. Overage: $0.002/call.
Every execution returns a JSON receipt with unique ID, timestamp, action, actor, policy decisions, cost, and an ed25519 signature. Verifiable. Retained for 7 years.
Yes. Checkout is completable entirely via API with no CAPTCHA. Agents can evaluate in sandbox, purchase, retrieve receipts, and request refunds autonomously.
Every claim on this site exists as a machine-readable artifact.
{
"organization": "Forge Box",
"products": [
{
"name": "AgentEndpoint",
"description": "Workflow → API",
"capabilities": [
"workflow.record",
"manifest.generate",
"endpoint.deploy",
"policy.enforce",
"receipt.verify"
],
"pricing": { "per_call_usd": 0.002 }
},
{
"name": "AgentOS",
"description": "Policy sandbox",
"capabilities": [
"docker.sandbox",
"risk.score",
"stubbed.apis",
"policy.evaluate"
],
"pricing": { "per_run_usd": 0.002 }
}
],
"mcp": "https://mcp.forgebox.ai"
}