Agent Reliability as a Service

Stop shipping agents that double-charge your customers.

AgentRaaS sits between your AI agents and every real-world action — guaranteeing exactly-once execution, proven under real concurrent load, not just claimed. Self-hosted or cloud.

✓ Webhook, SDK-style REST, or native MCP ✓ No vendor lock-in ✓ Self-hosted is unlimited and free, forever
EXECUTION LEDGER live — last 24h, this deployment
actions verified
duplicates caught
avg per action
01 — BUILT FOR THE SELF-HOSTED AI STACK

Not another SaaS gateway. A drop-in layer for the stack you already run.

Thousands of teams run n8n, Flowise, Langflow, Dify, Ollama, and LocalAI on their own Docker infrastructure — to cut SaaS fees, and to stay inside GDPR / EU AI Act data-residency rules. AgentRaaS is built to sit inside that stack, not replace it: one more Docker Compose service, zero data leaving infrastructure you control.

🔒 Air-gapped capable 🇪🇺 GDPR / EU AI Act friendly 🐳 One Docker Compose service 💸 No per-seat SaaS fees
n8n Flowise Langflow Dify Ollama LocalAI LangChain AutoGen CrewAI Claude Desktop Cursor Make Zapier
02 — THE PROBLEM

Your agent didn't fail. The network did — and nobody told it.

Payment retry

Your n8n workflow hits Stripe. It times out. n8n retries.

Result: the customer is charged twice, and you find out from a support ticket, not a log.

CRM duplicate

Your agent calls HubSpot to create a contact. The response is lost. It retries.

Result: two duplicate contacts, a messier pipeline, and a sales team that stops trusting the data.

Client update

Your agent sends a client a project status update. The confirmation times out. It retries.

Result: the client gets the same update twice — and starts wondering what else is off.

Team notification

Your agent posts an approval request to Slack. The webhook times out. It retries.

Result: your team approves the same request twice, or gets paged twice for one incident.

03 — HOW AGENTRAAS FIXES IT

A dedup slot claimed atomically, before anything real happens.

1

Your agent sends the request to AgentRaaS instead of the API directly.

2

AgentRaaS atomically claims a dedup slot for that exact request in Redis.

3

First call: forwarded to the real API, the result gets cached.

4

Retry or duplicate: the cached result comes back — never a second real execution.

04 — MCP-NATIVE, NOT JUST HTTP

MCP is how modern agents call tools now. AgentRaaS speaks it natively.

Model Context Protocol is the standard Claude Desktop, Cursor, and agent frameworks like LangChain, AutoGen, and CrewAI use to invoke tools. A stalled tool call gets retried just like a stalled HTTP request — same double-execution risk, different protocol. AgentRaaS's MCP gateway is a JSON-RPC proxy that applies the exact same atomic dedup guarantee to every tool call, not just webhooks.

WEBHOOK / HTTP

Point any client at us

n8n, Make, Zapier, or raw curl — change the target URL, nothing else.

POST /proxy/:service/:action
SDK-STYLE REST

No SDK package required

A clean per-service REST shape for scripts and internal tools.

POST /v1/sdk/:service/:action
NATIVE MCP

JSON-RPC tool calls

Claude Desktop, Cursor, LangChain, AutoGen, CrewAI — any MCP client.

POST /mcp
MCP Idempotency Guard — /mcp
# agent calls a tool via MCP
POST /mcp
{"jsonrpc":"2.0","id":"call_82f1","method":"tools/call",
 "params":{"name":"stripe.createCharge",
           "arguments":{"amount":4200,"customer":"cus_9f2k"}}}

→ 200 OK  // first call — forwarded, result cached
{"result":{"status":"success","charge_id":"ch_1N..."}}

# network stalls — agent retries the identical call 400ms later

→ 200 OK  // dedup slot already claimed — cached result, zero re-execution
{"result":{"status":"success","charge_id":"ch_1N...",
           "deduplicated":true}}
05 — WHERE IT'S USED

Any agent. Any workflow. Client-facing or internal.

AgentRaaS doesn't care what your agent is for — only that when it acts, it acts exactly once. If it can call an API, AgentRaaS can protect it.

💬

Customer support agents

Resolve tickets, send replies, trigger refunds — without a retry turning into two replies or two refunds.

📈

Sales & CRM agents

Log leads, update deals, enrich contacts in HubSpot or Salesforce — once per real event, not once per retry.

📅

Scheduling & client updates

Book meetings, send confirmations, post status updates to a client — exactly the number of times you meant to.

🔔

Internal team & ops agents

Post to Slack directly, or Microsoft Teams via Custom Actions — trigger approvals, hand off work between systems, SSRF-guarded.

🛒

Commerce & fulfillment agents

Update inventory, create orders, notify shipping — protected the same way whether it's Shopify or your own warehouse API.

Whatever you're building

Not on the curated list? Register it as a Custom Action in minutes — same dedup, same audit trail, same protection.

🏢

AI automation agencies & freelancers

Building client workflows in n8n or Make? Drop AgentRaaS in front of every client's Stripe, CRM, or messaging API so one retry storm doesn't double-charge a client account. The Agency plan adds a white-label dashboard per client tenant.

06 — WHAT YOU GET

Not just dedup. A full trust layer for autonomous action.

Every piece your agents need to take real actions safely, out of the box.

Exactly-once execution

Proven under real concurrent load with an automated test suite — not just a claim.

🔑

Self-serve credentials

Add your own Stripe, Twilio, or any provider's keys — encrypted at rest, no server access needed.

Custom Actions

Not limited to the curated list — register any endpoint, SSRF-guarded, and agents can call it too.

MCP native

A JSON-RPC gateway for Claude Desktop, Cursor, and any MCP client — every call protected the same way.

Circuit breaker

Stop hammering a broken upstream service. Trips open, recovers automatically.

Full audit trail

Every action logged — who, what, when, status, duration. Searchable dashboard, CSV export.

07 — INTEGRATIONS

Works with what you already use.

Stripe Twilio HubSpot Calendly Shopify Zoho Razorpay WhatsApp Zapier Make Adyen Mollie Airwallex Xendit PayPal Salesforce Slack Klarna Paystack GoCardless Opn Payments Microsoft Teams* + any endpoint

* via Custom Actions — not a pre-built connector, but reachable the same way any endpoint is: register it once, agents call it by name from then on.

Pricing that doesn't punish you for self-hosting.

Open-core, fair-code licensed — Community is free and self-hosted only. Agency and Enterprise run either cloud-hosted or self-hosted.

Agency

Cloud-hosted or self-hosted — manage client tenants under your own brand
$149 /month
Unlimited self-hosted · 50,000/month on Cloud
  • Up to 10 client tenants
  • Multi-tenant, white-label dashboard
  • Outbound rate smoothing (token bucket)
  • Priority email support
Get started →

Enterprise

Cloud-hosted or self-hosted/on-prem — production, multi-team agent fleets
Custom from $499/mo
Unlimited actions & workspaces, either way
  • Active-active HA clustering
  • Inbound HMAC verification (10+ providers)
  • PII masking & DLP redaction engine
  • SAML/OIDC SSO, RBAC & SOC2-ready audit export
Contact sales →

Full terms in LICENSE.md — a fair-code license modeled on n8n's Sustainable Use License. Enterprise features (src/ee/) are source-available under a separate commercial license.

Questions people actually ask

The short, honest answers — full detail is in the docs and LICENSE.md.

Is self-hosted really unlimited, on every tier?

Yes. Community, Agency, and Enterprise are all unlimited actions/month when you run them on your own infrastructure — no cap, no metering, no phone-home check. It's a term of LICENSE.md, not a "soft" limit we quietly enforce. The only metered tier is the free AgentRaaS Cloud account (500 actions/month) — because that one runs on our infrastructure, not yours.

What's the difference between Agency and Enterprise?

Agency ($149/mo) adds multi-tenancy and white-label branding — built for agencies managing multiple client workspaces under one dashboard. Enterprise (custom pricing) adds everything needed for a production multi-team deployment: active-active HA clustering, inbound HMAC verification, PII/DLP redaction, and SAML/OIDC SSO with RBAC. Both run cloud-hosted or self-hosted.

Is my data safe if I self-host?

Self-hosted means your audit log, credentials, and traffic never leave infrastructure you control — we don't see any of it. Stored credentials are encrypted at rest (AES-256-GCM), and the Enterprise tier adds PII/DLP redaction before anything touches the audit log, plus tamper-evident, SIEM-exportable logging for compliance-sensitive teams.

Do you support n8n, Make, or Zapier?

Yes — AgentRaaS is a proxy, not an SDK, so no-code tools work the same way code does: point the HTTP Request node at your AgentRaaS URL instead of the API directly. No custom node install required for any of them.

What happens if my agent retries a request?

AgentRaaS claims an atomic dedup slot in Redis before anything real happens. The first call gets forwarded and its result cached; any retry or duplicate — even concurrent ones — gets the cached result back instead of a second real execution. This is tested under real concurrent load, not just claimed (see npm test).

Is this open source?

The core engine (src/core/ — payload dedup, MCP gateway, dashboard) is MIT/Apache-2.0. Enterprise features (src/ee/ — SSO, HMAC, DLP, distributed rate limiting) are source-available under a separate commercial license. See LICENSE.md for the exact terms.