OPERATING SYSTEM FOR AUTONOMOUS AGENTS
TRANSPARENT CLEARINGHOUSE PRICING

PREDICTABLE RAILS. SCALE SAFELY.

Atomic spend limits, per-agent machine keys, and tamper-evident audit logs.

MONTHLYANNUALSAVE 20%
COMMUNITY & DEV
$0/month

FOREVER FREE · MIT LICENSE

Ideal for individual developers building local prototypes and testing MCP tool integrations.

INCLUDED CAPABILITIES:

  • Up to 3 active agent runtimes
  • Local MCP tool registry
  • In-memory event audit log
  • Docker Compose self-hosting
  • Community Discord support
TEAM & GROWTHPOPULAR
$49/month

PER WORKSPACE / MONTH

For engineering teams deploying autonomous production agents with hard financial rails.

INCLUDED CAPABILITIES:

  • Up to 25 active agent runtimes
  • Row-lock budget clearinghouse
  • Model Context Protocol sandboxing
  • Cryptographic SHA-256 audit ledger
  • Real-time SSE event telemetry
  • Priority email & developer support
ENTERPRISE
CUSTOM

CUSTOM ANNUAL CONTRACT

For organizations requiring dedicated cloud VPC clusters, on-prem runtimes, and custom SLAs.

INCLUDED CAPABILITIES:

  • Unlimited agent runtimes
  • Dedicated VPC or on-prem deployment
  • Hardware Security Module (HSM) keys
  • Custom security ring policies
  • Dedicated solutions architect
  • 99.95% availability SLA guarantee
ARCHITECTURE & BILLING

FREQUENTLY ANSWERED SPECS

HOW DOES THE ROW-LOCK CLEARINGHOUSE PREVENT SPEND RUNAWAYS?

Every tool invocation, embedding query, and LLM inference executes inside a PostgreSQL row-locked transaction. If an agent hits its daily or per-run limit, the transaction aborts instantly before executing.

CAN WE SELF-HOST AGENTOS ON OUR OWN INFRASTRUCTURE?

Yes. The Community edition is MIT licensed and runs via Docker Compose with standard PostgreSQL and Redis. No external cloud dependencies required.

HOW DOES MCP SANDBOXING PROTECT INTERNAL NETWORKS?

AgentOS compiles tool schemas strictly according to the Model Context Protocol. Outbound tool calls pass through an egress proxy that blocks RFC 1918 private subnets and metadata endpoints.

CAN WE RETRIEVE THE CRYPTOGRAPHIC AUDIT LOGS PROGRAMMATICALLY?

Yes. All audit entries are accessible via the REST API and Server-Sent Events feed. Every entry includes the SHA-256 hash of its predecessor, enabling offline verification.