OpenGuardrails
openguardrails.com
Spec sheet
- Purpose
- OpenGuardrails AIRS tests, inspects and protects AI agents at runtime.Read 4 Oct 2026 · openguardrails.com
- Integrations
- The plugin index lists Higress, DeepSeek Harness, litellm, Claude Code, Codex, opencode, OpenClaw, Hermes, LangGraph and a mitmproxy gateway example.Read 4 Oct 2026 · openguardrails.com
- Support
- The Enterprise plan includes support with an SLA.Read 4 Oct 2026 · openguardrails.com
- Headquarters
- Sheridan, Wyoming, United StatesRead 28 Sep 2026 · openguardrails.com
- Console
- The console includes a live monitor, agent and session explorer, findings triage, policies, a playground and API keys.Read 4 Oct 2026 · openguardrails.com
- Integration method
- There is no SDK; integrations use the API directly, with two POSTs per model call in the documented recipe.Read 4 Oct 2026 · openguardrails.com
- Open protocol
- The OGR protocol is an open Apache-2.0 specification with published JSON Schemas; the runtime product is commercial.Read 4 Oct 2026 · openguardrails.com
- Operational limit
- The default rate limit is 600 requests per minute per API key.Read 4 Oct 2026 · openguardrails.com
- Private deployment
- Private deployments run on customer Kubernetes or VMs with customer datastores and a model gateway hosted in the customer environment.Read 4 Oct 2026 · openguardrails.com
- Runtime checks
- It evaluates tool calls, resources and accounts before the model sees a request and checks responses before the agent acts on them.Read 4 Oct 2026 · openguardrails.com
- Security and privacy
- Starter masks secrets on the customer host before a request leaves it and restores them only into tool arguments.Read 4 Oct 2026 · openguardrails.com
- Service behavior
- When the runtime is unreachable, integrations use local preconfigured fail policies that default to open unless categories are explicitly set to closed.Read 4 Oct 2026 · openguardrails.com
- Verdicts
- The runtime returns allow, block or redact decisions, along with findings and redaction spans.Read 4 Oct 2026 · openguardrails.com
Plans and prices
Starter $10 a month Billed monthly; cancel anytime. Secret masking on your host · Secret ledger · Detects secrets, PII, dangerous commands and credential files Read 4 Oct 2026 · openguardrails.com
Pro $20 a month Billed monthly; cancel anytime. Includes Starter · Model judges on every tool call, prompt and reply · Sized for one agent in normal use · Four policy templates Read 4 Oct 2026 · openguardrails.com
Max $100 a month Billed monthly; cancel anytime. From $100/month · $100/month for 5x or $200/month for 20x · Multimodal storage and display · Priority evaluation Read 4 Oct 2026 · openguardrails.com
Enterprise Priced on request Annual license; priced on fleet size. Private deployment · Events stay in your infrastructure · Enterprise SSO or admin provisioning · Support with an SLA Read 4 Oct 2026 · openguardrails.com
Where Specifiction places it
- AI Guardrail Software#13 of 237.4