Live · Available today

For Platform & MLOps teams running AI at scale

Run Sgraal at any scale.
Any latency budget.

Three deployment paths. Plugin system. Autonomous healing. 30-day degradation forecast. Built for the SREs who get paged at 3am.

Sgraal already runs in production with 15ms p50, 99.95% uptime, and zero-dep edge mode for air-gapped deployments.

Three deployment modes

Pick the deployment that fits your topology.

Hosted for most teams. Self-hosted for regulated sectors. Edge mode for air-gapped, classified, or sub-millisecond latency budgets.

cloud

Hosted

sgraal.com · default

~15ms p50 latency. Full 87-module engine, fleet vaccine corpus, per-tenant calibration, Q-learning per-domain. No infra to manage.

Quickstart

from sgraal import SgraalClient
client = SgraalClient("sg_live_...")
result = client.preflight(memory_state, domain="fintech")
See pricing →
dns

Self-hosted

Docker / Helm · on-prem

Run Sgraal in your VPC. Docker image + Helm chart. Same engine, same API surface. Your tenant calibration stays inside your network. Enterprise tier.

Quickstart

# Helm
helm repo add sgraal https://charts.sgraal.com
helm install sgraal sgraal/sgraal \
  --set apiKey=sg_live_... \
  --set sgraalConfig.path=/secrets/cfg.json
Request Helm chart →
memory

Edge mode

in-process · zero-dep · sub-ms

Runs inside your Python process. Zero dependencies — no numpy, no requests. For air-gapped, classified envs, or trading desks that can't take ~15ms. Subprocess-isolated tests prove zero network leak.

Quickstart

from sgraal.edge import edge_preflight
result = edge_preflight(
    memory_state, domain="fintech")
# < 1ms p99, no network
See the cut line →
Platform features

Built for the SREs who run AI in production.

extension

Plugin system

Live

Per-tenant isolation, registry-only loading, escalate-only security monotonicity. Install custom security rules that can downgrade USE_MEMORY → BLOCK but never the reverse.

webhook

Webhook dispatch

Live

DNS-pinned dispatch to prevent DNS rebinding. SSRF-safe URL validation. Built-in formatters for Slack, PagerDuty, OpsGenie. Retries with exponential backoff + dead-letter queue.

monitor_heart

Behavioral profile per agent

Live

Call frequency trend, action-type escalation pattern, domain switching. Detect compromised or drifting agents before they cause incidents. Surfaced via /v1/agent/{id}/behavioral-profile.

psychology

Q-learning per-domain

Live

Closed-loop reinforcement learning from real outcomes. Report /v1/outcome after each agent action; Sgraal adapts its policy per-domain. Tenant-isolated Q-tables.

trending_down

30-day degradation forecast

Live

/v1/predict/degradation returns the projected day a given memory state will cross the BLOCK threshold. Schedule refresh ahead of customer impact.

bolt

Edge mode (sub-ms p99)

Live

Zero-dep in-process scoring with per-type thresholds (identity, policy, semantic, preference, episodic, shared_workflow, tool_state). Sufficient for many production deployments without calling sgraal.com. For workloads requiring fleet-wide vaccine signatures or cross-tenant analytics, use the hosted or self-hosted mode.

tune

Sgraal Studio

Concept · Coming

Web UI for tuning your scoring weights, Weibull λ values, and detection thresholds. Live A/B replay against your own 30-day history. Today: edit SGRAAL_SCORING_CONFIG env var directly.

Be first to know →
history

Memory Time Machine

Concept · Coming

Deterministic replay of past decisions with counterfactual branching. "If T-3 we had healed memory X, would T-2 decision have been different?" Git bisect for AI cognition.

Be first to know →
Observability

Live monitoring out of the box.

stream SSE streaming

/v1/preflight/stream emits 23 events across 4 phases (15 scoring module completions + 6 detection layer states + invariant check + final decision). Tap into it for live dashboards or live debugging.

curl -N https://api.sgraal.com/v1/preflight/stream \
  -H "Authorization: Bearer sg_live_..." \
  -d @memory.json

admin_panel_settings Admin endpoints

/v1/admin/endpoints returns the full endpoint inventory; /v1/admin/dlq exposes the dead-letter queue for failed webhook deliveries. Both gated by SGRAAL_ADMIN_TOKEN.

Returns 404 (not 401) if the admin token is not set on the server — prevents endpoint enumeration.

monitoring Prometheus / metrics

/metrics endpoint gated by SGRAAL_METRICS_TOKEN. Exposes per-tenant decision counters, latency histograms, circuit-breaker state, fleet vaccine propagation rate.

receipt_long Tamper-proof audit log

SHA256-chained decision log per tenant. Export via /v1/audit-log/export in CEF or LEEF for Splunk, Datadog, Elastic.

Three modes. One engine. Your stack.

15ms p50 hosted. Sub-ms p99 edge. Air-gapped self-host. Same wire format, same decision contract.