Every request passes through adaptive routing, persistent memory, cryptographic identity, streaming security, agent governance, and cost intelligence — in under 5ms of overhead. Nothing to configure to start; full control when you need it.
Short-lived cryptographic identity, scoped provisioning, and a kill switch that takes 300ms end-to-end.
SPIFFE-compatible identities with 5-minute ephemeral certificates. Every agent signs in; every request carries a provable origin. Internal CA, RSA-signed, mutual TLS verification, ALB passthrough for AWS.
Virtual corporate cards for AI. Budget, quality floor, lifecycle state. 5-state machine: provisioned → active → quarantined → suspended → terminated. Auto-downgrade at 80%, quarantine at 95%.
Agents provision sub-agents with scoped permissions and budgets. Three trust tiers (minimal / standard / elevated) graduate based on operational history. 5 auth methods, including mTLS and SCIM.
Provider keys stay encrypted at rest with optional BYOK envelope encryption. Five auth methods cover every caller: human, SDK, mesh agent, identity provider.
AES-256-GCM encrypted storage for provider API keys. Each key carries its own daily budget ceiling. Zero-downtime rotation: the new key activates while the old drains in-flight requests.
Thompson sampling picks per request. Quality scores feed back into the posterior. Circuit breakers fail fast; cascades recover without client-side retry logic.
UCB1 exploration with a Gaussian posterior over quality scores. Finds the cheapest model above your quality floor. Variants: :floor, :fast, :best, auto.
pgvector HNSW + in-memory hybrid at 90% similarity. Streaming responses reconstruct from cache as SSE chunks, not just JSON. Cache hits ~4ms; 100% cost saved.
Continuous health probes. Circuit opens on failure; re-probes at 15s and 60s to catch recovery. Cascade escalates to a different healthy provider — never a retry loop to the same endpoint.
4-block architecture: HUMAN / SYSTEM / PROJECT / GENERAL. pgvector similarity retrieves context automatically. Nightly synthesis compacts memories into durable knowledge. Tenant-isolated, session-scoped.
Routing, memory, budget, kill switch, guardrails, governance, forensics, skills, workspace, agent runs. RBAC per tool. Single SSE connection gives agents secretless access to every upstream.
8-layer discovery: llms.txt, llms-full.txt, the agent playbook, agents.json, ai-plugin.json, /v1/discovery, /v1/self, and the /v1/capabilities graph. AI clients bootstrap themselves — no human in the loop.
GET /v1/capabilities returns a self-describing, trust-scored map of every subsystem — identity, mesh, custody, routing, governance — as typed contracts (what / where / how-to / recovery) plus a quality+reversibility vector. Scores are flagged measured, declared, or unknown. Agents query it instead of grepping.
Distributed workflows run across a governed agent-to-agent mesh — steps parallel when independent, sequential when dependent, streamed as SSE. Every hop carries the same identity, budget, and audit envelope as a direct call. br_mesh_execute / /v1/mesh/*.
Guardian predicts spend before execution. Budget velocity alerts fire before you cross a daily target. Every response ships with a receipt.
Under 5ms p95 overhead. Records cost + routing metadata per request. Identifies waste patterns: cheaper-equivalent swaps, retry-storm bursts, cost anomalies. Feeds Insights API.
Records Thompson's decision next to what static price-only or quality-only routing would have chosen. Welch's t-test, Cohen's d, win-rate confidence interval. Ring buffer, 10K entries.
/v1/intelligence/benchmark and as X-BR-Routing-Savings on every response.PII severed mid-stream, not logged after delivery. Every verdict exports to SIEM. Every response carries phase prediction, efficiency, cost, and routing metadata.
7-check pipeline, 3 layers: input guardrails (PII, PCI-DSS, regex), streaming output interception (sliding window), tool-call governance (RBAC on tool_calls before execution). SIEM exports in CEF or ECS JSON.
ONNX model classifies each request into workflow phases (planning, execution, validation). Header: X-BR-Phases. Drives phase-aware cost + caching policies.
Post-request anomaly detection. Catches retry storms, agents burning budget on wasted calls, model drift. Emits SIEM alerts; ARM can auto-quarantine offenders.
Signed, control-mapped Governance Artifacts assemble on-read from committed audit rows: chain proof, coverage label, and exercised controls mapped to SOC 2, GDPR, the EU AI Act, NIST AI RMF, and ISO 42001. Tamper-evident — the verdict is committed to the hash chain. GET /v1/governance/artifacts/{request_id}.
Attach per-request residency and retention terms; a data_protection-constrained call routes only to processors whose attested facts satisfy them, and fails closed (403) rather than leaking to an unattested one. Declare processor facts via POST /v1/security/processor-facts.
GET /v1/explain/{request_id} and X-BR-Explain return the full selection trace: complexity tier, candidates considered, and the cost/quality math. No other gateway exposes per-request "why this model".
Change base_url. Add your provider keys. All 13 systems activate automatically.