Runtime agnostic
Cloud, edge, container, or on-prem process — instrumentation follows the agent, not a single host or orchestrator. Governance sees what the agent is doing now.
Developers
Build agents. Emit signals the control plane trusts.
Instrument once. Govern at runtime. PUVINoise™ brings telemetry and behaviour signals into a multi-tenant control plane — so operators cut MTTR instead of guessing from stderr.
SDK
A thoughtful SDK that gets out of your way
TypeScript-native, framework-agnostic, and zero-config by default. Start agent governance without rewriting your stack.
TypeScript native
Full type safety with auto-generated types.
Framework agnostic
LangChain, CrewAI, AutoGen, LangGraph, and more.
Zero friction
Sensible defaults — instrument and see signal in minutes.
Runs anywhere
Cloud, edge, or on-prem — wherever your agents run.
# Install the PUVINoise SDKnpm install @puvinoise/sdkAdoption without rewrites
Runtime, framework, and provider agnostic — zero friction to govern
Agent stacks change. Vendors change. What must not change is your ability to observe, decide, and recover while agents are live. PUVINoise attaches at runtime so governance starts without a platform migration.
Framework agnostic
LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, and custom runtimes. Adapters and OTel paths meet you where the agent already runs.
Provider agnostic
Model and cloud vendors stay your choice. PUVINoise does not lock you to one LLM, region, or hosting SKU to get signal, policy, and recovery.
Zero-friction onboarding
Install the SDK, emit lifecycle signals, verify in Command Centre. No fleet rewrite, no new agent framework, no months of platform plumbing before governance starts.
Why doing it all at runtime is the northstar
MTTR is the key — and MTTR only moves when detection, policy, and recovery share the live path.
Build-time reviews and static configs cannot see tool failures, policy skips, model drift, or cascading retries as they happen. Runtime is where blast radius grows and where minutes of delay become hours of customer impact. PUVINoise puts instrumentation, behaviour intelligence, governed controls, and recovery on the same runtime path — so operators diagnose with correlated evidence and remediate under policy instead of rebuilding dashboards after every Runtime Case. That is the MTTR northstar: shorten time-to-detect, time-to-decide, and time-to-recover without forcing teams onto a single framework or provider.
Faster time-to-detect: live behaviour signals, not log archaeology
Faster time-to-decide: correlated execution, policy, and proof in one control plane
Faster time-to-recover: governed remediation on the path agents already run
Lower adoption cost: agnostic attach means governance starts this sprint, not next platform program
Quickstart: instrument, verify, operate
Install and configure
Add the PUVINoise agent SDK to your runtime. Configure tenant and environment identifiers per your platform team's standards.
Emit telemetry & signals
Instrument key lifecycle events: tool invocations, policy checkpoints, errors, and behaviour markers your organization defines.
Verify in Command Centre
Confirm signals appear in operational views. Validate correlation IDs and execution context before promoting to broader fleets.
Hand off to operators
Once signals are trusted, SRE and agent ops use behaviour intelligence and Runtime Case workflows — MTTR-minded recovery without bespoke dashboards.
Developer surfaces
Everything you need to integrate
Meet your fleet where it runs — SDKs, a CLI, a typed API, and open standards you already use.
SDK
Typed instrumentation for agent lifecycles, tool calls, and behaviour markers with minimal boilerplate.
Open SDK docs →CLI
Scaffold, validate instrumentation, and inspect signal flow locally before you ship to production.
API
A versioned, documented API for querying signals, Runtime Cases, and fleet state programmatically.
OpenTelemetry
Bring existing OTel traces and metrics — PUVINoise enriches them with behaviour context.
Telemetry contract →Sidecar
A drop-in sidecar for runtimes where in-process instrumentation isn't an option.
Framework support
First-class adapters for LangChain, LangGraph, CrewAI, AutoGen, and LlamaIndex.
Architecture
From instrumentation to intelligence
Your instrumented agents emit signals into the tenant-scoped control plane, where the behaviour intelligence pipeline correlates, detects, and feeds governed recovery — a single runtime path from SDK to MTTR-minded outcome.
Tenant boundary
SDK
Ingest
Control Plane
Behaviour Intelligence
Prediction
Recovery
Legend: — tenant boundary · → data flow
Instrumentation layer — not a replacement for your stack
The SDK complements your existing frameworks and deployment model. We document patterns; you retain ownership of agent logic and infrastructure choices — because MTTR improves when governance attaches, not when you migrate.
Open, versioned documentation
Examples that reflect production concerns: tenancy, errors, retries
No requirement to migrate models, frameworks, or hosts to adopt instrumentation
Runtime-, framework-, and provider-neutral by design
Zero-friction path from install → signal → Command Centre → governed recovery
Answers
Developer questions, answered directly
Factual answers for engineers instrumenting agents — aligned with the SDK and control plane, not marketing filler.
How do I start agent governance with zero friction?
Install the PUVINoise SDK, emit lifecycle and behaviour signals, and verify ingest in Command Centre. You do not need to rewrite your agent framework or change model providers to start.
Is the SDK runtime, framework, and provider agnostic?
Yes. Instrumentation follows the agent process across cloud, edge, and on-prem runtimes, with adapters and OpenTelemetry paths for common frameworks and vendor-neutral model stacks.
Why instrument at runtime instead of only at build time?
Build-time reviews cannot see live tool failures or cascading retries. Runtime instrumentation feeds detection, policy, and recovery on the path agents already run — the path that moves MTTR.
Ready to start runtime governance?
Instrument in minutes, then talk to developer relations about fleet topology and MTTR outcomes.