Platform Engineers

Define once.
Trust everywhere.

Repeatable AI SRE workflows that scale across your org—same config, same outcome, every time. AURA handles the 80% so your team can focus on the 20% that matters.

Stop rebuilding the same agent scaffolding every time

Platform teams are tasked with productionizing AI for other teams to consume. That means common standards, safe defaults, and integrations with existing model and tool infrastructure. The hard part isn't the idea—it's making it repeatable enough to scale.

AURA is the open-source agent harness built for this job. Define agents in a TOML manifest like a Kubernetes config. AURA ships the assembled solution —batteries included, production-hardened—so your teams aren't rebuilding scaffolding from scratch every quarter.

[llm]
model = "gpt-5.2"

[agent]
name = "Multi-Worker Orchestrator"

[orchestration.worker.sre]
description = "Incident analysis worker"

[mcp.servers.mezmo]
description = "Mezmo MCP server"

[mcp.servers.datadog]
description = "Datadog MCP server"

[mcp.servers.pagerduty]
description = "PagerDuty MCP server"

[[vector_stores]]
...
How it works

From months to hours. From Lego blocks to an assembled solution.

AURA and Mezmo each solve a distinct problem. Together they cover the full stack—agent control and data optimization.
AURA - Agent Harness

Declarative workflows, production defaults

Define agents in a TOML manifest—like a Kubernetes config for AI. Open-source, works with any model or MCP server, config lives in source control. Same config, same outcome, anywhere.

Mezmo - Active Telemetry

Right data, right context, right cost

Sits between your telemetry sources and observability platforms. Filter, route, and enrich in-stream—no rip-and-replace. Teams see 50–85% cost reduction without changing what they're already running.

AURA + Mezmo

Control plane meets data plane

AURA is the car, Mezmo is the supercharger. Start with one, add the other when you're ready. Together, the same workflows become 50–70% more cost-efficient—agents get curated data, not a firehose.

What you get

One harness. Three workflow modes. Any model.

AURA maps to how platform and SRE teams actually operate—proactive monitoring, reactive response, and on-demand answers—all configurable from one TOML manifest.
AURA · Proactive mode
Build & prevent

Agents run continuously, building contextual knowledge of your systems. Identify issues before they escalate and automate fixes nobody has time to address manually.

AURA · Reactive mode
Incident response

Automated triage, root cause analysis, and post-mortem generation. Same workflow every time—from alert to remediation in under 5 minutes.

AURA · Ad hoc mode
Chat & explore

Natural language access to production systems. Any team member can ask questions and get contextual answers—connected to real data, not a sandbox.

Mezmo · Data layer
Just-in-time data delivery

Mezmo's MCP tools are purpose-built for agent task completion—curated, right-sized telemetry for each query. No context window bloat. No hallucinations.

Key capabilities

Everything your platform needs to run agents in production

From source control–based config to intelligent data routing—the pieces that make agentic AI production-ready.
Declarative TOML workflows

Config in source control — testable, iterable, auditable. Same outcome anywhere.

Hours to production

Aha moment in under 1 hour. Full deployment in hours, not months.

Open-source, no lock-in

Own your workflows and context. Works with any model, any MCP server.

Human-in-the-loop safety

Agents ask permission for sensitive operations. No accidental deletions.

Filter, sample & reduce

Remove low-value data before it hits expensive destinations. Route signal.

Responsive pipelines

Auto-scale processing capacity and sampling rates during traffic spikes.

Data enrichment

Add contextual metadata automatically — agents work with richer inputs.

Data compliance

Redact, encrypt, or mask PII in-stream before it reaches any destination.

Explore more

Browse resources to learn more about how it works
Blog
AURA in practice: real-world use cases for production AI agent infrastructure

Blog
Why we open-sourced AURA: Infrastructure for production AI


Blog
What is Active Telemetry



Blog
The observability stack is collapsing: Why context-first data is the only path to AI-powered root cause analysis

Ship repeatable AI workflows in hours, not months.

Start with AURA free—open-source, no vendor lock-in. Works with your existing models, tools, and stack. Add Mezmo's data layer when you're ready to optimize.