# Mezmo Docs

> Explore guides, APIs, tutorials, and reference materials for collecting telemetry and using Mezmo’s SRE agent to manage production environments.

## Home

- [Welcome](https://docs.mezmo.com/index.md): Build, optimize, and act on telemetry data with Mezmo.

- [Log Management (118 pages)](https://docs.mezmo.com/_llms/log-management.md): Documentation for Log Management.
- [Telemetry Pipelines (127 pages)](https://docs.mezmo.com/_llms/telemetry-pipelines.md): Documentation for Telemetry Pipelines.

## Mezmo Edge

- [Mezmo Edge Pipelines for Local Data](https://docs.mezmo.com/mezmo-edge/mezmo-edge-pipelines-for-local-data.md): Run telemetry pipelines locally with Mezmo Edge to access local sources, process data within your network, and use Rust-based regex.
- [Set Up Mezmo Edge in Kubernetes](https://docs.mezmo.com/mezmo-edge/set-up-mezmo-edge-in-kubernetes.md): Install Mezmo Edge in a Kubernetes cluster with the Mezmo Helm chart, then create, deploy, and monitor an Edge Pipeline.
- [Mezmo Edge Deployment Planning](https://docs.mezmo.com/mezmo-edge/mezmo-edge-deployment-planning.md): Sizing, scaling, durability, and performance guidance for planning a Mezmo Edge telemetry pipeline deployment in your own environment.
- [HTTP Source for Mezmo Edge](https://docs.mezmo.com/mezmo-edge/http-source-for-mezmo-edge.md): Configure any source to send data to a Mezmo Edge Pipeline via a RESTful POST over an allocated HTTP port.
- [Syslog Source for Mezmo Edge](https://docs.mezmo.com/mezmo-edge/syslog-source-for-mezmo-edge.md): Send syslog events to a Mezmo Edge Pipeline through a specified port using the Syslog over HTTP source within your own network.
- [Set Up Mezmo Edge in a Docker Container](https://docs.mezmo.com/mezmo-edge/set-up-mezmo-edge-in-a-docker-container.md): Run a single Mezmo Edge instance as a Docker container using Docker Compose, including the compose and processor config files.
- [Tap and View Mezmo Edge Pipeline Data on Premises](https://docs.mezmo.com/mezmo-edge/tap-and-view-mezmo-edge-pipeline-data-on-premises.md): Inspect data flowing through a local Mezmo Edge Pipeline using the vector tap CLI or GraphQL, without sending data to the Mezmo Web App.

## AURA

### Getting Started

- [AURA: open source agent harness for production SRE work](https://docs.mezmo.com/aura/index.md): AURA is an open source SRE agent for investigating production incidents, with scoped tool access, human approval gates, and end-to-end OpenTelemetry tracing.
- [AURA Quickstart](https://docs.mezmo.com/aura/quickstart.md): Install the aura binary locally, generate a config, connect an MCP server, and put your agent to work.
- [Installation](https://docs.mezmo.com/aura/installation.md): Install AURA with the install script, a direct binary download, Homebrew, or the APT and RPM package repositories.
- [Full-Stack Docker Quickstart](https://docs.mezmo.com/aura/quickstart-docker.md): Run the whole AURA stack with docker compose — orchestrator mode, a chat UI, and a trace viewer.
- [Example Configs](https://docs.mezmo.com/aura/example-configs.md): Example TOML configurations and advanced quickstarts for AURA agents.
- [Kubernetes SRE Orchestration Quickstart](https://docs.mezmo.com/aura/quickstart-k8s-sre.md): Deploy an AI-powered Kubernetes SRE agent using orchestration mode to coordinate cluster inspection and metrics analysis specialists.

### Configuration

- [Configuration Reference](https://docs.mezmo.com/aura/configuration-reference.md): Complete TOML field reference for AURA — agent identity, LLM providers, MCP, vector stores, scratchpad, skills, orchestration, HITL, and session storage.
- [Breaking Changes — 10 April 2026](https://docs.mezmo.com/aura/breaking-changes-20260410-agent-llm-toml-configuration.md): LLM behavior fields moved from [agent] to [llm]; Ollama params consolidated under [llm.additional_params].
- [Breaking Changes — 21 April 2026](https://docs.mezmo.com/aura/breaking-changes-20260421-llm-under-agent.md): [llm] moved from top-level to [agent.llm], enabling per-worker LLM overrides in orchestration mode.
- [Breaking Changes — 23 July 2026](https://docs.mezmo.com/aura/breaking-changes-20260723-empty-mcp-filter.md): An empty `mcp_filter` (`mcp_filter = []`) now grants no MCP tools instead of every MCP tool.

### Features

- [Streaming API Guide](https://docs.mezmo.com/aura/streaming-api-guide.md): OpenAI-compatible Server-Sent Events (SSE) streaming, custom aura.* events, tool result modes, and orchestration events.
- [A2A Integration](https://docs.mezmo.com/aura/a2a-implementation.md): A2A protocol endpoints, transport modes, the agent card URL, task lifecycle, and testing examples.
- [Human-in-the-Loop Approval Gates](https://docs.mezmo.com/aura/hitl.md): Configure webhook and conversational approval gates for orchestration worker tool calls.
- [Scratchpad (Context Window Management)](https://docs.mezmo.com/aura/scratchpad.md): Intercept large MCP tool outputs, explore them with dedicated tools, and manage token budgets automatically.
- [Skills (On-Demand Instructions)](https://docs.mezmo.com/aura/skills.md): Package task-specific instructions that AURA agents pull in only when a task calls for them.
- [Client-Side Tools](https://docs.mezmo.com/aura/client-side-tools.md): Risk model, protocol mechanics, and server/CLI configuration for client-side tool passthrough.
- [Ollama Guide](https://docs.mezmo.com/aura/ollama-guide.md): Ollama configuration, fallback tool-call parsing, and practical guidance for local models.
- [Telemetry & Privacy](https://docs.mezmo.com/aura/telemetry.md): Anonymous, opt-out CLI telemetry — the three-state consent model, exactly what is and isn't collected, kill switches, and how to audit it.
- [Request Lifecycle](https://docs.mezmo.com/aura/request-lifecycle.md): Request flow, timeout configuration, cancellation, and graceful shutdown behavior.
- [Tracing & Span Layout](https://docs.mezmo.com/aura/tracing-spans.md): Enable OpenTelemetry, understand AURA's span layout, and interpret OpenInference span kinds.

### CLI Reference

- [AURA CLI Reference](https://docs.mezmo.com/aura/cli-reference.md): The aura command-line client — install, run, configure, and use every feature of the interactive terminal client.

### Web Server Reference

- [AURA Web Server Reference](https://docs.mezmo.com/aura/web-server-reference.md): OpenAI-compatible web API server that exposes AURA agents through a standard chat completions endpoint — endpoints, deployment env vars, and architecture.

## Guides

### Optimization Tutorial

- [Introduction](https://docs.mezmo.com/OptTutorial/1-intro.md): Workshop overview for using the OpenTelemetry Demo and Mezmo to understand and optimize telemetry data for both MTTR and cost.
- [Shared Sources](https://docs.mezmo.com/OptTutorial/2-shared-sources.md): Create OpenTelemetry log, metric, and trace Shared Sources in Mezmo and save their access keys for the optimization workshop.
- [Setting Up the OTel Demo App](https://docs.mezmo.com/OptTutorial/3-configure-build-demo.md): Clone the OpenTelemetry Demo, configure the collector with your Mezmo Shared Source credentials, and run it via Docker.
- [Profiling Log Data](https://docs.mezmo.com/OptTutorial/4-profile-log-data.md): Build an exploration pipeline with the Mezmo Data Profiler to surface high-volume and unparsed log patterns in the OpenTelemetry Demo.
- [Log Data Optimization Pipeline](https://docs.mezmo.com/OptTutorial/5-optimize-logs.md): Build a responsive log pipeline that enriches, parses, routes by state, aggregates, and samples logs before sending them to Mezmo Log Analysis.
- [Metrics Data Optimization Pipeline](https://docs.mezmo.com/OptTutorial/6-optimize-metrics.md): Build a Mezmo pipeline that enriches, state-routes, aggregates, and limits cardinality on OpenTelemetry metrics to reduce volume.
- [Trace Data Optimization Pipeline](https://docs.mezmo.com/OptTutorial/7-optimize-traces.md): Build a Mezmo pipeline that enriches, state-routes, and samples OpenTelemetry traces to cut volume while preserving incident fidelity.
- [Updating to Responsive Pipelines](https://docs.mezmo.com/OptTutorial/8-optimize-responsively.md): Use a REST API shell script to switch your log, metric, and trace pipelines into incident mode for full-fidelity data on demand.
- [What's Next?](https://docs.mezmo.com/OptTutorial/9-next-steps.md): Recap the four OpenTelemetry optimization pipelines you built and explore further Mezmo capabilities like rehydration, alerting, and PII redaction.

### Practitioner's Guide to Data Optimization

- [Introduction: Telemetry Data Optimization with Mezmo Pipelines](https://docs.mezmo.com/practioner-guide-data-optimization/data-optimization-introduction.md): How Mezmo helps SREs understand, optimize, and reduce overwhelming telemetry volume, with an overview of what this practitioner's guide covers.
- [Optimize Your Observability Data in Six Steps](https://docs.mezmo.com/practioner-guide-data-optimization/optimize-your-observability-data-in-six-steps.md): A platform-agnostic approach to cutting log volume by 50%+ via archiving, filtering, parsing, merging, metric conversion, and responsive pipelines.
- [Analysis of Telemetry Data Optimization Techniques](https://docs.mezmo.com/practioner-guide-data-optimization/analysis-data-reduction-techniques.md): Summary results and findings from testing data reduction techniques on Priority 1 sources, showing 50%+ volume cuts without quality loss.
- [Pipeline Examples and Tutorials](https://docs.mezmo.com/practioner-guide-data-optimization/reference-architectures-for-data-optimization-pipelines.md): Index of example Mezmo Telemetry Pipelines and data optimization tutorials, including processor configuration settings.
- [Pipeline Example: Kafka Telemetry Data Optimization](https://docs.mezmo.com/practioner-guide-data-optimization/pipeline-architecture-for-data-reduction.md): An example pipeline that parses, routes, reduces, and converts Kafka logs to metrics while preserving errors and warnings at full fidelity.
- [Pipeline Example: Kubernetes Telemetry Data Optimization](https://docs.mezmo.com/practioner-guide-data-optimization/pipeline-architecture-for-kubernetes-data-optimization.md): An example pipeline that filters, converts to metrics, aggregates, and routes Kubernetes container logs while archiving originals for compliance.
- [Tutorial: Convert Events to Metrics](https://docs.mezmo.com/practioner-guide-data-optimization/pipeline-example--convert-200-events-to-metrics.md): Build a pipeline that routes Status 200 events through Event to Metric and Aggregate processors to reduce volume while keeping trend data.
- [Tutorial: Mask and Encrypt Data](https://docs.mezmo.com/practioner-guide-data-optimization/pipeline-module--security-and-compliance.md): Build a compliance processor group that routes events to Encrypt Field and Redact processors to protect PII like card numbers and user IDs.
- [Tutorial: Route Data](https://docs.mezmo.com/practioner-guide-data-optimization/pipeline-module--route.md): Build a routing group that uses a Route Processor and conditional statements to send financial, JSON, and Apache data down separate processing chains.
- [Demo Pipeline Overview](https://docs.mezmo.com/practioner-guide-data-optimization/demo-pipeline-guide8ke.md): Tour the trial Demo Pipeline's sources, Route and Filter processors, and Encrypt Field processor for handling credit card transaction data.

### Guide to Pipeline Architecture

- [Types of Telemetry Data Pipelines](https://docs.mezmo.com/guide-to-pipeline-architecture/types-of-telemetry-data-pipelines.md): Compare Mezmo pipeline patterns for ingestion, optimization, archiving and rehydration, and responsive processing, with example pipelines for each.
- [Understanding Your Data to Optimize It](https://docs.mezmo.com/guide-to-pipeline-architecture/understanding-your-data-to-optimize-it.md): Use the Mezmo Data Profiler to analyze streaming telemetry through Message Templates, Field Summaries, and Log Metrics before deciding how to optimize it.
- [Basic Log Analysis Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/basic-log-analysis-pipeline.md): Configure and use the Mezmo Log Analysis Destination with a Demo Logs Source to stream telemetry data into the Log Analysis viewer.
- [Basic Data Optimization Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/basic-data-optimization-pipeline.md): Explore the Demo Pipeline's Route, Filter, and Encrypt processors for handling transaction errors and encrypting credit card data.
- [Kafka Data Optimization Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/kafka-data-optimization-pipeline.md): Parse, route, and convert Kafka logs to metrics so routine events are summarized while errors and warnings reach storage at full fidelity.
- [Kubernetes Data Optimization Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/kubernetes-data-optimization-pipeline.md): Transform Kubernetes telemetry into metrics with Filter, Route, Event to Metric, and Aggregate Processors while retaining original data in storage.
- [Basic Data Rehydration Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/basic-data-rehydration-pipeline.md): Build pipelines to archive telemetry data to S3 and restore it to Mezmo Log Analysis using a restoration task.
- [Convert Events to Metrics](https://docs.mezmo.com/guide-to-pipeline-architecture/convert-events-to-metrics.md): Reduce log volume by routing routine 200 events through Event to Metric and Aggregate Processors, with example Processor configurations.
- [Mask and Encrypt Data](https://docs.mezmo.com/guide-to-pipeline-architecture/mask-and-encrypt-data.md): Build a data compliance processor group that routes events through Redact and Encrypt Field Processors to obfuscate PII such as user IDs and credit card numbers.
- [Route Data](https://docs.mezmo.com/guide-to-pipeline-architecture/route-data.md): Use a Route Processor with conditional statements to direct financial, JSON, and Apache data from multiple sources through specialized processing chains to different destinations.
- [Build a Basic Data Rehydration Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/build-a-basic-data-rehydration-pipeline.md): Archive telemetry data to an S3 bucket and restore it to Mezmo Log Analysis using the Archive Destination, Pipeline Data Restoration Source, and a restoration task.
- [Mezmo Log Analysis Source Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/log-analysis-source-pipeline.md): Overview of the four-step Pipeline that Mezmo Log Analysis customers use to optimize log data, including each Processor and its configuration.
- [Responsive OTel Pipeline Workshop](https://docs.mezmo.com/guide-to-pipeline-architecture/responsive-otel-pipeline-tutorial.md): Hands-on workshop for building responsive OpenTelemetry pipelines that route full-fidelity data during incidents and optimize for cost during normal operations.
- [1 - Introduction](https://docs.mezmo.com/guide-to-pipeline-architecture/1--introduction.md): Workshop overview and prerequisites for optimizing OpenTelemetry logs, metrics, and traces with Mezmo Pipelines.
- [2 - Create Shared Sources](https://docs.mezmo.com/guide-to-pipeline-architecture/2---shared-sources.md): Create OpenTelemetry log, metric, and trace shared sources in Mezmo for use in later pipeline steps.
- [4 - Analyze the Source Data](https://docs.mezmo.com/guide-to-pipeline-architecture/3---configure-and-build-the-demo.md): Build a Log Explorer pipeline with a Script Execution and Data Profiler processor to analyze your OTel source data.
- [3 - Build the OTel Demo Source](https://docs.mezmo.com/guide-to-pipeline-architecture/4---profile-log-data.md): Clone the OpenTelemetry Demo, configure it with your Mezmo shared source credentials, and build it locally.
- [5 - Create an OTel Log Handler Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/5---optimize-logs.md): Build a responsive log pipeline that parses custom Apache logs, reduces flood events, and routes data by operational state to Log Analysis.
- [6 - Create an OpenTelemetry Metric Handler Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/6---optimize-metrics.md): Build a responsive metric pipeline that aggregates metrics and limits tag cardinality, routing data by operational state.
- [7 - Create an OTel Trace Handle Pipeline](https://docs.mezmo.com/guide-to-pipeline-architecture/7---optimize-traces.md): Build a pipeline that samples OpenTelemetry traces during normal operation and routes data by operational state.
- [8 - Test the Responsive Pipelines](https://docs.mezmo.com/guide-to-pipeline-architecture/8---optimize-responsibly.md): Use the switch-state script to toggle pipeline states and observe how responsive pipelines adjust fidelity during incidents.

### Pipeline API Quickstart

- [Getting Started with the Mezmo Pipeline API](https://docs.mezmo.com/pipeline-api-quickstart/getting-started-with-the-mezmo-pipeline-api.md): Walk through curl examples to create a pipeline, add an HTTP source and access key, attach a transform and S3 destination, then publish.

- [API References (204 pages)](https://docs.mezmo.com/_llms/api-references.md): Documentation for API References.

## OpenAPI Specs

- [combined-mezmo-api](/apis/combined-mezmo-api.yaml)
- [ai-history](/apis/ai-history.json)
- [enterprise-api](/apis/enterprise-api.json)
- [log-analysis](/apis/log-analysis.json)
- [pipeline](/apis/pipeline.yaml)

## Optional

- [About](https://www.mezmo.com/about)
- [Blog](https://www.mezmo.com/blog)

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [Log Management (118 pages)](https://docs.mezmo.com/_llms/log-management.md): Documentation for Log Management.
- [Telemetry Pipelines (127 pages)](https://docs.mezmo.com/_llms/telemetry-pipelines.md): Documentation for Telemetry Pipelines.
- [API References (204 pages)](https://docs.mezmo.com/_llms/api-references.md): Documentation for API References.