Skip to content
J·BJon BishopFractional growth marketer

Data platforms · llms.txt file breakdown

ZenML llms.txt

A directly retrieved Markdown index for ZenML's documentation, with 475 links across 11 detected headings.

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Open saved text ↗

Showing the first 18000 characters. Load the complete file to read the remainder.

# ZenML - Bridging the gap between ML & Ops

## ZenML

- [Welcome to ZenML](https://docs.zenml.io/getting-started/introduction.md): Build production ML pipelines with ZenML and improve agentic systems with Kitaru.
- [Installation](https://docs.zenml.io/getting-started/installation.md): Installing ZenML and getting started.
- [Hello World](https://docs.zenml.io/getting-started/hello-world.md): Your first ML pipeline with ZenML - from local development to cloud deployment in minutes.
- [Your First AI Pipeline](https://docs.zenml.io/getting-started/your-first-ai-pipeline.md): Choose your path and build your first pipeline with ZenML in minutes.
- [Core Concepts](https://docs.zenml.io/getting-started/core-concepts.md): Discovering the core concepts behind ZenML.
- [System Architecture](https://docs.zenml.io/getting-started/system-architectures.md): Different variations of the ZenML architecture depending on your needs.
- [Deploy](https://docs.zenml.io/deploying-zenml/deploying-zenml.md): Why do we need to deploy ZenML?
- [Deploy with Docker](https://docs.zenml.io/deploying-zenml/deploying-zenml/deploy-with-docker.md): Deploying ZenML in a Docker container.
- [Deploy with Helm](https://docs.zenml.io/deploying-zenml/deploying-zenml/deploy-with-helm.md): Deploying ZenML in a Kubernetes cluster with Helm.
- [Migrate to Gateway API](https://docs.zenml.io/deploying-zenml/deploying-zenml/deploy-with-helm/migrate-to-gateway-api.md): Migrate ZenML Helm deployments from Ingress to Kubernetes Gateway API.
- [Deploy using HuggingFace Spaces](https://docs.zenml.io/deploying-zenml/deploying-zenml/deploy-using-huggingface-spaces.md): Deploying ZenML to Huggingface Spaces.
- [Deploy with custom images](https://docs.zenml.io/deploying-zenml/deploying-zenml/deploy-with-custom-image.md): Deploying ZenML with custom Docker images.
- [Secret management](https://docs.zenml.io/deploying-zenml/deploying-zenml/secret-management.md): Configuring the secrets store.
- [Custom secret stores](https://docs.zenml.io/deploying-zenml/deploying-zenml/custom-secret-stores.md): Learning how to develop a custom secret store.
- [Live event streaming](https://docs.zenml.io/deploying-zenml/deploying-zenml/live-event-streaming.md): Enable live event streaming on the ZenML server and consume the HTTP/SSE feed.
- [Connect](https://docs.zenml.io/deploying-zenml/connecting-to-zenml.md): Various means of connecting to ZenML.
- [with your User (interactive)](https://docs.zenml.io/deploying-zenml/connecting-to-zenml/connect-in-with-your-user-interactive.md): Connect to the ZenML server using the ZenML CLI and the web based login.
- [with your User (programmatic)](https://docs.zenml.io/deploying-zenml/connecting-to-zenml/connect-with-a-pat.md): Connect to the ZenML server using a Personal Access Token.
- [with a Service Account](https://docs.zenml.io/deploying-zenml/connecting-to-zenml/connect-with-a-service-account.md): Connect to the ZenML server using a service account and an API key.
- [Manage](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server.md): Learn how to upgrade your server to a new version of ZenML for the different deployment options.
- [Best practices for upgrading](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/best-practices-upgrading-zenml.md): Simple, step-by-step guide for keeping your ZenML workspaces (servers) up to date without breaking your teams.
- [Using ZenML server in production](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/using-zenml-server-in-prod.md): Learn about best practices for using ZenML server in production environments.
- [Troubleshoot your ZenML server](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/troubleshoot-your-deployed-server.md): Troubleshooting tips for your ZenML deployment
- [Migration guide](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/migration-guide.md): How to migrate your ZenML code to the newest version.
- [Migration guide 0.13.2 → 0.20.0](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/migration-guide/migration-zero-twenty.md): How to migrate from ZenML <=0.13.2 to 0.20.0.
- [Migration guide 0.23.0 → 0.30.0](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/migration-guide/migration-zero-thirty.md): How to migrate from ZenML 0.20.0-0.23.0 to 0.30.0-0.39.1.
- [Migration guide 0.39.1 → 0.41.0](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/migration-guide/migration-zero-forty.md): How to migrate your ZenML pipelines and steps from version <=0.39.1 to 0.41.0.
- [Migration guide 0.58.2 → 0.60.0](https://docs.zenml.io/deploying-zenml/upgrade-zenml-server/migration-guide/migration-zero-sixty.md): How to migrate from ZenML 0.58.2 to 0.60.0 (Pydantic 2 edition).
- [Steps & Pipelines](https://docs.zenml.io/concepts/steps_and_pipelines.md): Steps and Pipelines are the core building blocks of ZenML
- [Configuration](https://docs.zenml.io/concepts/steps_and_pipelines/configuration.md): Configuring and customizing your pipeline runs.
- [Scheduling](https://docs.zenml.io/concepts/steps_and_pipelines/scheduling.md): Learn how to create, update, activate, deactivate, and delete schedules for pipelines.
- [Logging](https://docs.zenml.io/concepts/steps_and_pipelines/logging.md): Learn how to control and customize logging behavior in ZenML pipelines.
- [YAML Configuration](https://docs.zenml.io/concepts/steps_and_pipelines/yaml_configuration.md): Learn how to configure ZenML pipelines using YAML configuration files.
- [Source Code and Imports](https://docs.zenml.io/concepts/steps_and_pipelines/sources.md): Understanding source roots and source paths
- [Execution](https://docs.zenml.io/concepts/steps_and_pipelines/execution.md): Step and pipeline execution.
- [Wait for External Input](https://docs.zenml.io/concepts/steps_and_pipelines/wait_resume.md): Pause a dynamic pipeline for external input and resume it after the input is resolved.
- [Advanced Features](https://docs.zenml.io/concepts/steps_and_pipelines/advanced_features.md): Advanced features and capabilities of ZenML pipelines and steps
- [Hooks](https://docs.zenml.io/concepts/steps_and_pipelines/hooks.md): Run custom code on pipeline and step lifecycle events and record hook invocations.
- [Dynamic Pipelines](https://docs.zenml.io/concepts/steps_and_pipelines/dynamic_pipelines.md): Write dynamic pipelines
- [Command Steps](https://docs.zenml.io/concepts/steps_and_pipelines/command_steps.md): Run arbitrary commands as pipeline steps
- [Streaming Events](https://docs.zenml.io/concepts/steps_and_pipelines/streaming_events.md): Publish live events from inside a step to subscribed clients.
- [Artifacts](https://docs.zenml.io/concepts/artifacts.md): Learn how ZenML manages data artifacts, tracks versioning and lineage, and enables effective data flow between steps.
- [Materializers](https://docs.zenml.io/concepts/artifacts/materializers.md): Understanding and creating materializers to handle custom data types in ZenML pipelines
- [Visualizations](https://docs.zenml.io/concepts/artifacts/visualizations.md): Learn how to visualize the data artifacts produced by your ZenML pipelines.
- [Stack & Components](https://docs.zenml.io/concepts/stack_components.md): Understanding and working with ZenML Stacks and Stack Components
- [Service Connectors](https://docs.zenml.io/concepts/service_connectors.md): Managing authentication to cloud services and resources with Service Connectors
- [Pipeline Snapshots](https://docs.zenml.io/concepts/snapshots.md): Create and run pipeline snapshots.
- [Pipeline Deployments](https://docs.zenml.io/concepts/deployment.md): Deploy pipelines as HTTP services for real-time execution
- [Deployment Settings](https://docs.zenml.io/concepts/deployment/deployment_settings.md): Customize the pipeline deployment ASGI application with DeploymentSettings.
- [Containerization](https://docs.zenml.io/concepts/containerization.md): Customize Docker builds to run your pipelines in isolated, well-defined environments.
- [Code Repositories](https://docs.zenml.io/concepts/code-repositories.md): Tracking your code and avoiding unnecessary Docker builds by connecting your git repo.
- [Secrets](https://docs.zenml.io/concepts/secrets.md): Registering and using secrets.
- [Environment Variables](https://docs.zenml.io/concepts/environment-variables.md): Configuring environment variables.
- [Tags](https://docs.zenml.io/concepts/tags.md): Use tags to organize tags in ZenML.
- [Metadata](https://docs.zenml.io/concepts/metadata.md): Enrich your ML workflow with contextual information using ZenML metadata.
- [Models](https://docs.zenml.io/concepts/models.md): Managing ML models throughout their lifecycle with ZenML
- [Dashboard](https://docs.zenml.io/concepts/dashboard-features.md): Explore the features and capabilities of the ZenML dashboard
- [Templates](https://docs.zenml.io/concepts/templates.md): Create and run templates in ZenML to standardize execution.
- [Community & content](https://docs.zenml.io/reference/community-and-content.md): All possible ways for our community to get in touch with ZenML.
- [Environment Variables](https://docs.zenml.io/reference/environment-variables.md): How to control ZenML behavior with environmental variables.
- [LLM Tooling](https://docs.zenml.io/reference/llms-txt.md): LLM tooling for ZenML - MCP servers, llms.txt, and Agent Skills
- [FAQ](https://docs.zenml.io/reference/faq.md): Find answers to the most frequently asked questions about ZenML.
- [Global settings](https://docs.zenml.io/reference/global-settings.md): Understanding the global settings of your ZenML installation.
- [Legacy docs](https://docs.zenml.io/reference/legacy-docs.md): All legacy docs of ZenML

## Kitaru (AI Agents)

- [Welcome to Kitaru](https://docs.zenml.io/kitaru/getting-started/readme.md): Replay-based evals for AI agents, in Python and TypeScript. Test your next change against what your agent already did in production.
- [Installation](https://docs.zenml.io/kitaru/getting-started/installation.md): Install Kitaru with one command, start the local server, and verify. Other install paths for project environments, TypeScript, and team servers.
- [Deploy Kitaru](https://docs.zenml.io/kitaru/getting-started/deploy.md): Self-host Kitaru for your team: one server, your Postgres, workers in the environments where your agents live.
- [Docker](https://docs.zenml.io/kitaru/getting-started/deploy/docker.md): Run the Kitaru server with Docker, using Compose for one host or the server container against your own Postgres.
- [Helm](https://docs.zenml.io/kitaru/getting-started/deploy/helm.md): Deploy the Kitaru server on Kubernetes with the first-party Helm chart, covering external Postgres, automatic migrations, ingress, and TLS.
- [Set up your coding agent](https://docs.zenml.io/kitaru/getting-started/setup.md): Install the MCP server and agent skills, then drive the whole Kitaru loop from Claude Code, Codex, or Cursor.
- [Quickstart](https://docs.zenml.io/kitaru/getting-started/quickstart.md): From an agent in production to your first replay-backed decision, driven by your coding assistant: every step is a prompt first, a command second.
- [Overview](https://docs.zenml.io/kitaru/core-concepts/concepts.md): A handful of nouns and one verb, and how sessions, replays, evaluators, cohorts, experiments, investigations, and workers fit together.
- [Agents & Sessions](https://docs.zenml.io/kitaru/core-concepts/agents-and-sessions.md): The agent is the identity, the session is the recording of every model call, tool call, and decision a run left behind.
- [Investigations & Annotations](https://docs.zenml.io/kitaru/core-concepts/investigations.md): Where your judgment enters the system: your coding assistant maps the evidence, interviews you in context, and pins your answers to exact trace evidence as annotations.
- [Replay](https://docs.zenml.io/kitaru/core-concepts/replay.md): Re-run a recorded session against your real code, unchanged for a faithful baseline or forked with one thing different.
- [Evaluators & Evaluations](https://docs.zenml.io/kitaru/core-concepts/evaluators.md): Evaluators turn sessions into evaluations: the rows they write. Numbers average, words count, free text gets read.
- [Analyzers & Insights](https://docs.zenml.io/kitaru/core-concepts/analyzers.md): Analyzers turn many sessions into insights: the aggregate read a single evaluator can't give you.
- [Cohorts](https://docs.zenml.io/kitaru/core-concepts/cohorts.md): Named, versioned sets of sessions; the population an experiment replays, frozen so results stay comparable.
- [Experiments](https://docs.zenml.io/kitaru/core-concepts/experiments.md): A named change, replayed across a cohort and evaluated. What improved, what regressed, before you ship.
- [Workers](https://docs.zenml.io/kitaru/core-concepts/workers.md): The process that runs replays, imports, and evaluators as subprocesses in your environment, so your code and data never leave your systems.
- [Under the Hood](https://docs.zenml.io/kitaru/core-concepts/under-the-hood.md): The machinery behind the loop: a FastAPI server on Postgres, workers claiming tasks, and where Kitaru sits beside your observability stack.
- [Complete returns agent tutorial](https://docs.zenml.io/kitaru/guides/returns-agent.md): Investigate supplied returns agent traces and test one evidence-led improvement.
- [1. Observe the recorded behavior](https://docs.zenml.io/kitaru/guides/returns-agent/observe.md): Verify the prepared returns evidence and select a bounded worklist for human review.
- [2. Judge the selected behavior](https://docs.zenml.io/kitaru/guides/returns-agent/judge.md): Create an investigation and store human judgments against exact trace evidence.
- [3. Define one behavior to test](https://docs.zenml.io/kitaru/guides/returns-agent/define.md): Turn accepted human evidence into one frozen cohort and evaluator version.
- [4. Replay one bounded change](https://docs.zenml.io/kitaru/guides/returns-agent/replay.md): Register one investigation-derived candidate and replay the frozen cohort safely.
- [5. Compare the paired evidence](https://docs.zenml.io/kitaru/guides/returns-agent/compare.md): Compare baseline and replay evidence and state the result at the size the cohort supports.
- [Replay a failure and fork it](https://docs.zenml.io/kitaru/guides/replay-and-overrides.md): Reproduce a recorded session, fork it with an override, and compare the two, so you can debug a failure or test a change before shipping it.
- [Build a regression suite from production](https://docs.zenml.io/kitaru/guides/regression-suite.md): Freeze a cohort of recorded runs, replay it against a change, and use the results in CI.
- [Write an evaluator](https://docs.zenml.io/kitaru/guides/write-an-evaluator.md): Turn your domain expert's criteria into a versioned evaluator: code checks, LLM judges, human calibration, and backfilling your history.
- [TypeScript and Mastra evaluators](https://docs.zenml.io/kitaru/guides/typescript-evaluators.md): Run TypeScript evaluation code and native Mastra scorers through versioned Kitaru evaluators.
- [Write an analyzer](https://docs.zenml.io/kitaru/guides/write-an-analyzer.md): Turn a pattern you'd otherwise eyeball across sessions into a versioned analyzer: the entrypoint contract, a runnable example, and how it runs on import.
- [Deterministic evaluations](https://docs.zenml.io/kitaru/guides/deterministic-evaluations.md): Run Kitaru's offline deterministic evaluators over recorded and imported sessions
- [Judge evaluations](https://docs.zenml.io/kitaru/guides/judge-evaluations.md): Judge recorded sessions with TypeSafe's jev model by asking your own yes/no, choice, and score questions, one evaluation result per question.
- [Tool policies](https://docs.zenml.io/kitaru/guides/tool-policies.md): Choose whether replayed tool calls use recorded results, static results, live tools, or model-generated responses.
- [Track cost and model usage](https://docs.zenml.io/kitaru/guides/llm-calls.md): Every model call recorded: tokens, cost, and call counts on every session, and how to total them across cohorts and experiments.
- [Overview](https://docs.zenml.io/kitaru/import-your-traces/import-your-traces.md): Bring the traces you already collect. Langfuse stays your system of record, Kitaru gets a runnable copy.
- [Post-import insights](https://docs.zenml.io/kitaru/import-your-traces/post-import-insights.md): Generate insights after an import on a local, self-hosted, or managed Kitaru server.
- [Langfuse](https://docs.zenml.io/kitaru/import-your-traces/import-langfuse-traces.md): Langfuse JSONL imports end to end: the accepted export, dedup semantics, and how imports execute on your worker.
- [LangSmith](https://docs.zenml.io/kitaru/import-your-traces/import-langsmith-traces.md): Turn LangSmith runs into replayable Kitaru sessions: the accepted export shapes, how threads group into sessions, dedup semantics, and what the importer cannot recover.
- [Braintrust](https://docs.zenml.io/kitaru/import-your-traces/import-braintrust-traces.md): Import Braintrust project logs into Kitaru: accepted export shapes, how spans become nodes, multi-turn grouping, and what the importer marks as lossy.
- [Logfire](https://docs.zenml.io/kitaru/import-your-traces/import-logfire-traces.md): Import Pydantic Logfire records-query exports into Kitaru: accepted export shapes, how OpenTelemetry GenAI spans become nodes, conversation grouping, and what the importer marks as lossy.
- [Arize Phoenix](https://docs.zenml.io/kitaru/import-your-traces/import-phoenix-traces.md): Import Arize Phoenix trace exports into Kitaru: supported UI and CLI files, span mapping, source identity, and known limits.
- [MLflow](https://docs.zenml.io/kitaru/import-your-traces/import-mlflow-traces.md): Import MLflow traces into Kitaru: accepted export shapes, how MLflow spans become nodes, session grouping, fetching from a tracking server, and what the importer marks as lossy.
- [Ki

Measured from the saved file

Links and embedded code

UTF-8 text size
69.3 KB71013 bytes
Token count
17681o200k_base encoding
Markdown links
475475 distinct URLs
Fenced code blocks
1520 lines in the file

Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.

Project H1
ZenML - Bridging the gap between ML & Ops

Context architecture

How the content is divided

9 H2 sections organize 475 parsed Markdown links. 475 links point to .md or .markdown paths; 0 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
ZenMLLine 36496642457
Kitaru (AI Agents)Line 7060121072949
LearnLine 13367109822807
ZenML ProLine 2034677741795
StacksLine 252131197294795
API ReferenceLine 3869985572359
SDK ReferenceLine 4885479130
ChangelogLine 4963611143
Querying This DocumentationLine 5080924199

Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.

Embedded material

Code, installation and API examples

Fenced blocks
1 closed
Declared languages
unlabeled (1)
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
1 fenced lines match request-method patterns
Authentication links
3 links have authentication-related labels

Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.

Inspect detected API and authentication lines

Source line 514 · unlabeled

GET https://docs.zenml.io/index.md?ask=<question>&goal=<user_goal>

Publisher prioritization

The Optional section

No H2 section named “Optional” was detected in this file.

The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.

Machine-readable routes

MCP references and configuration text

MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.

These are text and link observations. No MCP server connection, authentication or tool call was tested.

Index and bundle

llms-full.txt companion

Verified text companion

Text companion verified

https://docs.zenml.io/llms-full.txt ↗
Discovery
Conventional sibling path checked
HTTP response
206 · text/markdown; charset=utf-8
Text size
1.1 MB · 1133435 bytes (server-reported)
Token count
254583 o200k_base tokens
Retrieval scope
Complete body retrieved

A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.

Change evidence

What can be said about freshness

This capture establishes a baseline. Update frequency cannot be determined from one observation.

Linked release and migration material

9 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.

File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.

Capture identity and measurement method
Requested endpoint
https://docs.zenml.io/llms.txt
Final endpoint
https://docs.zenml.io/llms.txt
HTTP status
200
Content type
text/markdown; charset=utf-8
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
436e7f8d9221a615cf2017dbc40826c389d03ad51e1cd84b3c9dc105425adba4

Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.

Related tools and resources

Contact Jon