Skip to content
J·BJon BishopFractional growth marketer

Security · llms.txt file breakdown

Akka llms.txt

A directly retrieved Markdown index for Akka's documentation, with 168 links across 5 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.

# Akka Documentation

> Akka has one offering: the Akka Agentic AI Platform, which provides resilience and
> scalability for the agentic systems you build with it. Its four solutions are Akka SDK, Akka
> Specify, Akka Verify and Akka Optimize. They share one definition of an AI system, one
> runtime, one ledger and one governance model.

- Akka SDK is the component model for building agentic systems.
- Akka Specify is spec-driven development tooling that builds an agentic system from
  plain-language specifications and checks every change against them.
- Akka Verify is runtime-native evaluation, enforcement, evidence and governance for agents
  built on Akka or elsewhere.
- Akka Optimize routes traffic to the best open-weight model and trains smaller ones on your data.

Every system built with Akka runs on the Akka runtime, operated by you or by Akka Automated
Operations. The documentation sections are organized by task; the About Akka pages map each solution to
the sections that document it. Akka (formerly Lightbend) is distinct from the open-source Akka
actor library for the JVM, which is its lineage.

Personas: Builders (Application Developers, AI/ML Engineers, Product Managers), Operators
(Platform Engineers, SREs), Governance & Oversight (Compliance Analysts, InfoSec, FinOps).

## About Akka

- [About Akka](https://doc.akka.io/about-akka.html.md): The Akka Agentic AI Platform, its four solutions, and where each is documented
- [How the solutions work together](https://doc.akka.io/about/how-it-fits.html.md): What the four solutions share, and one agent followed from specification to a trained model
- [Akka SDK](https://doc.akka.io/about/akka-sdk.html.md): The component model: agents, workflows, entities, views, endpoints, timers and consumers
- [Akka Specify](https://doc.akka.io/about/akka-specify.html.md): Spec-driven development tooling: specifications, exit conditions and conformance
- [Akka Verify](https://doc.akka.io/about/akka-verify.html.md): Evaluation, the five control mechanisms, governance and the ledger
- [Akka Optimize](https://doc.akka.io/about/akka-optimize.html.md): Model routing, serving, training and spend
- [How Akka runs](https://doc.akka.io/about/how-akka-runs.html.md): The runtime, deployment options, and Akka Automated Operations
- [Resources](https://doc.akka.io/resources.html.md): Blogs, demos, webinars, foundational works, training, and community

## Getting Started

- [Getting started](https://doc.akka.io/getting-started/index.html.md): Install the Akka plugin, set up your environment, and run your first specification
- [Set up your environment](https://doc.akka.io/getting-started/set-up-env.html.md): Four self-contained setup paths — install using your AI harness, manually set up your AI harness, manually set up your environment, or use a container
- [Spec-first hello agent](https://doc.akka.io/getting-started/spec-your-first-agent.html.md): Build your first agent with spec-driven development
- [Code-first hello agent](https://doc.akka.io/getting-started/author-your-first-service.html.md): Build the same agent by hand in Java
- [Multi-agent tutorial](https://doc.akka.io/getting-started/planner-agent/index.html.md): Orchestrate multiple agents with a workflow
- [RAG chat tutorial](https://doc.akka.io/getting-started/ask-akka-agent/index.html.md): Build a retrieval-augmented chat agent
- [Shopping cart tutorial](https://doc.akka.io/getting-started/shopping-cart/index.html.md): Build an event-sourced service with entities and views
- [Retrieval-Augmented Generation (RAG)](https://doc.akka.io/getting-started/ask-akka-agent/rag.html.md): Semantic search on vector databases to enrich AI model requests
- [CLI installation](https://doc.akka.io/getting-started/install-cli.html.md): Install the Akka CLI
- [Log in to a remote environment](https://doc.akka.io/getting-started/log-in.html.md): Log in to deploy to or manage a remote Akka environment

## Building with AI

- [Spec-Driven Development](https://doc.akka.io/sdk/spec-driven-development.html.md): The primary development approach: build from plain-language specifications, checked on every change
- [Enforced mode](https://doc.akka.io/sdk/enforced-mode.html.md): Require exit conditions and conformance checks before changes merge
- [À la carte mode](https://doc.akka.io/sdk/a-la-carte-mode.html.md): Choose which development commands and checks to run
- [Specify command reference](https://doc.akka.io/reference/specify/index.html.md): Commands for specifications, planning, implementation, inspection, and release
- [Using an AI coding assistant](https://doc.akka.io/sdk/ai-coding-assistant.html.md): Enable AI assistants to use the Akka CLI natively

## SDK Components

- [Components overview](https://doc.akka.io/sdk/components/index.html.md): Akka's core building blocks, with a decision guide for choosing between them and when not to use each
- [Agents](https://doc.akka.io/sdk/agents.html.md): AI model-backed components with session memory and multi-agent collaboration
- [Autonomous Agents](https://doc.akka.io/sdk/autonomous-agents.html.md): Durable model-driven processes with typed tasks and multi-agent coordination
- [Workflows](https://doc.akka.io/sdk/workflows.html.md): Long-running, multi-step business processes with compensation
- [Event Sourced Entities](https://doc.akka.io/sdk/event-sourced-entities.html.md): State persistence via immutable event log
- [Key Value Entities](https://doc.akka.io/sdk/key-value-entities.html.md): State persistence via full-state snapshots
- [Views](https://doc.akka.io/sdk/views.html.md): Read-optimized projections across entities
- [HTTP Endpoints](https://doc.akka.io/sdk/http-endpoints.html.md): REST APIs with JSON, OpenAPI, server-sent events, and WebSocket support, plus serving web application assets
- [Web applications](https://doc.akka.io/sdk/web-applications.html.md): Serve a web application from a service — single-page application assets, static files, or generated HTML — alongside the API it calls, on your own domain with TLS
- [gRPC Endpoints](https://doc.akka.io/sdk/grpc-endpoints.html.md): High-performance APIs with gRPC
- [MCP Endpoints](https://doc.akka.io/sdk/mcp-endpoints.html.md): Expose tools, resources, and prompt templates to MCP clients
- [Consumers](https://doc.akka.io/sdk/consuming-producing.html.md): Stream-based event consumption and production
- [Timed Actions](https://doc.akka.io/sdk/timed-actions.html.md): Scheduled and delayed calls

## Agents

- [Model provider details](https://doc.akka.io/sdk/model-provider-details.html.md): Anthropic, OpenAI, Google, AWS Bedrock, Ollama, and more
- [Prompts](https://doc.akka.io/sdk/agents/prompt.html.md): Choosing the prompts for agents
- [Agent invocation](https://doc.akka.io/sdk/agents/calling.html.md): Calling agents from Akka code
- [Session memory](https://doc.akka.io/sdk/agents/memory.html.md): Managing agent session memory
- [Structured responses](https://doc.akka.io/sdk/agents/structured.html.md): Handling strongly typed responses from LLMs
- [Failure handling](https://doc.akka.io/sdk/agents/failures.html.md): Handling agent failures
- [Function tools](https://doc.akka.io/sdk/agents/extending.html.md): Extending agents with function (callback) tools
- [Streaming agent responses](https://doc.akka.io/sdk/agents/streaming.html.md): Streaming model responses with agents
- [Multi-agent orchestration](https://doc.akka.io/sdk/agents/orchestrating.html.md): Orchestrating and supervising multiple agents
- [Testing agents](https://doc.akka.io/sdk/agents/testing.html.md): Testing agents and agentic behavior

## Autonomous Agents

- [Agent definition](https://doc.akka.io/sdk/autonomous-agents/defining.html.md): Building an `AgentDefinition` with accepted task types, tools, guardrails, iteration limit, model, and optional instructions
- [Autonomous agent tasks](https://doc.akka.io/sdk/autonomous-agents/tasks.html.md): Task definitions, instances, lifecycle, snapshots, dependencies, and notifications
- [Autonomous agent coordination patterns](https://doc.akka.io/sdk/autonomous-agents/coordination.html.md): Sequential, delegative, collaborative, and emergent patterns for multi-agent systems
- [Autonomous agent coordination capabilities](https://doc.akka.io/sdk/autonomous-agents/capabilities.html.md): Delegation, handoff, teams, moderation, external input, and capability composition
- [Autonomous agent client API](https://doc.akka.io/sdk/autonomous-agents/client.html.md): `runSingleTask`, `assignTasks`, pause/resume, agent state, notification stream
- [Autonomous agent notifications](https://doc.akka.io/sdk/autonomous-agents/notifications.html.md): Lifecycle, task, handoff, delegation, team, conversation, messaging, and struggle notifications
- [Testing autonomous agents](https://doc.akka.io/sdk/autonomous-agents/testing.html.md): Mocking with `TestModelProvider` and `AutonomousAgentTools` helpers

## Security and governance

- [Classifiers](https://doc.akka.io/sdk/agents/classifiers.html.md): Classify content for use by agents, guardrails, and sanitizers
- [Runtime evaluators and the ledger](https://doc.akka.io/sdk/evaluators.html.md): Bind evaluators to agents, record verdicts, and read the ledger
- [Guardrails](https://doc.akka.io/sdk/agents/guardrails.html.md): Runtime policy enforcement
- [Data sanitization](https://doc.akka.io/sdk/sanitization.html.md): Mask personally identifiable information in logs and agent model inputs
- [Developing Access Control Lists (ACLs)](https://doc.akka.io/sdk/access-control.html.md): Implementing ACLs to control access to your Akka service endpoints
- [JSON Web Tokens (JWTs)](https://doc.akka.io/reference/jwts.html.md): Understanding JWT concepts and their role in Akka authentication
- [Developing JSON Web Tokens (JWT)](https://doc.akka.io/sdk/auth-with-jwts.html.md): Implementing JWT-based authentication in your Akka services
- [TLS certificates](https://doc.akka.io/operations/tls-certificates.html.md): Configuring and managing TLS certificates for secure communications

## Development and configuration

- [Configuration](https://doc.akka.io/sdk/setup-and-configuration/index.html.md): Configuring and initializing Akka services
- [Setup and dependency injection](https://doc.akka.io/sdk/setup-and-dependency-injection.html.md): Integrating dependency injection with Akka services
- [Serialization](https://doc.akka.io/sdk/serialization.html.md): Configuring and customizing serialization for entity data and messages
- [Run a service locally](https://doc.akka.io/sdk/running-locally.html.md): Steps to run and test Akka services in a local development environment
- [Run locally with a broker](https://doc.akka.io/sdk/running-with-broker.html.md): Run an Akka service locally against a Kafka broker or the Google Pub/Sub emulator
- [Run a local cluster](https://doc.akka.io/sdk/local-cluster.html.md): Run a multi-node Akka cluster locally

## Testing

- [Testing overview](https://doc.akka.io/testing/index.html.md): Three kinds of testing — unit, integration, evaluation
- [Unit testing](https://doc.akka.io/testing/unit.html.md): Exercise one component at a time with per-component TestKits
- [Integration testing](https://doc.akka.io/testing/integration.html.md): Exercise multiple components together against an in-process runtime
- [Evaluation](https://doc.akka.io/testing/evaluation/index.html.md): Run an agent through evaluation cases in a TestKit test and check replies and traced tool calls with built-in evaluators, a judge and a gate
- [Evaluation getting started](https://doc.akka.io/testing/evaluation/getting-started.html.md): An agent with two tools, a test class with a mocked model, one case, then a gated batch
- [Evaluation cases and evaluators](https://doc.akka.io/testing/evaluation/eval-cases.html.md): `EvalCase` parts and every built-in evaluator with its report name and when it is inconclusive
- [Model judges](https://doc.akka.io/testing/evaluation/judges.html.md): `Judge.modelBased`, `shouldSatisfy` and `shouldScoreAtLeast`, the judge prompt, gating on the judge pass rate
- [Gates and reports](https://doc.akka.io/testing/evaluation/gates-and-reports.html.md): Gate factories, reading an `EvalReport` and a failed case
- [Replaying recorded interactions](https://doc.akka.io/testing/evaluation/replay.html.md): `EvalCaseParser`, the JSONL format, `ToolBindings` and budgets from recorded spend

## Samples and blueprints

- [Samples and blueprints catalog](https://doc.akka.io/getting-started/samples.html.md): Browse runnable samples and generate systems from blueprints, filtered by AI use case, pattern, domain, components, and governance.
- [helloworld-agent](https://raw.githubusercontent.com/akka-samples/helloworld-agent/refs/heads/main/README.md): Agent with LLM greetings and session memory
- [multi-agent](https://raw.githubusercontent.com/akka-samples/multi-agent/refs/heads/main/README.md): Multi-agent system with an Autonomous Agent coordinator delegating to worker agents
- [ask-akka-agent](https://raw.githubusercontent.com/akka-samples/ask-akka-agent/refs/heads/main/README.md): RAG agent with vector search and streaming
- [shopping-cart](https://raw.githubusercontent.com/akka-samples/shopping-cart-quickstart/refs/heads/main/README.md): Event-sourced shopping cart
- [transfer-workflow](https://raw.githubusercontent.com/akka-samples/transfer-workflow-compensation/refs/heads/main/README.md): Funds transfer with compensation

## Integrations

- [Integrations overview](https://doc.akka.io/sdk/integrations/index.html.md): Standard Java APIs, no proprietary adapters needed
- [Component and service calls](https://doc.akka.io/sdk/component-and-service-calls.html.md): Invoke other services and components directly
- [AI & models](https://doc.akka.io/sdk/integrations/ai-and-models.html.md): 9 built-in LLM providers plus custom provider support
- [Data & knowledge](https://doc.akka.io/sdk/integrations/data-and-knowledge.html.md): Vector DBs, relational, NoSQL, search engines. No caching layer needed.
- [Messaging & events](https://doc.akka.io/sdk/integrations/messaging-and-events.html.md): Akka-native first, external brokers when needed
- [APIs & protocols](https://doc.akka.io/sdk/integrations/apis-and-protocols.html.md): REST, OpenAPI, WebSocket, gRPC, MCP, A2A, and browser-facing web application assets
- [Identity & security](https://doc.akka.io/sdk/integrations/identity-and-security.html.md): Native secrets, Azure KeyVault, standard Java APIs
- [Observability](https://doc.akka.io/sdk/integrations/observability.html.md): OpenTelemetry metrics and logs exporting
- [Streaming](https://doc.akka.io/sdk/streaming.html.md): Built-in stream processing and Akka Streams

## Deployment

- [Choose how you run Akka](https://doc.akka.io/deployment/index.html.md): The deployment options for running Akka services and how they compare
- [How AAO works](https://doc.akka.io/deployment/technical-overview.html.md): Deployment architecture, data flows, and infrastructure responsibilities
- [Production readiness](https://doc.akka.io/deployment/production-readiness/index.html.md): Responsibilities, readiness checks, and disaster recovery
- [Self-managed operations](https://doc.akka.io/deployment/configuring.html.md): Configure the runtime on infrastructure you operate

## Operating

- [Operating](https://doc.akka.io/operations/index.html.md): Project setup, service deployment, monitoring, and automation
- [Deploy a service](https://doc.akka.io/operations/services/deploy-service.html.md): Deploying to Akka
- [Observability](https://doc.akka.io/operations/observability-and-monitoring/index.html.md): Metrics, logs, traces, OTEL export
- [Secrets management](https://doc.akka.io/operations/projects/secrets.html.md): Built-in secrets with Azure KeyVault integration
- [Automate](https://doc.akka.io/operations/automate.html.md): Authenticate automation, integrate CI/CD, scan dependencies, and use the Platform API
- [CI/CD integration](https://doc.akka.io/operations/integrating-cicd/index.html.md): GitHub Actions and other CI/CD tools
- [Multi-region setup](https://doc.akka.io/operations/regions/setup.html.md): Add regions to a project, choose how stateful components select their primary region, and change the project's primary region
- [View logs](https://doc.akka.io/operations/observability-and-monitoring/view-logs.html.md): Accessing and analyzing logs from Akka services
- [View traces](https://doc.akka.io/operations/observability-and-monitoring/traces.html.md): Working with distributed tracing in Akka applications
- [View metrics](https://doc.akka.io/operations/observability-and-monitoring/metrics.html.md): Monitoring performance metrics for Akka services
- [Exporting metrics, logs, and traces](https://doc.akka.io/operations/observability-and-monitoring/observability-exports.html.md): Sending observability data to external monitoring systems
- [Configure message brokers](https://doc.akka.io/operations/projects/message-brokers.html.md): Setting up and configuring message brokers for Akka services
- [Using Aiven for Apache Kafka](https://doc.akka.io/operations/projects/broker-aiven.html.md): Integrating Aiven-hosted Kafka with Akka services
- [Using Confluent Cloud as Kafka service](https://doc.akka.io/operations/projects/broker-confluent.html.md): Setting up Confluent Cloud Kafka for use with Akka services
- [Using AWS MSK as Kafka service](https://doc.akka.io/operations/projects/broker-aws-msk.html.md): Configuring AWS Managed Streaming for Kafka with Akka services
- [Using a self-hosted or arbitrary Kafka cluster](https://doc.akka.io/operations/projects/broker-kafka.html.md): Connecting Akka to any Kafka cluster that meets the supported authentication and TLS requirements
- [Using Google Cloud Pub/Sub as message broker](https://doc.akka.io/operations/projects/broker-google-pubsub.html.md): Integrating Google Cloud Pub/Sub with Akka services
- [Projects](https://doc.akka.io/operations/projects/index.ht

Measured from the saved file

Linked document

UTF-8 text size
27.5 KB28145 bytes
Token count
6475o200k_base encoding
Markdown links
182182 distinct URLs
Fenced code blocks
0259 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
Akka Documentation

Opening blockquote

Akka has one offering: the Akka Agentic AI Platform, which provides resilience and scalability for the agentic systems you build with it. Its four solutions are Akka SDK, Akka Specify, Akka Verify and Akka Optimize. They share one definition of an AI system, one runtime, one ledger and one governance model.

Context architecture

How the content is divided

18 H2 sections organize 182 parsed Markdown links. 178 links point to .md or .markdown paths; 9 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
About AkkaLine 2381102269
Getting StartedLine 34101503364
Building with AILine 475745166
SDK ComponentsLine 55131768409
AgentsLine 71101120276
Autonomous AgentsLine 8471290289
Security and governanceLine 9481105265
Development and configurationLine 1056839192
TestingLine 11491478348
Samples and blueprintsLine 12661026235
IntegrationsLine 13591238305
DeploymentLine 1474582124
OperatingLine 154253767850
InferenceLine 182101733399
ConceptsLine 196274022910
TrainingLine 227338894
Show 2 more sections
H2 sectionLinksUTF-8 bytesTokens
ReferenceLine 233182438551
OptionalLine 254 · Optional439395

Nested indexes

1 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.

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
0 closed
Declared languages
No fenced blocks detected
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
0 fenced lines match request-method patterns
Authentication links
0 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.

Publisher prioritization

The Optional section

1 H2 section named “Optional” contain 4 parsed links. 178 links sit outside those sections. That puts 2.2% of the file’s parsed links under Optional.

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://doc.akka.io/llms-full.txt ↗
Discovery
Conventional sibling path checked
HTTP response
200 · text/plain
Text size
1.6 MB · 1720223 bytes (measured)
Token count
390461 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

2 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://doc.akka.io/llms.txt
Final endpoint
https://doc.akka.io/llms.txt
HTTP status
200
Content type
text/plain
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
898d386ee9826677ee1be318da3d5a72b066339fe09e25d14f7e59ada9a60022

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