Akka vs Kestra (2026)

Agents call function tools and MCP tools as the model requests, services integrate over REST, OpenAPI, gRPC, WebSocket and Kafka or other brokers, and guardrails check MCP tool requests and responses.

Sourcedoc.akka.io/sdk/agents.html.mdread 2026-09-27

The AI Agent task takes tools of Kestra's own, including any Kestra task or flow called as a tool (KestraTask, KestraFlow), web search (Google Custom Search, Tavily), MCP clients over SSE, stdio and streamable HTTP, and another agent as a tool, and the platform ships over 2,000 plugins for databases, cloud services, messaging and business systems with managed credentials through secrets.

Sourcekestra.io/docs/ai-tools/ai-agentsread 2026-09-25

Durable workflows run long multi step processes with compensation and resume from the current step after a restart, agents share a session under a workflow, and autonomous agents coordinate by delegation, handoff, teams and moderation with a registry for dispatching to specialists at runtime.

Sourcedoc.akka.io/sdk/workflows.html.mdread 2026-09-27

Kestra is a workflow engine whose flows, declared in YAML, run tasks through flowable control primitives (Sequential, Parallel, Loop, LoopUntil, Switch, If, DAG and Subflow), with retries, error handling and backfills. For agents, an AI Agent task decides which tools and tasks to run and in what order, a parent agent can delegate to a child agent wrapped as a tool, and an A2A client forwards work to a remote agent.

Sourcekestra.io/docs/workflow-components/tasks/flowable-tasksread 2026-09-25

Timed Actions schedule delayed and recurring calls, Consumers react to event streams and Kafka topics, and Akka Streaming processes real time inputs such as IoT metrics, audio and video that can start agents, alongside HTTP, gRPC, WebSocket and MCP endpoints.

Sourcedoc.akka.io/llms.txtread 2026-09-27

Flows declare Schedule (cron), Flow (another flow finishing), Webhook, Polling and Realtime triggers, and an MCP Tool trigger registers a flow as a tool an outside agent can call.

Sourcekestra.io/docs/workflow-components/triggersread 2026-09-25

Durable memory can hold semantic knowledge and retrieved data, and a sample RAG agent shows vector search with streaming, but indexing and retrieval over a customer's documents is code the developer writes. Akka does not ship a knowledge store of its own.

Sourcedoc.akka.io/akka-memory.html.mdread 2026-09-27

The IngestDocument task chunks and embeds the customer's documents into an embeddings store (Kestra's own KV Store, or Chroma, Elasticsearch, PGVector, Pinecone, Qdrant, Weaviate and others), and the RAG ChatCompletion task and EmbeddingStoreRetriever query that store so an agent answers from the customer's data. The embeddings persist across runs.

Sourcekestra.io/docs/ai-tools/ai-rag-workflowsread 2026-09-25

Akka Memory keeps session memory for the turns of an interaction and durable long term memory across users, sessions and agents, scoped per session, per agent or shared, stored as an event sourced journal that is both the in memory tier and the durable record, with compaction of older context. Akka does not publish retention or deletion terms.

Sourcedoc.akka.io/akka-memory.html.mdread 2026-09-27

Agents built in Kestra remember information across executions through a memory plugin. The KestraKVStore memory saves the chat messages from the agent's own turns to a namespace KV entry keyed by memoryId, with PostgreSQL and Redis memories as alternatives, so one conversation or customer can be deleted without touching the rest. A TTL sets its expiry, drop set to AFTER_TASKRUN deletes it after use, and scheduled purges cover KV pairs. KV pairs can be created, edited and deleted in the Kestra UI, through tasks and through the REST API.

Sourcekestra.io/plugins/plugin-ai/memory/io.kestra.plugin.ai.memory.kestrakvstoreread 2026-09-25

A workflow can pause for an approval command and resume where it left off, durably across crashes, deployments and days; autonomous agent pipelines carry a human approval task between drafting and publishing; Akka Verify HITL boundaries block in a reviewer queue until a person decides; and guardrails check model and MCP tool requests and responses, failing closed.

Sourceakka.io/llms-full.txtread 2026-09-27

A Pause task holds a flow at a chosen step, for output validation or manual approval, until a person resumes it from the UI or API. Approval chains route decisions to specific users or teams, with audit logs recording who approved or rejected each request and why, and Human-in-the-Loop Approvals with custom inputs come in the Enterprise Edition.

Sourcekestra.io/docs/use-cases/approval-processesread 2026-09-25

The trust center (Akka dba Lightbend, Inc.) lists SOC 2 Type II on request, a public SOC 3, ISO 27001, ISO 42001, PCI DSS, HIPAA and GDPR among 50 standards, and Akka Automated Operations provides access control at the organization level, with secured HTTP and gRPC endpoints and secrets management in the SDK.

Sourcetrust.akka.ioread 2026-09-27

The Enterprise Edition includes SSO, LDAP and SCIM, role based access control with a permissions reference, policies, and multi tenant storage isolation, with audit logs and a secrets manager as supporting controls. Kestra Cloud is SOC 2 compliant.

Sourcekestra.io/pricingread 2026-09-25

A non sampled, hash chained interaction log records each agent interaction with authority snapshots, Verify emits typed events for every guardrail, human and evaluation decision, the local and Akka console show traces for debugging, and metrics, logs and traces export over OpenTelemetry.

Sourceakka.io/llms.txtread 2026-09-27

Every execution is recorded for step by step inspection. The Executions view shows status, logs, outputs and metrics per task through Gantt and Topology views, AI Agent tasks can log each model request and response, and the Enterprise Edition adds audit logs recording every action by users and service accounts plus log shipping to an external store.

Sourcekestra.io/docs/ui/executionsread 2026-09-25

Akka runs self managed on the customer's own VMs, containers, Kubernetes, PaaS or edge, or through Akka Automated Operations in the customer's VPC or Akka's serverless cloud, with projects pinned to chosen regions, multi region replication and data pinning, and sovereign cloud deployments for China, Hong Kong, Singapore, North America, Canada and the EU.

Sourceakka.io/llms-full.txtread 2026-09-27

The open source edition is Apache 2.0 licensed and self hosts on the customer's infrastructure, cloud or Kubernetes, and the Enterprise Edition runs on cloud, on premises or air gapped, with Kestra Cloud as the managed option.

Sourcekestra.io/pricingread 2026-09-25

A samples and blueprints catalog filters by AI use case, pattern, domain and governance: downloadable working samples such as a medical tagging agent with human verification, a real estate customer service agent and an IoT monitoring agent, plus 460 blueprints that the Akka Specify plugin turns into runnable systems.

Sourcedoc.akka.io/getting-started/samples.html.mdread 2026-09-27

Kestra publishes Blueprints, a searchable catalog of validated, documented flows, including AI agent and RAG flows, that a buyer adopts into a namespace with one click from inside the product and then adjusts; the Enterprise Edition adds custom blueprints, an organization's own approved set.

Sourcekestra.io/docs/concepts/blueprintsread 2026-09-25

Nine providers are built in, Anthropic, OpenAI, Gemini, Vertex AI, Bedrock, Mistral, Hugging Face, Ollama and LocalAI, any other plugs in as a custom provider, each agent can set its own model, and an AI Gateway Router and Akka Optimize route work to served open weight models.

Sourcedoc.akka.io/sdk/integrations/ai-and-models.html.mdread 2026-09-27

Each AI task takes its model through Kestra's provider property, so the customer picks among providers of Kestra's own for Anthropic, OpenAI, Azure OpenAI, Amazon Bedrock, Google Gemini and Vertex AI, Mistral, DeepSeek, Ollama, OpenRouter and others, and an Enterprise policy can set the provider across a namespace.

Sourcekestra.io/docs/ai-tools/ai-agentsread 2026-09-25

The Akka SDK is the component model for agents, workflows, entities, views and endpoints, services expose HTTP, gRPC and MCP endpoints with A2A and ACP built into agents, and a CLI and Claude Code plugin with an MCP server manage projects. The runtime is source available under BSL.

Sourcedoc.akka.io/llms.txtread 2026-09-27

Kestra is API first, with every UI action available through its REST API, and ships official SDKs for Java, Python, JavaScript and TypeScript, and Go, a Terraform provider, and custom plugin development. Its MCP servers expose flows as named tools over HTTP for outside agents, with authentication set per server.

Sourcekestra.io/docs/api-reference/kestra-sdkread 2026-09-25

EvalKit scores a service against a dataset of eval cases with deterministic, heuristic and agentic evaluators, saves baselines that CI gates regressions against, and renders reports; RedKit red teams against AILuminate and OWASP LLM Top 10 taxonomies, and Verify runs evaluations inline or over the interaction log.

Sourcedoc.akka.io/testing/evaluation/index.html.mdread 2026-09-27

Unit Tests in the Enterprise Edition run test suites that mock tasks and assert on flow behavior, so a change can be checked before production without real side effects. Those assertions check that the flow behaves as configured, and Kestra does not describe an evaluation harness, scored test cases or a judge for agent output.

Sourcekestra.io/docs/enterprise/governance/unit-testsread 2026-09-25

Akka is a runtime and SDK for backend agentic services, with no browser or computer use component.

Sourcedoc.akka.io/llms.txtread 2026-09-27

The AI Agent's tools are Kestra tasks and flows, web search, MCP clients and other agents, none of them a browser or desktop it operates. Kestra does not describe a browser automation environment or a hosted browser workload, though script tasks run any code the customer supplies.

Sourcekestra.io/docs/ai-tools/ai-agentsread 2026-09-25