Kestra

Tools come with the platform as well as the runtime: 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. These are authenticated actions the vendor supplies, not only the customer's own code.

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

Kestra is a workflow engine: 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

A retrieval layer ships with the platform: 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 and stay queryable wherever the store lives.

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

The approval step is the vendor's own: 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. Kestra's human in the loop use case documents approval chains that route decisions to specific users or teams, with audit logs recording who approved or rejected each request and why. The pricing page lists Human-in-the-Loop Approvals with custom inputs under the Enterprise Edition.

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

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

Sourcekestra.io/pricingread 2026-09-25

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

Agents built in Kestra remember information across executions through a memory plugin: the KestraKVStore memory saves the chat messages to a namespace KV entry keyed by memoryId (PostgreSQL and Redis memories are the alternatives). The agent's own turns write it. It is keyed per memoryId in a namespace, 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, so the memory has a writer, a scope, a lifetime and customer controls.

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

Deployment goes into the customer's own environment: the open source edition is Apache 2.0 licensed (per the repository's license file) 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

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. Each blueprint is a whole flow that does its own job.

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

Flows start on their own: they 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

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

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

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. The assertions read on whether the flow behaves as configured, not on how well an agent's output performs. No evaluation harness, scored test cases or judge for agent output of Kestra's own is documented.

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

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. No browser automation environment or headless browser guide appears in Kestra's documentation, and while script tasks run any code the customer supplies, no browser workload is documented as hosted.

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