LlamaIndex Workflows

OrchestrationMIT

LlamaIndex Workflows is a Python library for controlling the execution flow of an AI application. You split the application into steps; each step receives an event, does its work and returns an event, which decides the next step. Events are Pydantic objects, a context object holds per-run state, and a handler streams events while a run is in progress. Developers install it on its own with pip and can serve workflows with the llamactl command line tool.

The code lives in the run-llama/llama-agents repository. The durable workflows page says resumption is at-least-once, so step side effects must be safe to repeat.

Pinout

  • MCP server: not checked yet
  • HTTP API: not checked yet
  • command line: supported, verified
  • Python SDK: supported, verified
  • TypeScript SDK: not checked yet
  • OpenAPI description: not checked yet
Where each pin comes from
InterfaceStatusSource we readRead on
MCP serverNot checked yet——
HTTP APINot checked yet——
Command lineSupported, verifiedRepository README, llamactl commands
Python SDKSupported, verifiedWorkflows documentation, install line (pip install llama-index-workflows)
TypeScript SDKNot checked yet——
OpenAPI descriptionNot checked yet——

Facts

Facts about LlamaIndex Workflows
LicenseMIT. GitHub repository page, Resources, read .
Repository namerun-llama/llama-agents. GitHub repository page, read .
Python packagepip install llama-index-workflows (standalone install). Workflows documentation, read .
Programming modelEvent-driven, step-based control of execution flow; each step receives an event and returns an event. Workflows documentation, read .
EventsUser-defined Pydantic objects, plus built-in start and stop events. Workflows documentation, read .
Streamingrun() returns a handler; stream_events() yields events while the workflow runs. Workflows documentation, read .
Run statePer-run shared state through ctx.store. Workflows documentation, read .
PersistenceNo built-in checkpointer; state is saved with Context.to_dict() and restored with Context.from_dict(). Durable workflows page, read .
Runtime pluginDBOS runtime journals step transitions to a database so a crashed workflow can resume. Durable workflows page, read .
Command line tooluv tool install llamactl, then llamactl init, serve and deployments create. GitHub repository README, read .
Latest package releasellama-index-workflows@2.26.1. GitHub Releases page, read .
Last commit. GitHub API, latest commit on the default branch of run-llama/llama-agents, read .

Call example

class HelloWorkflow(Workflow):
    @step
    async def greet(self, ev: StartEvent) -> StopEvent:
        return StopEvent(result=f"Hello, {ev.name}")

Limits

  • There is no built-in checkpointer; persistence is manual or through a runtime plugin.
  • Resume is at-least-once, so step side effects must be safe to repeat.

Strengths

  • Installs standalone with pip install llama-index-workflows.
  • Events are typed Pydantic objects and runs can stream events.
  • The repository is MIT licensed.

Alternatives to LlamaIndex Workflows

All orchestration tools for agents
  1. Low-level framework for stateful, long-running agent workflows built as graphs.

    Orchestration
  2. Typed Python SDK for building agents across many model providers.

    Orchestration
  3. Durable execution platform, open source, used to run long-lived agents.

    Orchestration
  4. Open-source Python framework for multi-agent workflows; separate commercial platform.

    Orchestration

Last check: . Method: public repository and docs read automatically, page and day written down. Next check due within 90 days. How we check

Is this your tool? Write to hello@agent-tools.directory from an address on its domain to correct a pin or a fact.