← Projects

Agent Orchestration Framework

Orchflow

A dependency-free Python framework for readable multi-agent pipelines: sequential, parallel, conditional, and resumable flows.

0 deps

zero runtime dependencies in core

AsyncIOLiteLLMPydantic

Orchflow live demo

live Flow.events() stream

Live LLMsSafe presetsRate limitedRepo

Runtime graph

0events0parallel0ok

Ready to run.

Final

No output yet.

Inspector

No event selected.

Video walkthrough

Watch the complete Orchflow demo

Open on YouTube ↗

A six-minute walkthrough of the same project story: readable Python steps, parallel branches, live events, retries, traces, and JSON checkpoint resume.

What it proves

A live case for readable multi-agent workflows

Readable orchestration

The running demo is still a normal Flow([...]) list: plan, a parallel group, synthesis, condition, finalizer.

Parallel work you can inspect

The three research agents share a parallel_group_id, so the UI can prove they fanned out and rejoined.

Resume is visible

Failure mode saves a JSON checkpoint, reloads it, and appends new traces after resume.

Safe live model demo

Visitors can adjust small inputs and model presets, while the backend enforces allowlisted models and rate limits.

The API

The backend is still plain Python

The portfolio UI is only a viewer. The value comes from Orchflow: step functions stay readable, while the framework handles fan-out, retries, lifecycle events, checkpoints, and resume.

real step function
from orchflow import Agent, Flow, StepContext, condition, step
 
@step(name="technical_research", retry=2)
async def technical_research(input: dict, context: StepContext):
return await researcher.run(prompt, context=context)
same flow shape the demo runs
flow = Flow([
plan,
[market_research, technical_research, risk_review],
synthesize,
condition(
when=lambda ctx: ctx.previous["quality_score"] >= 0.8,
then=publish_ready,
otherwise=revise,
),
finalize,
])

Get started

Install from PyPI

pip
$ pip install orchflow
$ pip install "orchflow[litellm]"

v0.5.0 · tag-based PyPI releases · core has zero runtime dependencies.

← All projects