Flowgentic
Flowgentic runs agent components and LangGraph workflows as tasks on
RADICAL AsyncFlow.
Documentation: stride-research.github.io/flowgentic.
Status
Flowgentic 0.4.0 is a repair release in maintenance mode. It removes features
that 0.3 shipped broken or unsafe, or that did not serve its purpose. It adds
accept, which checks an agent's output before it becomes HPC work, and it
carries the trace into the tasks it submits, so an agent's decisions, the tasks
they run in and their model calls form one OpenTelemetry trace. The LangGraph
execution adapter (LangraphIntegration) is frozen and gets no new features.
New applications can bind agents with bind_agent, or run LangGraph on
AsyncFlow directly.
| Agent framework | Workflow engine | Backends | Python |
|---|
| LangGraph 1.x | RADICAL AsyncFlow 0.6.0 | Local | 3.10, 3.11, 3.12 |
Project status lists the tested versions, the known limitations
and the archived branches.
What it provides
bind_agent (flowgentic.agent) binds an agent component, any object
with an ainvoke(context) method, to an AsyncFlow task on a named backend.
Each call to the bound agent runs the component as that task and returns its
structured decision with the agent's identity and timing, and is an
OpenTelemetry invoke_agent span.accept (flowgentic.acceptance) accepts or rejects an agent's output
on explicit checks, before it becomes HPC work. It asks again with the
reasons, within an attempt budget, and falls back to a deterministic value
when no proposal passes. Each call, attempt and check is recorded in the
run's trace.LangraphIntegration (flowgentic.langGraph) runs a LangGraph graph's
tools, services, tasks and nodes as AsyncFlow tasks, in their caller's trace.
Install
From a clone, with the locked environment:
git clone https://github.com/stride-research/flowgentic.git
cd flowgentic
uv sync --locked
Or build the wheel and install it into a new environment. The
v0.4.0 GitHub release carries the same wheel.
uv build
uv venv --python 3.10 flowgentic-env
uv pip install --python flowgentic-env/bin/python dist/flowgentic-0.4.0-py3-none-any.whl
Run the demos
Two demos in examples/ai-hpc-coupling/ run offline, with no model
credentials: a deterministic LangGraph graph, and an agentic one whose agents
take scripted decisions.
make examples-ai-hpc-deterministic
make examples-ai-hpc-agentic
Getting started
explains their output, and examples/ai-hpc-coupling/README.md the other
demos.
Development
uv sync --locked --extra dev
uv run --extra dev pytest -q
uv run --extra dev mkdocs build --strict
CONTRIBUTING.md covers the environment, coding style,
tests and pull requests. Report bugs and requests as
GitHub issues.
CHANGELOG.md lists the changes in each release.
How to cite
If you use Flowgentic in your work, please cite it. CITATION.cff
holds the metadata, and GitHub's "Cite this repository" menu turns it into APA
or BibTeX:
Alsaadi, A., Amirghofran, Y., Barbero, C., Cordovez, D., Dominguez, J.,
Oliveros, D., & Turilli, M. (2026). Flowgentic (Version 0.4.0) [Computer
software]. https://github.com/stride-research/flowgentic
License
MIT; see LICENSE.
