chu2bard

DAG-based multi-agent workflow engine with state management

17
0
69% credibility
Found Feb 11, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Agentplex is a Python toolkit for creating and running workflows of connected tasks that pass shared information between them in a structured sequence.

How It Works

1
🔍 Discover Agentplex

You hear about a simple tool that lets you chain everyday tasks together, where each one uses the results from the previous, like steps in a recipe.

2
📦 Get it ready

You easily add this tool to your computer setup so it's available for your projects.

3
🔗 Design your task chain

You create individual actions, like 'set a starting number' or 'double the number', and connect them so they flow one into the next.

4
▶️ Start the workflow

With everything linked, you press go and let the tasks run in the right order, sharing information as they go.

5
Watch it happen

Your actions execute smoothly, even in parallel when possible, building up results step by step.

Enjoy the results

You get the final outcome, like turning 42 into 84, with your whole process working perfectly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is agentplex?

Agentplex is a Python-based engine for building multi-agent workflows as directed acyclic graphs (DAGs), where you define steps as simple functions, wire them with dependencies, and run them with automatic topological ordering. It handles state management across nodes, passing data seamlessly while supporting async execution and parallel branches for efficient workflows. Developers get a lightweight way to orchestrate complex, agent-like processes without heavy orchestration tools.

Why is it gaining traction?

It stands out with a dead-simple API: add nodes, edges, and execute—zero boilerplate for DAG-based stateful workflows. Async parallelism and built-in error tracking mean faster runs for real-world agent plex setups, unlike verbose alternatives. Early adopters hook on the snapshot history for debugging multi-agent flows.

Who should use this?

Backend devs crafting AI agent pipelines, like chaining LLMs with data processors. Python scripters building ETL jobs or simulation workflows needing dependency graphs. Teams prototyping multi-agent systems before scaling to Cadence or Temporal.

Verdict

At 17 stars and 0.7% credibility score, agentplex feels pre-alpha—basic docs, no tests, and rough edges like unhandled edge cases limit production use. Grab it for quick Python DAG experiments if you want agentplex-style state management without overhead, but watch for maturity.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.