Home Projects Hephaestus
Hephaestus
Python

Hephaestus

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

by Ido-Levi · GitHub
Stars
Forks
Trending
Created
Last commit
Category
Language
ai-agentsautonomous-agentsclaude-codePython
View on GitHub
In plain words

Watch AI agents create their own workflows based on tasks they identify, rather than pre-defined instructions.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Hephaestus — GitHub preview card
📈 Star history
1 1841 176
2026-07-202026-08-31
📈 Track Hephaestus

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

Hephaestus has 1.2k stars on GitHub. It has been forked 125 times. Hephaestus is written mainly in Python. It has been in active development since 2025. Its main topics are ai-agents, autonomous-agents, claude-code, llm.

Frequently asked questions

What is Hephaestus?

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

Is Hephaestus open source?

Hephaestus is an open-source project.

Is Hephaestus free?

Yes. Hephaestus is free and open source — you can use, modify and self-host it.

What language is Hephaestus written in?

Hephaestus is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Hephaestus

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=ido-levi-hephaestus)](https://olud.ai/project/ido-levi-hephaestus.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.