# Ido-Levi/Hephaestus

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

Repository: https://github.com/Ido-Levi/Hephaestus
Canonical: https://ross.abutalabs.com/products/hephaestus
Language: Python
License: NOASSERTION
License Family: other
Topics: ai-agents, autonomous-agents, claude-code, llm
Last push: 2025-12-01T07:39:12+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 26, longevity 25
- inputs: {"age_days": 352, "days_push": 275, "days_rel": 283, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1183, forks 125 (observed 2026-08-28T04:03:54.513105+00:00)

## What it is
Hephaestus is a Python-based semi-structured agentic framework where AI agents dynamically create tasks and build workflows as they discover what needs to be done, rather than following fully predefined instructions. It includes Hephaestus Dev, a pre-configured setup with production-ready workflows for software development tasks like bug fixing, feature development, and documentation generation.

## Use cases
- build software from a product requirements document with ai agents
- let ai agents fix and verify bugs automatically
- generate documentation for an existing codebase
- index a repository to build codebase knowledge in memory
- orchestrate multiple ai agents on complex software projects
- add features to a codebase following existing patterns
- create self-building agent workflows instead of predefined ones

## When to choose
- you want agents to adapt and create tasks based on discoveries rather than fixed plans
- you need multi-agent coordination for software development tasks
- you want prebuilt workflows for PRD-to-software, bug fixing, or doc generation
- your project is Python 3.8+ and you're comfortable with alpha-stage tooling

## When to avoid
- you need a stable, production-hardened framework - it's explicitly alpha
- you prefer fully deterministic, predefined workflow pipelines
- you need a non-Python or non-CLI integration
- the AGPL-3.0 license is incompatible with your usage

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, workflow-automation, llm-inference, developer-tools
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: agentic-workflows, dynamic-task-generation, multi-agent, claude-code, software-development-automation, alpha, ai-agents, automation

## Member repositories
- Ido-Levi/Hephaestus (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.513105+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:24:30.860808+00:00, confidence not recorded.
  - readme: https://github.com/Ido-Levi/Hephaestus (fetched 2026-08-28T04:03:54.513105+00:00, sha 6c8416f5dca7)
- Data as of 2026-08-30T08:39:29.467469+00:00.