macaron-software

macaron-software / software-factory

Public

Multi-Agent Software Factory — Autonomous AI agents orchestrating the full product lifecycle with SAFe, TDD, and auto-heal capabilities

ai-agents auto-heal autonomous-agents devops fastapi
55
2
100% credibility
Found Feb 28, 2026 at 47 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An open-source platform orchestrating AI agent teams to automate the full software development lifecycle from ideation to deployment using SAFe methodology.

How It Works

1
🔍 Discover the Software Factory

You hear about a virtual factory where smart helpers team up to build software from your ideas.

2
📦 Get it running

Download and start it with simple steps, like turning on a helpful workshop on your computer.

3
🔗 Link smart thinkers

Connect thinking helpers so they can understand and create things for you.

4
💡 Share your idea

Tell it about your app dream, like a carpool matcher for work buddies.

5
🤖 Watch the team build

See the helpers chat and turn your idea into a full plan with tasks and goals.

6
▶️ Run the work

Press go and watch them code, test, and fix everything automatically.

🎉 Enjoy your ready app

Get a working project with code, tests, and even auto-checks running smoothly.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 47 to 55 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 software-factory?

Software Factory is a Python-based platform that deploys 161 autonomous AI agents to orchestrate the full software development lifecycle—from ideation workshops and SAFe portfolio planning to TDD coding, testing, deployment, and auto-healing incidents. Users get a FastAPI web dashboard with real-time SSE streaming of agent collaborations, a CLI for commands like `sf ideation "e-commerce app"` or `sf missions start`, and a REST API for integrations, all powered by multi-provider LLMs like MiniMax or Azure OpenAI. It solves the pain of manual coordination in multi-agent AI software development by enforcing structured workflows, DORA metrics tracking, and quality gates across projects.

Why is it gaining traction?

This stands out in the crowded multi agent github space with its SAFe-aligned structure (Portfolio > Epic > Feature > Story), 10 orchestration patterns like hierarchical or network for agent teams, and built-in resilience like self-healing TMA missions that detect crashes and auto-fix code. Developers hook on the live demo at sf.macaron-software.com, agent mercato for trading specialized roles (e.g., SRE or QA), and tools like Playwright E2E tests or bandit SAST scans bundled in Docker—no setup hassle. It's a full software factory for langgraph multi agent github experiments, with adaptive intelligence evolving teams via Thompson sampling.

Who should use this?

Dev leads or SREs in SAFe teams experimenting with multi agent ai software development through cross team collaboration, especially for ideation-to-deploy pipelines on Angular migrations or security audits. Frontend/backend devs tired of boilerplate CI/CD and manual retrospectives will appreciate the auto-provisioned TMA, security, and tech debt missions per project. Small teams prototyping multi agent software engineering without hiring more humans.

Verdict

Intriguing early-stage bet for multi agent orchestration github copilot workflows, but with only 26 stars and 1.0% credibility score, treat as experimental—docs are multilingual and polished, but expect bugs in production runs. Spin up the Docker demo today if you're curious about agent-driven software factories; skip for mission-critical unless you contribute.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.