managedcode/MCAF
MCAF is a framework for building software products together with AI coding agents.
Organizes durable engineering context—code, docs, `AGENTS.md` files, and versioned skills—directly in the repository so AI agents work from repo-native guidance rather than external configuration. Enforces verification through layered tests and static analysis as decision gates, not opinions, with strict coverage baselines and a TDD-first approach. Uses skill packs (reusable workflow templates) and hierarchical `AGENTS.md` files (root + local) to keep agent instructions explicit, small, and scoped to their application context.
Stars
45
Forks
6
Language
CSS
License
CC-BY-4.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/managedcode/MCAF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
covibes/zeroshot
Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to...
a5c-ai/babysitter
Babysitter enforces obedience to agentic workforces and enables them to manage extremely complex...
Q00/ouroboros
Stop prompting. Start specifying.
Priivacy-ai/spec-kitty
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor,...
AsiaOstrich/dev-autopilot
Agent-agnostic unattended development orchestrator. Plan interactively, execute autonomously,...