CodeAF
Open-source control plane for coordinating AI coding agents in production
Visit agentfield.ai ↗What is CodeAF?
CodeAF is an open-source platform for running teams of AI coding agents from a single terminal. It provides a control plane to build, scale, and govern agents across any model, with every layer open source and deployable on your own infrastructure. The system coordinates multiple specialized agents—planners, coders, reviewers, and testers—to handle complex software engineering tasks end-to-end.
Designed for teams and enterprises, CodeAF offers private deployment, governance policies, audit trails, and identity management. It's used in production by organizations including JPMorgan, ServiceNow, Microsoft, and SAP. The maker indicates it was built with Claude Code. Installation is available via a single command, with full documentation and benchmarks provided.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered CodeAF automatically. Evidence: GitHub Agent-Field/SWE-AF; repo has .claude. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients