Warren
Run coding agents as managed infrastructure workloads
Visit app.warren.run ↗What is Warren?
Warren is a platform for running AI coding agents as isolated, observable workloads on infrastructure you control. It manages the full lifecycle of agent runs—from workspace setup and execution through Git delivery—handling isolation, spend limits, live event streams, and recovery. The project describes itself as turning coding agents from terminal sessions into production infrastructure.
Warren owns the workspace, run lifecycle, spend and concurrency limits, steering, cancellation, recovery, and Git delivery. Each run starts from a fresh branch, stays within a sandbox boundary, and can be monitored, steered, or cancelled in real time. Completed work is committed and optionally opened as pull requests. The platform persists run state, events, cost, token use, and outcomes via HTTP API, CLI, and UI.
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 Warren automatically. Evidence: GitHub jayminwest/warren; repo has .claude, AGENTS.md, CLAUDE.md. 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