GitHub Repository

Control plane that runs AI coding agents (Codex, Claude Code, Gemini, OpenCode, Grok, Cursor) as disciplined contributors: each task gets an isolated git worktree + Docker Compose stack, profile-driven validation, a created PR, and an autonomous PR-monitor loop (review, CI fixes, base sync, auto-merge). GitHub & BitBucket. Apache-2.0.

5 starsPython

AWF – run parallel AI coding agents, each in its own Docker workspace

Name: AWF – run parallel AI coding agents, each in its own Docker workspace
Availability: InStock
Author: dimileeh

by dimileeh·Jun 16, 2026·5 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerWizardryZero to OneSolve My Problem

Runs agent swarms without collisions—each task gets isolated Docker + auto-merge loops.

Strengths

•Isolated git worktree plus Docker Compose per agent prevents shared state and credential leaks.
•Autonomous PR-monitor loop handles review comments, CI fixes, base sync, and auto-merge.
•Operator console shows live resource capacity and governed merge queue across parallel agents.

Weaknesses

•Alpha status with 14 open issues suggests rough edges in production workflows.
•Requires teams already using multiple coding agents—niche but growing audience.