Optio: Orchestrating AI Coding Agents in Kubernetes from Ticket to PR

Optio is an open-source orchestration system for AI coding agents that manages the complete workflow from task intake to merged pull request without requiring constant human supervision. Built with Fastify, Next.js, BullMQ, and Drizzle on Postgres, it ships with a Helm chart for production deployment.
How It Works
The system follows a three-stage pipeline:
- Intake – Pulls tasks from GitHub Issues, Linear, or manual creation
- Execution – Spins up isolated Kubernetes pods per repo, runs Claude Code or Codex in git worktrees
- PR Monitoring – Watches CI checks, review status, and merge readiness every 30 seconds
The key differentiator is the feedback loop. When CI breaks, Optio feeds the failure back to the agent. When a reviewer requests changes, the comments become the agent's next prompt. It continues until the PR merges or you manually stop it.
Architecture and Features
Optio uses a pod-per-repo architecture with one long-lived Kubernetes pod per repository. Each pod maintains git worktree isolation for multiple concurrent tasks. The system includes:
- Self-healing – Auto-resumes the agent on CI failures, merge conflicts, or reviewer change requests
- Completion automation – Squash-merges the PR and closes the linked issue when all checks pass
- Per-repo configuration – Model selection, prompt templates, container images, concurrency limits, and setup commands tunable per repository
- Code review agent – Automatically launches a review agent as a subtask with separate prompt and model
- Real-time dashboard – Live log streaming, pipeline progress, cost analytics, and cluster health monitoring
Technical Implementation
The architecture consists of three main components:
- Web UI (Next.js on port 3100) with dashboard, task management, and live streaming
- API Server (Fastify) with workers for task queue, PR watcher, health monitoring, and ticket sync
- Kubernetes cluster with repo pods containing multiple worktrees running AI agents
Services include repo pool management, review agent execution, and authentication/secrets handling, all backed by Postgres for tasks, logs, and events.
📖 Read the full source: HN AI Agents
👀 See Also

Clash of Agents: An MMA Arena for Testing Autonomous AI Agent Behavior
Clash of Agents is an experiment where autonomous AI agents compete in an MMA fighting arena with turn-based combat, post-fight analysis, and social interactions. Agents register, choose fighting disciplines, train stats, and fight with 21 real MMA moves and a combo system.

Claude Plugins: Computer Vision, Multi-Agent Council, and Self-Debugging Workflow
Three Claude plugins were released: Computer Vision v1.7.0 for Windows app automation, The Council v3.1.0 for adversarial multi-agent consultation, and Upwork Scraper v0.2.0 for job market analysis. A demonstration showed Claude using these plugins to diagnose and fix its own Solitaire automation bug.

AI Token Monitor: macOS Tool Tracks Local Claude Usage and Cost
A developer built AI Token Monitor, a macOS menu bar app that reads local Claude session files to track token usage, model distribution, and cost equivalents without API keys. The open-source tool revealed 6.5M tokens ($4,924 at API pricing) over 35 days in one user's case.

Building CLIs for AI Agents: Design Principles from Google's gws CLI
Google's gws CLI demonstrates how to design command-line interfaces specifically for AI agents, prioritizing raw JSON payloads over human-friendly flags and implementing safety rails against hallucinations.