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

Agent-factory: A Claude Code Plugin for Persistent AI Sub-Agent Teams
Agent-factory is a Claude Code plugin that creates persistent sub-agent teams with distinct personalities and file-based memory. It scaffolds 2-5 agents per project through a conversational interview process, with each agent having specific roles like code review, tech debt tracking, or strategy.

Vyra: Intelligent Web Video Editor for Claude Agents via MCP
Vyra indexes footage so Claude can semantically search and edit video directly—supports motion graphics, music sync, smart masking, transcript editing, color grading, and 30+ effects.

MCP Server for Semantic Search in Obsidian Vaults
A developer built an MCP server that indexes Obsidian vaults into Qdrant with local embeddings, enabling semantic search instead of keyword matching. It chunks markdown by headings, uses BAAI/bge-small-en-v1.5 embeddings, and works with Claude Code, Cursor, Windsurf, or any MCP client.

Nudge: A local-first app that surfaces Claude-generated plans via contextual triggers
Nudge is a free, local-first iOS/Android app that lets you paste markdown plans (from Claude, ChatGPT, Notes) and attach triggers like time, location, Wi-Fi, inactivity, or one-time to surface them via local notifications.