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

Audacity-MCP: Claude AI Integration for Local Audio Editing with 131 Tools
Audacity-MCP connects Claude to Audacity via pipe interface, enabling voice-controlled audio editing with 131 tools, 9 automated pipelines, and local Whisper transcription without cloud dependencies.

bareguard: A Lightweight Safety Gate for AI Agents — Now on npm
bareguard v1.0 is a ~1000-line, single-dependency safety layer for AI agents that blocks destructive actions (rm -rf, DROP TABLE) and enforces budget limits with human escalation. Part of the bare suite, live on npm.

PocketBot: A Local AI Autopilot for iOS Using App Intents and On-Device Inference
PocketBot is an iOS app that runs a quantized 3B Llama model locally on iPhone's Neural Engine via Metal, using Apple's AppIntents and CoreLocation frameworks to create event-driven automations without cloud data transmission.
Claude Code vs Codex: 36 vs 28 files, $2.50 vs $2.04, infinite loop caught — real-world comparison
A developer runs the same two tasks on Claude Code and Codex (Cursor): PR triage bot and real-time code review UI. Results: 36 vs 28 files, $2.50 vs $2.04 cost, Claude produced fewer TypeScript errors, Codex had an infinite React loop.