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

Selfware: Rust-based local AI agent framework with PDVR architecture
Selfware is an open-source AI agent framework built in Rust for local inference, implementing a PDVR cognitive cycle with 54 built-in tools and designed for long-running tasks on consumer hardware.

Using an MCP Server to Optimize React Native Apps with Claude Code
An MCP server streams live runtime data from a React Native app into Claude Code, identifying performance issues like Zustand store thrashing and unnecessary re-renders.

Portable Mind Format (PMF): Provider-Agnostic Agent Specification with 15 Open-Source Agents
The Portable Mind Format (PMF) is a JSON-based specification for defining AI agent identities that can run across multiple models and providers, including Claude, GPT-4, Gemini, DeepSeek, and local models via Ollama. It includes 15 MIT-licensed production agents and converters for Claude Code, Cursor, GitHub Copilot, and Gemini CLI.

Building syntaqlite: A SQLite DevTools Project Created with AI Assistance
Lalit Maganti built syntaqlite, a set of developer tools for SQLite, over three months using AI coding agents after wanting it for eight years. The project required parsing SQL exactly like SQLite, which involves adapting SQLite's dense C codebase with over 400 grammar rules.