Optio – Orchestrate AI coding agents in K8s to go from ticket to PR
I think like many of you, I've been jumping between many claude code/codex sessions at a time, managing multiple lines of work and worktrees in multiple repos. I wanted a way to easily manage multiple lines of work and reduce the amount of input I need to give, allowing the agents to remove me as a bottleneck from as much of the process as I can. So I built an orchestration tool for AI coding agents:Optio is an open-source orchestration system that turns tickets into merged pull requests using AI coding agents. You point it at your repos, and it handles the full lifecycle:- Intake — pull tasks from GitHub Issues, Linear, or create them manually- Execution — spin up isolated K8s pods per repo, run Claude Code or Codex in git worktrees- PR monitoring — watch CI checks, review status, and merge readiness every 30s- Self-healing — auto-resume the agent on CI failures, merge conflicts, or reviewer change requests- Completion — squash-merge the PR and close the linked issueThe key idea is the feedback loop. Optio doesn't just run an agent and walk away — when CI breaks, it feeds the failure back to the agent. When a reviewer requests changes, the comments become the agent's next prompt. It keeps going until the PR merges or you tell it to stop.Built with Fastify, Next.js, BullMQ, and Drizzle on Postgres. Ships with a Helm chart for production deployment.
FL score
out of 100
Verdict
high confidence
Competition
7
competitors found, emerging market, funded players
Trend
No signal yet
An open-source K8s-native orchestration system for AI coding agents to automate the full ticket-to-PR lifecycle with self-healing feedback loops.
The pain
The gap
Build angle
Strengths
- Addresses a real, daily pain point for developers adopting AI coding agents.
- Highly specific and unserved niche: K8s-native, open-source, end-to-end orchestration with self-healing feedback loops.
- Strong future relevance as AI agent adoption grows.
- Deep creator fit and understanding of the problem.
- Initial validation with a Show HN launch.
Risks
- High build and maintenance complexity for a solo builder.
- Market is crowded with heavily funded competitors (Devin, Copilot, Cursor) who could pivot or expand capabilities.
- Open-source monetization strategy requires careful planning and execution beyond core product development.
- Requires user trust in autonomous AI agents, which is still evolving.
- Dependency on external AI models (Claude, OpenAI) introduces potential cost and API stability risks.
Next steps
- Gather in-depth feedback from early users (from Show HN) to validate specific pain points addressed by the feedback loop and K8s integration.
- Clearly define the minimum viable paid feature for enterprise customers (e.g., advanced security, custom integrations) that goes beyond the open-source core.
- Explore partnerships with K8s platforms or cloud providers to facilitate distribution and potential managed service offerings.
- Start building a community around the open-source project to drive contributions and adoption, leveraging K8s and developer forums.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 26
- Solution gap
- 17
- Willingness to pay
- 14
- Buildability
- 8
Optio addresses a real and specific pain point for developers using AI coding agents, particularly those in K8s environments, with a unique angle on automated feedback loops. The market is crowded but there's a niche; however, the build complexity for a solo founder is high.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
Optio presents a compelling value proposition in a growing market, but faces challenges with build complexity and the need for clear monetization against well-funded incumbents.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Optio is strong on problem clarity and creator fit within a specific niche but faces challenges with inherent system complexity and open-source monetization strategies for a solo builder.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Optio has a clear value prop for a specific, reachable audience and has initiated validation, but its open-source business model and market assumptions carry some risk.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Optio addresses a critical, growing pain for specific developers, with a clear, valuable narrow wedge, poised to become more essential as AI coding matures.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- Gather in-depth feedback from early users (from Show HN) to validate specific pain points addressed by the feedback loop and K8s integration.
- Clearly define the minimum viable paid feature for enterprise customers (e.g., advanced security, custom integrations) that goes beyond the open-source core.
- Explore partnerships with K8s platforms or cloud providers to facilitate distribution and potential managed service offerings.
- Start building a community around the open-source project to drive contributions and adoption, leveraging K8s and developer forums.
Who is already there, emerging market
An autonomous AI software engineer that plans, executes, and debugs complex engineering tasks with minimal human input.
Pricing: Core plan: Starts at $20/month (pay-as-you-go, $2.25 per ACU). Team plan: $500/month (includes 250 ACUs, $2.00 per ACU). Enterprise: Custom pricing.
An AI-first IDE that offers code completion, chat-based assistance, and multi-file editing with AI agents.
Pricing: Hobby: Free (limited Agent requests and Tab completions). Pro: $20/month ($16/month billed yearly) for individuals, with a monthly credit pool. Pro+: $60/month ($48/month billed yearly) for 3x credit usage. Ultra: $200/month for 20x usage and priority access. Teams: $40/user/month ($32/user/month billed yearly). Enterprise: Custom pricing.
An AI-powered environment for multi-file editing, code generation, code review, and issue resolution directly within GitHub and various IDEs.
Pricing: Copilot Free: $0 (limited completions and premium requests). Copilot Pro: $10/month or $100/year (unlimited completions, 300 premium requests). Copilot Pro+: $39/month or $390/year (everything in Pro, 1,500 premium requests, priority access). Copilot Business: $19/user/month. Copilot Enterprise: $39/user/month.
A platform that empowers users to design and manage intelligent agents to perform tasks using natural language instructions across various software tools and APIs.
Pricing: Free Tier: $0. Pro Plan: $49/month. Business: $199/month. Enterprise: Custom pricing. API: Pay-as-you-go. (Note: Some sources indicate pricing is not publicly released and is enterprise-model based, requiring direct contact for quotes).
An AI-native development environment and advanced AI coding assistant that keeps developers in flow.
Pricing: Starts around $15 per seat, using "premium model credits" with usage caps.
A terminal-native coding agent with a VS Code extension, focusing on agent orchestration and code quality.
Pricing: $20/month.
A Rust-built, open-source terminal agent that offers interactive, agentic coding with configurable approval modes, as well as cloud-based agentic execution through OpenAI's platform.
Pricing: Included with ChatGPT Plus ($20/month). Costs are usage-based (tokens/API calls) when used via API.
What they charge
Recent news
- Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR
Hacker News, March 25 2026
- Kubernetes Builds a Sandbox CRD for AI Agents - Cloud Native Now
Cloud Native Now, March 25 2026
- CNCF Nearly Doubles Certified Kubernetes AI Platforms - PR Newswire
PR Newswire, March 24 2026
- Emergent Runs 30000 AI Coding Environments on Kubernetes. Here's Why That Matters
VentureBeat, March 09 2026
- Kelos: Orchestrating Autonomous AI Coding Agents on Kubernetes - DEV Community
DEV Community, March 15 2026
Market signals
The market for orchestrating AI coding agents, particularly in Kubernetes environments for end-to-end development workflows (ticket to PR), is rapidly growing. This is evidenced by recent investments in AI coding platforms, the emergence of specialized AI agent orchestration tools, and the Kubernetes community's efforts to create specific support for AI agents. The trend indicates a shift towards AI workers participating autonomously in software systems, demanding robust infrastructure and orchestration capabilities.
What frustrates people
- AI suggestions can be repetitive or 'sticky'.
- Difficulty maintaining context across multi-repo or deeply interconnected systems (e.g., microservices, monorepos).
- Integration fatigue and rising usage-based costs.
- Debugging across distributed systems lacks depth.
- Lack of transparency and predictability in pricing, especially with usage-based models and hidden costs.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “Optio – Orchestrate AI coding agents in K8s to go from ticket to PR”.