HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
kelos-dev
kelos
Go2026–2026
kelos-dev / kelos

kelos

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

Systems & InfrastructureAI & Machine LearningDevOps & Cloud
Explore on GitHubRead Hacker News discussions
2Distinct people
13Mentions
0Explicit recommenders
358GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 1:49:46 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day13 dated mentions

Observed mentions: 2026-02-10 02:53:14 UTC to 2026-03-04 14:26:57 UTC.

0122026-02-10 00:00:00 UTC to 2026-02-11 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsFeb 102026-02-11 00:00:00 UTC to 2026-02-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-12 00:00:00 UTC to 2026-02-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-13 00:00:00 UTC to 2026-02-14 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-02-14 00:00:00 UTC to 2026-02-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-15 00:00:00 UTC to 2026-02-16 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 comments2026-02-16 00:00:00 UTC to 2026-02-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-17 00:00:00 UTC to 2026-02-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-18 00:00:00 UTC to 2026-02-19 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 comments2026-02-19 00:00:00 UTC to 2026-02-20 00:00:00 UTC (exclusive): 2 mentions; 2 submissions, 0 comments2026-02-20 00:00:00 UTC to 2026-02-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-21 00:00:00 UTC to 2026-02-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsFeb 212026-02-22 00:00:00 UTC to 2026-02-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-23 00:00:00 UTC to 2026-02-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-24 00:00:00 UTC to 2026-02-25 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-02-25 00:00:00 UTC to 2026-02-26 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-02-26 00:00:00 UTC to 2026-02-27 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-02-27 00:00:00 UTC to 2026-02-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-28 00:00:00 UTC to 2026-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-01 00:00:00 UTC to 2026-03-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-02 00:00:00 UTC to 2026-03-03 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-03-03 00:00:00 UTC to 2026-03-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-04 00:00:00 UTC to 2026-03-05 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsMar 4

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 102026-02-10 00:00:00 UTC2026-02-11 00:00:00 UTC110
Feb 112026-02-11 00:00:00 UTC2026-02-12 00:00:00 UTC000
Feb 122026-02-12 00:00:00 UTC2026-02-13 00:00:00 UTC000
Feb 132026-02-13 00:00:00 UTC2026-02-14 00:00:00 UTC110
Feb 142026-02-14 00:00:00 UTC2026-02-15 00:00:00 UTC000
Feb 152026-02-15 00:00:00 UTC2026-02-16 00:00:00 UTC211
Feb 162026-02-16 00:00:00 UTC2026-02-17 00:00:00 UTC000
Feb 172026-02-17 00:00:00 UTC2026-02-18 00:00:00 UTC000
Feb 182026-02-18 00:00:00 UTC2026-02-19 00:00:00 UTC211
Feb 192026-02-19 00:00:00 UTC2026-02-20 00:00:00 UTC220
Feb 202026-02-20 00:00:00 UTC2026-02-21 00:00:00 UTC000
Feb 212026-02-21 00:00:00 UTC2026-02-22 00:00:00 UTC000
Feb 222026-02-22 00:00:00 UTC2026-02-23 00:00:00 UTC000
Feb 232026-02-23 00:00:00 UTC2026-02-24 00:00:00 UTC000
Feb 242026-02-24 00:00:00 UTC2026-02-25 00:00:00 UTC110
Feb 252026-02-25 00:00:00 UTC2026-02-26 00:00:00 UTC101
Feb 262026-02-26 00:00:00 UTC2026-02-27 00:00:00 UTC110
Feb 272026-02-27 00:00:00 UTC2026-02-28 00:00:00 UTC000
Feb 282026-02-28 00:00:00 UTC2026-03-01 00:00:00 UTC000
Mar 12026-03-01 00:00:00 UTC2026-03-02 00:00:00 UTC000
Mar 22026-03-02 00:00:00 UTC2026-03-03 00:00:00 UTC110
Mar 32026-03-03 00:00:00 UTC2026-03-04 00:00:00 UTC000
Mar 42026-03-04 00:00:00 UTC2026-03-05 00:00:00 UTC110

What Hacker News says

13 sources
gjkim042·Mar 4, 2026Submission

Show HN: Kelos – Run Claude —dangerously-skip-permissions on Kubernetes

Kelos is a Kubernetes framework for orchestrating autonomous coding agents. It runs Claude Code, Codex, Gemini, OpenCode, or custom agents safely in isolated, ephemeral pods. The idea is that you define your everyday development workflows as YAML and let them run continuously on Kubernetes. Agent tasks are Kubernetes CRDs, so things like: - Watch for “bug” issues → auto-draft a fix PR - Auto-review incoming pull requests - Auto-triage new issues with labels and priority - Periodically scan the codebase → propose improvements - Test the project as a new user → surface rough edges Kelos is using this on itself. The self-development pipeline picks up open issues, investigates them, opens or updates a PR, self-reviews, and retries if CI fails. When the agent gets stuck, it labels the issue needs-input and stops: https://github.com/kelos-dev/k
Read the rest
elos/tree/main/self-developmen... I still do the final review and manually merge PRs, but it’s been quite helpful. https://github.com/kelos-dev/kelos Happy to answer questions about the design or what’s broken.
2 points · Open discussion
gjkim042·Mar 2, 2026Submission

Show HN: Kelos – Define your AI coding agent workflow as YAML on Kubernetes

Kelos is a Kubernetes framework for orchestrating autonomous AI coding agents (like Claude Code) in ephemeral pods. The original goal was sandboxing — I didn't want to run agents with --dangerously-skip-permissions locally. But the real unlock turned out to be declarative workflows. You define agent tasks as Kubernetes CRDs, things like: - Watch for "bug" issues → auto-draft a fix PR - Auto-review incoming pull requests - Auto-triage new issues with labels and priority - Periodically scan the codebase → propose improvements - Test the project as a new user → surface rough edges Self-development pipeline: https://github.com/kelos-dev/kelos/tree/main/self-developmen... I've been using Kelos to develop Kelos. When something breaks, I refine the YAML or add features to the controller. It's early and rough around the edges, but the core loop w
Read the rest
orks. Happy to answer questions about the design or what's broken.
4 points · Open discussion
gjkim042·Feb 26, 2026Submission

Show HN: I run a team of AI agents on my Kubernetes cluster

I built Axon, an open-source Kubernetes controller that turns AI coding agent runs into a declarative API. I can define my development workflow in YAML so that Axon handles the rest — isolation, credentials, git workspace, agent plugins, output capture. I use it to develop Axon itself. I run a team of specialized agents on my cluster, each with a different job: Workers — Watch for GitHub issues, pick them up, investigate, write code, open PRs, self-review, and iterate until CI passes. If an agent gets stuck, it pauses and asks for my feedback. I respond on the issue, and it picks back up. Fake User — Runs daily. Pretends to be a new developer trying Axon for the first time. Reads the README, tries CLI commands, reviews error messages. When it finds rough edges, it files issues. This catches things I’d never notice as the author. Strategis
Read the rest
t — Runs twice a day. Thinks about new use cases, integrations, and API improvements. Reads the codebase, checks recent activity, and proposes ideas as issues. Some of the best feature ideas in Axon’s backlog came from this agent. Triage — Classifies new issues by type, checks if they’re already fixed, detects duplicates, and posts a triage report. The whole setup is YAML files you can kubectl apply on your own cluster. Repo: https://github.com/axon-core/axon Self-development pipeline: https://github.com/axon-core/axon/tree/main/self-development It’s not magic though. The workers produce mediocre PRs sometimes and I still do the final review before merging. The fake user occasionally files issues that make no sense. The strategist sometimes suggests things that already exist. But even with the noise, it improves itself pretty well.
2 points · Open discussion
gjkim042·Feb 24, 2026Submission

Show HN: Axon – A Kubernetes-native framework for AI coding agents

Hi HN, I originally started this project simply to safely run autonomous coding agents (like Claude in auto-mode) in isolated environments. But as I built it, I realized the potential was much bigger than just sandboxing: it's about making a coding agent callable like a standard API, and ultimately, defining your entire development workflow as infrastructure. Axon is a Kubernetes-native framework that abstracts the coding agent itself. By standardizing the container interface, you can seamlessly plug in Claude, Codex, Gemini, OpenCode, or your own custom images without changing your orchestration. How it works under the hood: The architecture relies on standard K8s CRDs (Tasks, Workspaces, TaskSpawners, and AgentConfigs). A Task is the fundamental unit of work for a coding agent. When a Task is created, Axon spins up an ephemeral Pod with
Read the rest
a freshly cloned git workspace to execute it. You use an AgentConfig to declaratively define the specific rules, custom skills, and MCP (Model Context Protocol) servers the agent is allowed to access during that Task. A TaskSpawner reacts to GitHub events (like a new issue or PR) and automatically generates these Tasks on the fly. Deterministic outputs (branch names, PR URLs, token usage) are captured directly back into the K8s resource status. To test this, I built a fully autonomous self-development pipeline. It actively triages issues, suggests new features, finds bugs, and writes the code to fix them. It uses standard GitHub issues and PR comments as the feedback loop to guide the agents. You can see how that is wired together here: https://github.com/axon-core/axon/tree/main/self-development The main repo is here (with demo video): https://github.com/axon-core/axon I’d love to get your real-world feedback—especially on the CRD design, the container abstraction model, and what new features you would need to actually integrate this into your workflows.
1 points · Open discussion
gjkim042·Feb 19, 2026Submission

Show HN: Axon – Let coding agents develop their own framework on Kubernetes

I started Axon to run claude --dangerously-skip-permissions safely — just isolate it in an ephemeral K8s Pod and the flag isn’t dangerous anymore. It grew into an orchestration tool. You apply a Task, Axon spins up an isolated Pod, the agent works autonomously, and you get back a PR link, branch name, and exact cost in USD. TaskSpawner can watch GitHub Issues and spawn agents automatically. I use Axon to develop Axon itself — agents pick up issues, open PRs, and self-review: https://github.com/axon-core/axon/blob/main/self-development... Written in Go, Apache 2.0. Would love feedback on the approach.
3 points · Open discussion
gjkim042·Feb 18, 2026
Hello HN, I built Axon because I wanted to run Claude Code fully autonomously but didn't want to give it free reign over my laptop. The insight was simple: Kubernetes already solves the hard problems. Isolation? Pods. Ephemeral environments? Jobs. Credential scoping? RBAC + Secrets. Scheduling dozens of agents? That's just scheduling. So --dangerously-skip-permissions inside an ephemeral Pod isn't actually dangerous — the blast radius is zero for the host. Axon is a Kubernetes controller (a few CRDs, no external dependencies) that wraps AI coding agents as Jobs. You apply a Task, Axon spins up an isolated Pod, the agent works autonomously, and you get back a branch name, PR URL, and exact cost in USD. The part I'm most excited about is TaskSpawner. It polls GitHub Issues and creates a Task for each match. I use this to develop Axon itself
Read the rest
— every open issue gets picked up by an agent that investigates, opens a PR, and self-reviews. If it gets stuck, it labels the issue axon/needs-input and stops. Remove the label, it re-queues on the next poll. The full setup is here: https://github.com/axon-core/axon/blob/main/self-development... Current state: Claude Code is the primary agent today. The agent type is pluggable (single switch in job_builder.go) and I added Codex, Gemini CLI, and OpenCode support. Written in Go, Apache 2.0 licensed — fully open source. A few things I'd genuinely love feedback on: * Is the CRD design (Task / Workspace / AgentConfig / TaskSpawner) intuitive or over-abstracted? * Would a web UI add value, or is kubectl + CLI enough for this kind of tool? * Anyone running autonomous agents in production today? Curious what problems you've hit. Happy to answer questions about the architecture or the experience of letting agents develop their own framework. Contributions welcome!
In Show HN: Axon – Run autonomous coding agents(Claude, Codex) safely on Kubernetes
gjkim·Feb 10, 2026Submission

Show HN: K8s controller to sandbox Claude Code (merged 47 PRs to itself)

Hi HN, I'm the author of Axon. I built this because I wanted to use agentic tools like Claude Code, but I was worried about running claude with --dangerously-skip-permissions on my local machine. Axon is a Custom Resource Definition (CRD) that spins up ephemeral Pods for every agent task. It creates a safe blast radius. The Dogfooding: To test it, I used Axon to develop Axon. Over this weekend, I ran agents that read the repo, implemented features/fixes, and opened PRs. I merged 47 of them. It feels like having a team of juniors working in parallel. The repo is written in Go. I'd love feedback on the controller architecture or the CRD design.
1 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.