axon-core

axon-core / axon

Public

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

agentic-ai agentic-coding ai ai-agents ci-cd
53
8
100% credibility
Found Feb 10, 2026 at 24 stars 2x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

Axon enables running autonomous AI coding agents like Claude Code, Codex, and Gemini in isolated Kubernetes pods for safe, scalable code tasks triggered manually or automatically from GitHub issues or schedules.

How It Works

1
🔍 Discover Axon

You hear about a helpful tool that lets smart assistants safely improve your code projects without any risk to your computer.

2
⚙️ Easy setup

With one simple command, you add the tool to your setup and connect your code folder and thinking helper.

3
💡 Give a task

You simply describe what needs fixing, like 'add safety checks to the login', and launch it.

4
👀 Watch it work

You see the assistant grab your code, make changes step by step, and test everything in its own safe space.

5
🚀 Review results

It finishes by sharing a ready-to-review update link, so you can check and approve the smart fixes.

6
Go automatic?
🔄
Keep manual

Run tasks whenever you need quick help on specific issues.

⏰
Set automatic

Let it scan for open problems and handle routine fixes without you lifting a finger.

🎉 Smarter code

Your projects get better faster, with safe, reliable help from AI that works just like a teammate.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 24 to 53 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is axon?

Axon runs autonomous AI coding agents like Claude Code, OpenAI Codex, and Google Gemini in isolated Kubernetes pods, giving them full permissions without host risks. You define tasks via CLI (`axon run "fix bug #42"`) or CRDs, and it handles ephemeral workspaces cloned from Git repos, even auto-pushing PRs with GitHub tokens. Built in Go on Kubernetes CRDs, it scales agents across CI pipelines or repos, tracking phases like Pending to Succeeded.

Why is it gaining traction?

It unlocks "dangerously skip permissions" safely in pods, unlike local runs that risk your machine, while TaskSpawners auto-turn GitHub issues (filtered by labels) into fix tasks or cron jobs. Developers hook it into Argo or Helm for hands-free refactoring at scale, with observable logs and zero deps beyond a cluster. Stands apart from tools like GitHub Copilot by enabling fully autonomous loops, akin to AI run autonomous labs accelerating code optimization.

Who should use this?

Platform engineers building internal dev portals for self-service AI code gen. CI/CD teams automating bug triage from issues into PRs. Kubernetes operators scaling agent workloads across microservices, like nightly test fixes or batch refactors.

Verdict

Grab it if you're on Kubernetes and want safe, scalable AI agents—CLI and CRDs make it dead simple to try. At 1.0% credibility (18 stars, solid docs/tests but early stage), productionize cautiously; fork or watch for task chaining roadmap.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.