Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.
mirrord is a Rust-built tool that runs a local process as though it were a pod inside a live Kubernetes cluster, routing the process's network traffic, file I/O, and environment variables through a real target pod without requiring a deployment. It supports Claude Code, Cursor, Codex CLI, and other AI coding agents, letting agents write and immediately test generated code against actual cluster services, real environment variables, and live queue contents within seconds. The integration is documented alongside ready-made workflow skills in the companion repository metalbear-co/skills. Beyond AI agents, developers can use mirrord through a VS Code extension, an IntelliJ plugin, or the CLI via `mirrord exec <command> --target pod/my-pod`. Technically, mirrord deploys an agent pod on the same node as the target, using Linux capabilities such as CAP_NET_ADMIN and CAP_SYS_PTRACE to mirror incoming traffic and intercept outgoing connections. Backend engineers, DevOps teams, and AI coding workflows that need real cluster context without disrupting shared environments are the primary beneficiaries.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
- ✓Documented (README)
git clone https://github.com/metalbear-co/mirrord && cp mirrord/*.md ~/.claude/agents/Subagents overview
What people ask about mirrord
What is metalbear-co/mirrord?
+
metalbear-co/mirrord is subagents for the Claude AI ecosystem. Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic. It has 5.2k GitHub stars and was last updated today.
How do I install mirrord?
+
You can install mirrord by cloning the repository (https://github.com/metalbear-co/mirrord) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is metalbear-co/mirrord safe to use?
+
Our security agent has analyzed metalbear-co/mirrord and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains metalbear-co/mirrord?
+
metalbear-co/mirrord is maintained by metalbear-co. The last recorded GitHub activity is from today, with 89 open issues.
Are there alternatives to mirrord?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy mirrord to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/metalbear-co-mirrord)<a href="https://claudewave.com/repo/metalbear-co-mirrord"><img src="https://claudewave.com/api/badge/metalbear-co-mirrord" alt="Featured on ClaudeWave: metalbear-co/mirrord" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.