Open-source (Apache 2.0) Kubernetes UI with a built-in MCP server for AI agents: topology, events, Helm, GitOps and audits — on your laptop or in your cluster.
Radar is the missing Kubernetes interface for humans and agents: a UI optimised for people, and an MCP server optimised for AI agents, over the same live cluster.
It is open source, runs on your laptop or in your cluster, and needs no account — a single binary that makes sense of topology, events, Helm, GitOps and audits.
| Pricing | Open Source |
|---|---|
| Category | Coding & Development |
| Platforms | mac, windows, linux |
| Company | Skyhook |
| Best for | Kubernetes operators who want one interface for humans and agents over live clusters |
| Official website | radarhq.io |
The right coding tool depends on where you write code and how much of your codebase it can understand. IDE integration is the first filter — a tool that lives in your editor, sees your project files and respects your stack will help far more than a general chatbot you paste snippets into. Look for accurate completions, clear explanations of suggested changes, and strong refactoring and debugging support for your main languages. Privacy deserves real attention: check whether your code is used for training, and whether a self-hosted or enterprise option exists for sensitive projects. Price against the hours it actually saves — most developers feel the difference within the first week of real use.
Radar is the missing Kubernetes interface for humans and agents: a UI optimised for people, and an MCP server optimised for AI agents, over the same live cluster.
Radar offers Live resource topology graph for the whole cluster, Event timeline reaching past the default 1-hour TTL, GitOps visibility for Argo CD and Flux, including drift and diagnosis, Helm chart visibility and image internals, 44 best-practice cluster audit checks, framework-labelled, Built-in MCP server giving cluster context to Claude Code, Codex, Cursor and any MCP agent and Single binary install via Homebrew, Scoop, Krew, .rpm or direct download.
Radar is open source, so the software itself is free to download, use and self-host. Your only costs are the infrastructure you run it on and any paid services you connect to it.
Strengths of Radar include Free forever and open source under Apache 2.0; MCP server makes live clusters readable to AI agents; No account required to run it. On the downside, AI investigations live in the paid Radar Cloud tiers, not the free open-source build.
by Flatbread
Turns a coding-agent session into one shareable link: the prompt, every step, what broke, what fixed it, and the diff — readable by people and resumable by agents.
Best for: Developers running coding agents who want shareable, resumable records of what their agents actually did
Limitation: No pricing published on the official homepage
by MAO
Multi-agent orchestration canvas: Claude Code, Codex, Gemini and Grok work as a team on one canvas, handing work to each other through drawn wires.
Best for: Developers running several coding agents at once who want them coordinated instead of colliding
Pricing: Paid
Limitation: Each agent still needs its own login and subscription
by Arco
MIT-licensed Codex plugin (local MCP server plus panel UI) for browsing and editing GitHub and Linear issues and pulling issue context into your conversation.
Best for: Codex users who triage GitHub and Linear issues without leaving the conversation
Pricing: Open Source
Limitation: Requires a Codex desktop environment plus the codex CLI (and the gh CLI for GitHub) — not a standalone tool
by Polylane
Production-issue agents that learn what you run, detect issues from metrics, logs and traces, and fix what they can by opening pull requests.
Best for: Engineering teams tired of on-call pages who want production fixes to arrive as pull requests
Limitation: No pricing shown in the official site text fetched
by Entire
Git forge built for agent-human collaboration — pull requests are replaced by 'Trails', agent-scored evals on every push, with agent sessions and prompts searchable in the repo as Continuous Memory.
Best for: Teams building software with AI agents who want evals and agent context inside the repo
Pricing: Paid
Limitation: Pay-as-you-go — costs scale with model-provider rates
by Dedica
Checks whether AI agents can actually use your website — 125 free checks across discovery, access, usability and payments, a score out of 100, and one fix file per issue for your coding agent.
Best for: Website owners who want AI agents — and their users — to complete tasks on their site
Pricing: Freemium
Limitation: Fixes require the paid kit — the free tier only scores
