Lineman lives inside Claude Code, not beside it. It installs as a plugin and sits quietly on the data-heavy tool calls your model already makes: file reads, build and test output, code search, web fetches. Instead of the raw dump, it hands back the parts that matter. Because it works at the tool layer, it doesn't care what you're building in.
Whatever language your project happens to be in, the work Lineman does is the same. A secondary model condenses bulky tool output before it reaches your primary model, so you spend context on reasoning rather than on scrolling. That's what keeps it language-agnostic by design.
One plugin, every language you already use
Lineman has no per-language setup. The same install covers the stacks teams ship every day:
- TypeScript, JavaScript, Node.js and the web frameworks on top: React, Next.js, Vue, Angular
- Python, Go, Rust for services, tooling, and systems work
- Java, Kotlin and Swift across server and mobile
- C, C++, C# for performance-critical and .NET codebases
- Ruby and PHP for web applications
A monorepo that mixes several of these is where Lineman earns its keep. A single large file read, a noisy test run, or a wide grep costs the same context whether it's Rust or Ruby, and Lineman compresses all of them the same way.
It rides on the tools, not the syntax
Lineman doesn't parse your project to "understand" a particular language. It intercepts the tool calls (reading a file, running a command, searching the tree, fetching a page) and returns a tighter result. New frameworks, generated code, config files, lockfiles, and logs all benefit without being special-cased. If Claude Code can call the tool, Lineman can compress what comes back.
Runs where Claude Code runs
The plugin is the same on macOS, Linux, and Windows. Every step runs inside a Claude Code session, so there's nothing platform-specific to configure. Install it once per machine, authenticate, and your next large file read or build triage goes through Lineman automatically.
Support for more editors and assistants is on the roadmap. For now, Claude Code is the home, and that's where the savings show up across whatever you happen to be working in.
See the savings on your stack
The savings come from how much data-heavy work you do, not which language you do it in, so the best way to size them is against your own workload. The savings calculator on the homepage estimates what Lineman would trim from your real usage, and the full method is on the benchmarks page. Pricing for individuals and teams is on the pricing page, and you can start a trial without a card.