Lineark – Linear CLI and Rust SDK for Humans and LLMs

Name: Lineark – Linear CLI and Rust SDK for Humans and LLMs
Availability: InStock
Author: fb03

by fb03·Feb 15, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainSolve My ProblemNiche Gem

13K token MCP server replaced by 1K token CLI discovery for AI agents.

Strengths

•Solves real pain: agentic coding context bloat with smart, discoverable CLI interface.
•Codegen pipeline from Linear's GraphQL schema ensures SDK stays in sync without manual work.
•Dual UX design: human-readable output (tables/JSON auto-detection) + lean agent integration.

Weaknesses

•Unofficial Linear client — dependent on API stability; Linear could break it anytime.
•Still early (v0.8.6, 27 stars) — adoption and real-world edge cases TBD.

Post Description

lineark is an unofficial CLI and Rust SDK for Linear (the issue tracker). I built it because I use Claude Code heavily, and the Linear MCP server eats ~13K tokens of context just to describe its tools — before my agent does any actual work.

lineark takes a different approach: it's a CLI your agent calls via Bash. The full command reference (lineark usage) is under 1,000 tokens.

It's also just a nice CLI for humans — human-readable names instead of UUIDs, auto-detected output format (outputs tables in terminal/interactive session, JSON when piped).

Under the hood: the SDK is fully generated from Linear's GraphQL schema via a custom codegen pipeline (apollo-parser → typed Rust). The CLI consumes the SDK with zero raw GraphQL — just typed method calls. You can also create your own lean return data types and validate them against Linear's schema at comptime.

MIT Licensed.

Happy to answer questions. Thanks!