linghungegeg/Linghun

What is it?

Key features

• 01Terminal UI where the model reads, edits and verifies code in your project
• 02File writes and shell commands gated by permissions and path checks
• 03Verification states distinguish PASS, PARTIAL, FAIL and unverified claims
• 04Code index and workspace snapshots to reduce repeated file reads
• 05Git stable points for checkpoints, rollback and handoff
• 06Per-role model routing and support for several provider API styles

Use cases

• Diagnosing and fixing a failing build or test suite in a local repository
• Making multi-file changes while keeping a Git checkpoint before risky edits
• Running a long task in the background and reviewing its evidence afterward
• Connecting a local internal tool to an AI coding session through the app bridge

Quick start

1. 1

   Install the CLI globally with npm

   npm install -g @linghun/cli
2. 2

   Start Linghun inside your project

   linghun
3. 3

   In Linghun, configure a model provider

   /model setup

Things to know

• !Requires Node.js 22 or newer.
• !Needs your own model provider API key to run the AI features.
• !The README describes Windows as the first-class platform.

Topics

FAQ

What is Linghun?

A local-first, evidence-first AI coding terminal that connects LLMs to real project files, tools, permissions, verification and context. Linghun is a TypeScript command-line coding assistant installed via npm as @linghun/cli. It runs in a terminal UI inside your project and lets a language model read code, edit files, run builds, tests and scripts, and inspect Git state, with file writes and shell commands going through a permission and path-safety layer.

Is Linghun free to use? What license does it have?

Linghun is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.

Is Linghun still maintained?

Updated within 6 months. The last commit to Linghun was on Aug 19, 2026.

What can I use Linghun for?

Diagnosing and fixing a failing build or test suite in a local repository Making multi-file changes while keeping a Git checkpoint before risky edits Running a long task in the background and reviewing its evidence afterward Connecting a local internal tool to an AI coding session through the app bridge

How do I install Linghun?

Install the CLI globally with npm: npm install -g @linghun/cli Start Linghun inside your project: linghun In Linghun, configure a model provider: /model setup

Where can I get Linghun?

The source code and installation instructions are on GitHub: https://github.com/linghungegeg/Linghun