Inaricode — AI skill for Claude Code
InariCode — TypeScript CLI for an AI coding assistant: multi-provider chat (Claude, OpenAI, Kimi, Ollama, …), Rust engine tools, optional YAML config with per-provider keys, inari cursor (Cursor Cloud.
How to install Inaricode
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open kyuna0312/inaricode and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Inaricode does
InariCode — TypeScript CLI for an AI coding assistant: multi-provider chat (Claude, OpenAI, Kimi, Ollama, …), Rust engine tools, optional YAML config with per-provider keys, inari cursor (Cursor Cloud Agents), and inari providers.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Ataru — High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus 351 ★
- Engrim — The Universal Cross-Model Episodic Memory Standard 219 ★
README
INARI CODE 🦊
A modular, terminal-based AI development system integrating tmux, LazyVim, and OpenCode.
Concept
INARI CODE provides a clean developer workflow with:
- Tmux workspaces - Pre-configured tmux sessions for development, debugging, code review
- LazyVim integration - AI-powered keymaps for code refactoring and fixes
- OpenCode AI - Prompt-based code generation, refactoring, and bug fixes
Architecture
inari-code/
├── cli/inari # CLI tool
├── core/
│ ├── tmux/ # Workspace scripts
│ │ ├── dev.sh # Development session
│ │ ├── debug.sh # Debug session
│ │ ├── review.sh # Code review session
│ │ └── test.sh # Test session
│ ├── nvim/lua/plugins/ # LazyVim plugins
│ │ └── ai-keymaps.lua # AI keymaps
│ └── ai/
│ ├── ai.sh # AI wrapper
│ └── prompts/ # Prompt templates
├── workflows/ # YAML workflows
└── docs/
└── DEVELOPMENT.md # 6-month plan
Installation
git clone https://github.com/yourrepo/inari-code.git
cd inari-code
chmod +x install.sh
./install.sh
Add to PATH:
echo 'export PATH="$HOME/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc
Quick Start
inari dev # Start development workspace
inari status # Show active sessions
inari help # Show help
Commands
| Command | Description |
|---|---|
inari dev |
Start dev workspace (nvim + opencode + npm run dev + test) |
inari debug |
Start debug workspace (logs + terminal + nvim) |
inari review |
Start code review (nvim + git log + opencode) |
inari test |
Start test workspace (npm test + nvim) |
inari status |
Show active sessions |
inari config |
Show/set configuration |
inari list |
List available workflows |
Configuration
# Set project directory
in
Related Skills
Agent Rs
Pure-Rust async runtime for LLM agents. Multi-provider (Anthropic/OpenAI/Ollama), tool-capable end-to-end, str
Reql
REQL – A graph-native code index engine for agents. Scans Python, TypeScript, Go, Rust, Java, and 30+ language
Polyglot Refactor
Semantic, AST-safe multi-language code refactoring engine for AI agents and developers (Kotlin, Swift, TypeScr
Ovo Local LLM
A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-devi
Ollama Cc Plugin
Use local/cloud ollama models from Claude Code as a second engine: read-only consult/review, agentic worktree-
Zenith
Self-hosted, local-first AI workspace on your own Ollama models — chat, a Claude-Code-class coding agent, deep
Related Agents
Provider Debugger
Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints
ZeroClaw Android
Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepS
Second Opinion
Gets an independent review from a NON-Claude model (via a local CLI such as kimi, or a local Ollama model) and