Looplia

Skills-first agentic workflow automation for Human and AI Agents.
Powered by Claude Agent SDK.

Get Started View on GitHub

looplia

$ bun install -g @looplia/looplia-cli

# Install Looplia CLI globally

$ looplia init

# Initialize workspace with skills from marketplace

$ looplia run writing-kit —file article.md

# Transform content into a structured writing kit

Why Looplia?

A new approach to AI workflows — skills as first-class citizens, not rigid code.

Skills-First Architecture

Workflows declare skills + missions in natural language. Claude determines the best approach. No rigid agent definitions required.

Workflow-as-Markdown

Define workflows in readable YAML frontmatter + Markdown. Version control friendly, human-readable, easy to share and modify.

Build with AI

Describe what you want in plain English. looplia build generates a complete workflow definition automatically.

Sandbox Isolation

Each run creates an isolated sandbox with inputs, outputs, and logs. Pause and resume anytime with —sandbox-id.

How It Works

Skills-first architecture for intelligent workflow automation

⚡

Universal Skill Executor

Each workflow step runs in its own context via the Skill Executor. Every step uses the same pattern: skill: + mission:. Context offload keeps the main agent clean.

🧩

Plugin Architecture

Built-in plugins (looplia-core, looplia-writer) plus skills from default marketplaces (Anthropic, ComposioHQ). Install more via looplia skill add.

✓

Validation System

Hook-based validation tracks completion per step via validation.json. Sandbox isolation enables pause and resume with full execution context.

Workflow Executor Architecture - showing Universal Skill-Executor loading looplia-core and looplia-writer plugins, with sandbox validation

Writing Kit: Human Engagement in Action

See how domain skills transform content into creative fuel for writers. Each step produces structured output that the next step builds upon.

media-reviewer

Deep Analysis

Extracts themes, quotes, and key concepts from source material. Identifies patterns and relationships in the content.

→ summary.json

No more re-watching or re-reading to find that perfect quote

idea-synthesis

Creative Ideation

Generates creative hooks, writing angles, and thought-provoking questions. Builds on the analysis to spark ideas.

→ ideas.json

A brainstorming partner that never runs dry

writing-kit-assembler

Kit Assembly

Combines analysis and ideas into an actionable writing brief with outlines, angles, and source references.

→ writing-kit.json

Your creative brief, ready to inspire

---
name: writing-kit
version: 1.1.0
description: Transform content into a comprehensive writing kit

steps:
  # Step 1: Deep content analysis
  - id: summary
    skill: media-reviewer
    mission: |
      Deep analysis of content to extract key themes.
      Extract minimum 3 verbatim quotes, at least 5 key points.
    input: ${{ sandbox }}/inputs/content.md
    output: ${{ sandbox }}/outputs/summary.json

  # Step 2: Creative ideation (depends on analysis)
  - id: ideas
    skill: idea-synthesis
    mission: Generate creative hooks, angles, and questions.
    needs: [summary]
    input: ${{ steps.summary.output }}
    output: ${{ sandbox }}/outputs/ideas.json

  # Step 3: Assemble the writing kit (final deliverable)
  - id: writing-kit
    skill: writing-kit-assembler
    mission: Combine insights into an actionable writing brief.
    needs: [summary, ideas]
    input:
      summary: ${{ steps.summary.output }}
      ideas: ${{ steps.ideas.output }}
    output: ${{ sandbox }}/outputs/writing-kit.json
    final: true
---

Not replacing writers, empowering them.

Looplia handles the research grunt work so humans can focus on what they do best: crafting compelling narratives.

Multi-Provider Support

Choose your AI provider. Switch models with a single command.

export ANTHROPIC_API_KEY=sk-ant-...
looplia run writing-kit --file article.md

# Run GLM-4.7 cloud model locally
looplia config provider preset OLLAMA_GLM47_CLOUD
export OLLAMA_API_KEY=ollama  # Optional, defaults to "ollama"
looplia run writing-kit --file article.md

# Use OpenRouter with dashboard-configured preset
looplia config provider preset OPENROUTER_PRESET
export OPENROUTER_API_KEY=sk-or-v1-...
looplia run writing-kit --file article.md
# Models configured at: https://openrouter.ai/settings/presets

looplia config provider preset ZENMUX_MINIMAX_M21
looplia config provider set auth-token sk-xxx
looplia run writing-kit --file article.md

Model Presets

Anthropic, Claude Code Subscription, Ollama, OpenRouter, and ZenMux. See all presets.

Cost Optimization

Switch between providers based on cost, speed, or capability requirements per workflow.

Skill Registry

Skills from curated marketplaces, ready to use.

Default Marketplaces

Skills from Anthropic and ComposioHQ installed automatically.

Third-party Skills

Add community marketplaces with looplia registry add. Install individual skills with looplia skill add.

Selective Loading

Declare required skills in workflow skills: field. Only needed skills are loaded, reducing context usage.

Get Started

From zero to first workflow in under 5 minutes.

Installation Set up Looplia and configure your API keys.

Quick Start Run your first workflow in 5 minutes.

CLI Reference Complete command reference for init, run, build, and config.

Understanding Workflows Learn the skills-first workflow architecture.

Skill Registry Discover and install skills from marketplaces.