Awesome LLM Apps: Over 100 open-source agent templates and skills to run instantly
A curated repository containing over 100 open-source, Apache-2.0 licensed AI agents and skills. It features single-command integrations for tools like Claude Code, Cursor, and Codex, with step-by-step templates ranging from codebase analysis to system architecture reviews.
Impact: High
Why it matters
You can instantly add structured skills to your coding agents or spin up production-ready multi-agent teams with minimal configuration.
TL;DR
- 01Offers 100+ production-ready agent templates under a permissive Apache-2.0 license.
- 02Enables direct installation of skills into coding tools like Claude Code and Cursor via a single npx command.
- 03Includes hybrid multi-model orchestration examples combining Claude, GPT-5.6, and Gemini.
Key facts
- Total Templates
- 100+
- License
- Apache-2.0
Fast Integration with CLI
The library introduces a streamlined way to inject custom features into active coding agents. Using the npx skills add command, you can install specialized tools directly into agents operating in Claude Code, Codex, or Cursor. Each skill runs under an Apache-2.0 license and is verified through a dedicated CI gate.
For example, to quickly audit your codebase for abandoned or incomplete features, run:
npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyardDiverse Agent Templates
The repository hosts code for over 100 functional templates. These include:
- Scope Creep Detector: Evaluates a diff against its pull request description to prevent bloated branches.
- System Architect Agent: Uses DeepSeek R1 reasoning alongside Claude to run comprehensive architectural reviews.
- Advisor Orchestrator Worker: Implements a hierarchical agent loop using Claude, GPT-5.6, and Gemini 3.5 Flash.
All agents can be launched by cloning the repository, navigating to the target directory, and executing with local API environment variables.
Try it in 2 minutes
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_travel_agentbash
✓ When to use
- When you want to bootstrap a production RAG or multi-agent application quickly.
- When you need helper tools to analyze pull requests or code history inside agentic IDEs.
✕ When NOT to use
- If you require highly proprietary, pre-certified enterprise orchestration architectures with strict non-Apache licensing terms.
What to do today
- Clone the repository and test the local travel or data analysis agent.
- Add the Scope Creep Detector skill to your local Cursor or Claude Code setup.
Sources