Shubhamsaboo/awesome-llm-apps
This Apache-2.0 collection provides runnable agent, skill, MCP, memory, multi-agent, and RAG examples across major model providers, useful for borrowing patterns before choosing a stack.
The repository collects **100+ open-source** agents, skills, and RAG apps under **Apache-2.0**. Examples span single-file agents, production-style tool loops, background jobs, multi-agent teams, voice, generative UI, MCP, memory, and retrieval.
Use it as a pattern library: run the smallest example matching your problem, inspect its tool and state boundaries, then transplant only the useful plumbing. Provider coverage includes Claude, Gemini, GPT, DeepSeek, Llama, and Qwen.
The repository collects **100+ open-source** agents, skills, and RAG apps under **Apache-2.0**. Examples span single-file agents, production-style tool loops, background jobs, multi-agent teams, voice, generative UI, MCP, memory, and retrieval. Use it as a pattern library: run the smallest example matching your problem, inspect its tool and state boundaries, then transplant only the useful plumbing. Provider coverage includes Claude, Gemini, GPT, DeepSeek, Llama, and Qwen. Breadth is not production validation. The material says skills pass a security and eval CI gate, but provides no comparable reliability results for the wider app catalog; sensitive medical, financial, and mental-health examples need independent controls.
This provides a broad, runnable discovery layer for agent architectures, but the candidates show how quickly useful examples need narrowing into governed systems with durable evidence, bounded roles, and domain-specific verification. Its strongest role is therefore prototyping and comparison: reuse isolated plumbing after inspection, while treating catalog inclusion and skill CI as weaker evidence than workflow-level reliability, especially in sensitive domains.