GitHubGitHub RepoNeeds Review

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.

GitHub

Open Source Open Markdown Open JSON

Source Summary

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.

Practical Implication

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.

Agent-Ready Context

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.

Connected Context · Feed7 Judgment

This broadens the available design space for agents, skills, retrieval, memory, and tool loops, but changes discovery more than confidence: the catalog is useful for locating minimal reference implementations, not for inferring production readiness. Its stated skill gates provide a narrower trust signal than the repository’s breadth, leaving sensitive examples dependent on independent evaluation and controls.

VoltAgent/awesome-agent-skillsBoth serve as discovery indexes whose breadth requires selective inspection; this repository extends beyond skills into runnable application and orchestration patterns without resolving catalog-wide trust.MadsLorentzen/ai-job-searchThe job-search framework exemplifies how one catalog pattern becomes a bounded application with domain-specific review and artifact-verification loops.Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard DocumentsThe benchmark supplies the kind of domain-specific reliability evidence the wider catalog lacks and shows why specialized stages and verification matter in sensitive rule-heavy work.virgiliojr94/book-to-skillIt provides a concrete retrieval-to-skill pattern that can guide selection from the catalog, while defining when progressive disclosure is preferable to repeatedly loading source documents.

Context Map

agentcodingresearch#skills#multi-agent#retrieval

Uncertainty

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.