做AI的都该看看awesome-llm-apps。 不是因为118.2k star。 而是它把核心问题解决地很干净

100多个AI Agent和RAG应用，每个都能直接跑…我昨天clone了个客服机器人，配好API key贼钟就聊上了，不用自己从零搭框架。

覆盖场景巨全，从PDF问答到联网搜索、从自动化办公到多Agent协作都有。想找个参考实现直接抄，比自己翻文档硬啃快太多了。

每个项目都有清晰README和演示截图，踩坑成本极低。我试过好几个同类合集，大部分是摆设跑不起来，这个是真的能跑。

有技术基础的可以二次开发，小白照着文档跑也行。 这项目作者是某大厂AI工程师，把自己平时工作流里跑通的东西全开源了。 我翻了下commit记录，更新频率比很多商业产品还勤。 同样的方案要是找外包做，没个几万块下不来，等于白捡一套实战经验库。 你们手头有没有类似好用的AI应用合集，推荐几个我继续挖？

https://github.com/Shubhamsaboo/awesome-llm-apps…

#AI #AI工具老炮

Shubhamsaboo/awesome-llm-apps

Source: https://github.com/Shubhamsaboo/awesome-llm-apps

Awesome LLM Apps

100+ open-source AI agents, agent skills, and RAG apps. Hand-built, tested end-to-end, Apache-2.0.

Clone it, ship it, sell it - 100% free and open-source

Works with Claude, Gemini, GPT, DeepSeek, Llama, Qwen and other open-source models.

Step-by-step tutorials on Unwind AI · Quick start · Browse all templates

Project Graveyard	Insurance Claim Live Agent Team	AI Fraud Investigation Agent
Self-Improving Agent Skills	AI Home Renovation Agent	Always-on HN Briefing Agent

🚀 Run one now

Give your coding agent a new skill in 10 seconds:

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard

Then ask it: “why do I never finish my side projects?”

Or clone and run any agent in 30 seconds:

git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent
pip install -r requirements.txt
streamlit run travel_agent.py

📬 New templates drop weekly. Get them in your inbox on Unwind AI.

🙏 Thanks to our sponsors

Vorflux

Become a Sponsor

📂 Browse all templates

🧩 Agent Skills

Give your coding agent new abilities. One command to install, plain English to use. Every skill ships real code and passes a security + eval CI gate. Works with Claude Code, Codex, Cursor, and other coding agents. Browse all skills →

• ⚰️ Project Graveyard - Finds every side project you abandoned, tells you why each one died, and helps you finish the one worth going back to
• 🔭 Scope Creep Detector - Checks whether a diff grew beyond its stated intent and recommends what to keep, split, or justify
• 🏺 Commit Archaeologist - Reconstructs why a file or code region exists from its introducing commit, later edits, co-changes, and intent clues
• 🩺 Dependency Doctor - Checks a dependency manifest for standard-library pins, obsolete backports, unpinned entries, duplicate constraints, and yanked releases
• 🧠 Advisor Orchestrator Worker - Meta Loop with Claude Fable 5 as advisor, GPT-5.6 as orchestrator, and Gemini 3.7 Flash as worker
• ♾️ Self-Improving Agent Skills - Automatically optimize agent skills using Gemini and ADK

🌱 Starter AI Agents

Single-file agents that run with just an API key - a great place to start.

• 🎙️ AI Blog to Podcast Agent - Turn any blog URL into a narrated podcast episode
• ❤️‍🩹 AI Breakup Recovery Agent - An agent team that talks you through the post-breakup spiral
• 📊 AI Data Analysis Agent - Ask questions of any CSV or Excel file in plain English
• 🩻 AI Medical Imaging Agent - Diagnostic analysis of X-rays and scans with Gemini
• 😂 AI Meme Generator Agent (Browser) - Makes memes by driving a real browser, not an image API
• 🎵 AI Music Generator Agent - Prompt in, MP3 track out
• 🛫 AI Travel Agent (Local & Cloud) - Personalized day-by-day travel itineraries
• ✨ Gemini Multimodal Agent - Video analysis plus web search in one agent
• 🔄 Mixture of Agents - Multiple LLMs answer, one aggregates the best response
• 📊 xAI Finance Agent - Real-time stock analysis powered by Grok
• 🔍 OpenAI Research Agent - Multi-agent topic research with the OpenAI Agents SDK
• 🕸️ Web Scraping AI Agent - Describe what to extract and the agent scrapes it

🚀 Advanced AI Agents

Production-style agents with tools, memory, and multi-step reasoning.

• 🏚️ 🍌 AI Home Renovation Agent with Nano Banana Pro - Photos of your space in, renovation plan and photorealistic renders out
• 🧠 DevPulse AI - Multi-Agent Signal Intelligence - Aggregates and scores technical signals into a daily intelligence digest
• 🔍 AI Deep Research Agent - Comprehensive web research with the OpenAI Agents SDK and Firecrawl
• 📊 AI VC Due Diligence Agent Team - Multi-agent startup investment analysis with Gemini 3
• 🔬 AI Research Planner & Executor (Google Interactions API) - Multi-phase research with stateful conversations and auto-generated infographics
• 🤝 AI Consultant Agent - Market analysis and strategy recommendations with live web research
• 🏗️ AI System Architect Agent - Architecture reviews using DeepSeek R1 reasoning plus Claude
• 💰 AI Financial Coach Agent - Personalized budget, debt, and savings analysis
• 🎬 AI Movie Production Agent - Script drafts and casting ideas from a one-line movie concept
• 📈 AI Investment Agent - Stock comparison reports built on Yahoo Finance data
• 📡 Earnings Call Analyst Agent - Turns YouTube earnings calls into a playback-synced analyst workspace
• 🏋️‍♂️ AI Health & Fitness Agent - Tailored diet and workout plans from your goals
• 🚀 AI Product Launch Intelligence Agent - Go-to-market intelligence on competitor launches
• 🔍 AI Fraud Investigation Agent - Cross-references public records to flag facilities that don’t add up
• 🗞️ AI Journalist Agent - Researches, writes, and edits articles on any topic
• 🧠 AI Mental Wellbeing Agent - A coordinated agent team for mental health support plans
• 📑 AI Meeting Agent - Context, industry insights, and strategy briefs before you walk in
• 🧬 AI Self-Evolving Agent - Agents that rewrite their own workflows with EvoAgentX
• 👨🏻‍💼 AI Sales Intelligence Agent Team - Generates competitive sales battle cards in real time
• 🎧 AI Social Media News and Podcast Agent - Curates your trusted sources into briefs and generated podcasts
• 🌐 Openwork - Open Browser Automation Agent _{↗ external} - Open-source agent that operates a real browser
• 🛡️ Trust-Gated Multi-Agent Research Team - Every agent verified, every action in a hash-chained audit trail

🛰️ Always-on Agents

Background agents that run on schedules or events, monitor changing context, decide what needs attention, and proactively deliver updates, artifacts, or actions.

• 📰 Always-on Hacker News Briefing Agent - A scheduled scout that ships a ranked daily brief to Slack or email
• 📡 Release Radar Agent - Watches dependency releases and briefs you on breaking, deprecated, security, and major-version changes

🤝 Multi-agent Teams

Multiple agents collaborating to accomplish complex, cross-domain tasks.

• 🧲 AI Competitor Intelligence Agent Team - Structured competitor teardowns built from their own websites
• 💲 AI Finance Agent Team - A financial analyst team in 20 lines of Python
• 🎨 AI Game Design Agent Team - Full game concepts from a swarm of design specialists
• 🧭 AG2 Adaptive Research Team - Agent teamwork with routing and fallback, built on AG2
• 👨‍⚖️ AI Legal Agent Team (Cloud & Local) - Research, contract analysis, and strategy from a full legal bench
• 💼 AI Recruitment Agent Team - Resume screening to interview scheduling, end to end
• 🏠 AI Real Estate Agent Team - Property search, market analysis, and recommendations
• 👨‍💼 AI Services Agency (CrewAI) - A digital agency that scopes and plans your software project
• 👨‍🏫 AI Teaching Agent Team - A faculty of agents that builds your complete learning path
• 💻 Multimodal Coding Agent Team - Snap a photo of a coding problem, get a sandboxed solution
• ✨ Multimodal Design Agent Team - Design critiques from a Gemini-powered expert panel
• 🎨 🍌 Multimodal UI/UX Feedback Agent Team - Landing page feedback plus an auto-generated improved version
• 🌏 AI Travel Planner Agent Team - A complete trip itinerary, crafted by a team

🗣️ Voice AI Agents

Speech-in, speech-out agents using real-time voice APIs.

• 🗣️ AI Audio Tour Agent - Self-guided audio tours from your location, interests, and pace
• 📞 Customer Support Voice Agent - Voice answers grounded in your own docs
• 🛡️ Insurance Claim Live Agent Team - Real-time voice claim intake with Gemini Live
• 🔊 Voice RAG Agent (OpenAI SDK) - Ask your PDFs questions, hear the answers
• 🎙️ OpenSource Voice Dictation Agent (Wispr Flow clone) _{↗ external} - Open-source dictation that types where you talk

🖼️ Generative UI and Agentic Frontends

Agents that render interactive UI components, not just text: forms, cards, charts, editable plans.

• 🗂️ Generative UI Starter Project - A chat-driven kanban board you and the agent work together
• 🪙 AI Financial Coach Agent - Budget, savings, and debt plans rendered as interactive cards
• 📊 AI Dashboard Canvas Agent - Describe a dashboard in chat, charts assemble on a live canvas
• 🛠️ AI MCP App Builder - Describe an MCP app, get a live sandboxed instance back
• ✈️ MCP Apps Generative UI Showcase - MCP apps that render real interactive UI, flight search included
• 🎛️ AI Shadcn Component Generator - Chat your way to production-ready shadcn components
• 🔍 AI Deep Research Agent - Research where every tool call renders as a live workspace card

🎮 Autonomous Game-Playing Agents

Agents that play games end-to-end: reasoning, strategy, and action.

• 🎮 AI 3D Pygame Agent - DeepSeek R1 writes PyGame code, browser agents run it live
• ♜ AI Chess Agent - Agent White vs Agent Black with validated moves
• 🎲 AI Tic-Tac-Toe Agent - Two different LLMs battle it out, move by move

♾️ MCP AI Agents

Agents that connect to external tools and data via Model Context Protocol.

• ♾️ Browser MCP Agent - Drive a real browser with natural language over MCP
• 🐙 GitHub MCP Agent - Explore and analyze any repo in plain English
• 📑 Notion MCP Agent - Talk to your Notion pages from the terminal
• 🌍 AI Travel Planner MCP Agent - Itineraries built on live Airbnb and Google Maps data
• 🔀 Multi-MCP Agent Router - Specialist agents, each wired to its own MCP server
• 🔌 OpenAI Remote MCP Tool Bridge - Connect OpenAI function calling directly to a remote MCP server

📀 RAG (Retrieval Augmented Generation)

Retrieval pipelines, from simple chains to agentic and multi-source.

• 🔥 Agentic RAG with Embedding Gemma - Fully local agentic RAG with EmbeddingGemma and Llama 3.2
• 🧐 Agentic RAG with Reasoning - Watch the agent’s step-by-step reasoning as it retrieves
• 📰 AI Blog Search (RAG) - Agentic search over blog content, built on LangGraph
• 🔍 Autonomous RAG - GPT-4o answers from your PDFs, falls back to web search
• 🔄 Contextual AI RAG Agent - Managed RAG: datastore to grounded chat in minutes
• 🔄 Corrective RAG (CRAG) - Retrieval that grades itself and retries before answering
• 📎 Typed Agentic RAG with Pydantic AI - Validated answers with exact citations, or a refusal when evidence is weak
• 🐋 Deepseek Local RAG Agent - Local DeepSeek reasoning over your own documents
• 🤔 Gemini Agentic RAG - Query rewriting and web fallback with Gemini Flash Thinking
• 👀 Hybrid Search RAG (Cloud) - Keyword plus vector search feeding Claude
• 🔄 Llama 3.1 Local RAG - Chat with any webpage, fully offline
• 🖥️ Local Hybrid Search RAG - Hybrid search with everything running on your machine
• 🧬 Multimodal Agentic RAG - Text, PDFs, images, audio, and video, answered with citations
• 🦙 Local RAG Agent - Llama 3.2 and Qdrant, no API keys required
• 🧩 RAG-as-a-Service - A production RAG service in under 50 lines
• ✨ RAG Agent with Cohere - Command R7B retrieval with web-search fallback
• ⛓️ Basic RAG Chain - The minimal retrieval pipeline, applied to pharma research
• 📠 RAG with Database Routing - Routes each question to the right database automatically
• 🖼️ Vision RAG - Ask questions about images and PDF pages with Embed-4
• 🩺 RAG Failure Diagnostics Clinic - Find out why your RAG pipeline is wrong, systematically
• 🕸️ Knowledge Graph RAG with Citations - Multi-hop answers with verifiable source attribution

💾 LLM Apps with Memory

Agents and chatbots that remember conversations and user state across sessions.

• 💾 AI ArXiv Agent with Memory - Paper search that remembers your research interests
• 🛩️ AI Travel Agent with Memory - A travel assistant that remembers your preferences
• 💬 Llama3 Stateful Chat - Session-persistent chat with Llama 3
• 📝 LLM App with Personalized Memory - A chatbot that keeps context across conversations
• 🗄️ Local ChatGPT Clone with Memory - Fully local, with a personal memory per user
• 🧠 Multi-LLM Application with Shared Memory - Different models, one shared conversation memory

💬 Chat with X

Turn any data source into a chat interface.

• 💬 Chat with GitHub (GPT & Llama3) - Any repo, answered in 30 lines of RAG
• 📨 Chat with Gmail - Ask your inbox questions
• 📄 Chat with PDF (GPT & Llama3) - The classic, in 30 lines of Python
• 📚 Chat with Research Papers (ArXiv) (GPT & Llama3) - Explore arXiv conversationally with GPT-4o
• 📝 Chat with Substack - Chat with any newsletter’s archive
• 📽️ Chat with YouTube Videos - Ask videos questions via their transcripts

🎯 LLM Optimization Tools

Reduce token usage, context size, and API cost without losing quality.

• 🎯 Toonify Token Optimization - Reduce LLM API costs by 30-60% using TOON format
• 🧠 Headroom Context Optimization - Reduce LLM API costs by 50-90%

🔧 LLM Fine-tuning

End-to-end fine-tuning recipes for open-source models.

• 🦥 Gemma 3 Fine-tuning - 4-bit LoRA with Unsloth, small and readable
• 🦙 Llama 3.2 Fine-tuning - Fine-tune in 30 lines, free on Colab

🧑‍🏫 AI Agent Framework Crash Courses

Deep-dive tutorials on the major agent frameworks.

• Google ADK Crash Course - Starter agent, structured outputs, tools (built-in, function, third-party, MCP), memory, callbacks, plugins, and multi-agent patterns. Model-agnostic.
• OpenAI Agents SDK Crash Course - Starter agent, function calling, structured outputs, tools, memory, evaluation, handoffs, swarm orchestration, and routing logic.