--- title: "209 Free AI Projects to Build Before 2027 (Every Link, Sorted by Level)" description: "All 209 free AI projects from awesome-llm-apps (140K stars) and ai-engineering-hub (38K stars), with a checked link for each: RAG, agents, MCP, voice, fine-tuning, sorted from beginner to advanced, plus the 10 I would build first." date: "2026-09-27" type: "resource" tags: [] legacy: true ---

You commented projects, so here are all 209, with a working link for each one. They come from two open-source GitHub repos, and every project has its own folder with code and a README. I checked every link on 27 September 2026.

The short version: 121 projects from awesome-llm-apps and 88 from ai-engineering-hub, covering RAG, agents, MCP, voice, fine-tuning and more. All free to clone. Some call paid model APIs, and plenty run fully local with Ollama. Build three, not thirty.

The two repos

Shubhamsaboo/awesome-llm-apps ~140K ★

github.com/Shubhamsaboo/awesome-llm-apps

Apache-2.0. Starter agents that run with one API key, production-style agents, multi-agent teams, RAG tutorials, MCP agents, voice agents, generative UI, memory, fine-tuning and a set of agent skills for coding agents. It was updated on 26 September 2026.

patchy631/ai-engineering-hub ~38K ★

github.com/patchy631/ai-engineering-hub

MIT. Projects sorted into beginner, intermediate and advanced: local OCR and chat apps, RAG, agent workflows, MCP servers, model comparisons, fine-tuning and full production systems.

Start with these 10

  1. Chat with PDF (GPT & Llama3): The hello world of AI apps. Build it in an evening so RAG stops being a buzzword.
  2. Local RAG Agent: Same idea, fully local with Llama 3.2 and Qdrant. No API key, no bill.
  3. Llama OCR: Local OCR with Llama 3.2 vision. Point it at your handwritten notes.
  4. GitHub MCP Agent: Your first MCP project. Ask questions about any repo in plain English.
  5. Corrective RAG (CRAG): RAG that grades its own retrieval and retries. Great interview talking point.
  6. Always-on Hacker News Briefing Agent: A scheduled agent that sends you a ranked daily brief. Shows you can ship something that runs without you.
  7. LLM Panel Agent Team: Three models review the same diff blind, then argue. A fun multi-agent build.
  8. NotebookLM Clone: RAG, citations and podcast generation in one app. A proper capstone.
  9. Gemma 3 Fine-tuning: 4-bit LoRA with Unsloth. Your first fine-tune, small and readable.
  10. Project Graveyard: A Claude Code / Codex skill that finds the side projects you abandoned and helps you finish one. Start here if you have a graveyard.

All 209 projects

Numbered straight through so you can say "I built #47".

Part 1: awesome-llm-apps (121 projects)

Agent Skills (8)

  1. Project Graveyard: Finds every side project you abandoned, tells you why each one died, and helps you finish the one worth going back to
  2. First Reader: Simulates real readers going through your draft and reports where they lose interest, where they stop reading, and what they remember afterward, without rewriting a word
  3. Scope Creep Detector: Checks whether a diff grew beyond its stated intent and recommends what to keep, split, or justify
  4. Commit Archaeologist: Reconstructs why a file or code region exists from its introducing commit, later edits, co-changes, and intent clues
  5. Dependency Doctor: Checks a dependency manifest for standard-library pins, obsolete backports, unpinned entries, duplicate constraints, and yanked releases
  6. Advisor Orchestrator Worker: Meta Loop with Claude Fable 5.1 as advisor, GPT-6 Astra as orchestrator, and Gemini 3.8 Flash as worker
  7. Thinking Out Loud: Echoes a voice ramble back as a scannable brief, with the model's guesses quarantined and your reversals flagged
  8. Self-Improving Agent Skills: Automatically optimize agent skills using Gemini and ADK

Starter AI Agents (13)

  1. AI Blog to Podcast Agent: Turn any blog URL into a narrated podcast episode
  2. AI Breakup Recovery Agent: An agent team that talks you through the post-breakup spiral
  3. AI Data Analysis Agent: Ask questions of any CSV or Excel file in plain English
  4. AI Medical Imaging Agent: Diagnostic analysis of X-rays and scans with Gemini
  5. AI Meme Generator Agent (Browser): Makes memes by driving a real browser, not an image API
  6. AI Music Generator Agent: Prompt in, MP3 track out
  7. AI Travel Agent (Local & Cloud): Personalized day-by-day travel itineraries
  8. AI x402 Paying Agent: An agent with a wallet that pays per-call for the data it needs: no API keys
  9. Gemini Multimodal Agent: Video analysis plus web search in one agent
  10. Mixture of Agents: Multiple LLMs answer, one aggregates the best response
  11. xAI Finance Agent: Real-time stock analysis powered by Grok
  12. OpenAI Research Agent: Multi-agent topic research with the OpenAI Agents SDK
  13. Web Scraping AI Agent: Describe what to extract and the agent scrapes it

Advanced AI Agents (22)

  1. AI Home Renovation Agent with Nano Banana Pro: Photos of your space in, renovation plan and photorealistic renders out
  2. DevPulse AI - Multi-Agent Signal Intelligence: Aggregates and scores technical signals into a daily intelligence digest
  3. AI Deep Research Agent: Comprehensive web research with the OpenAI Agents SDK and Firecrawl
  4. AI VC Due Diligence Agent Team: Multi-agent startup investment analysis with Gemini 3
  5. AI Research Planner & Executor (Google Interactions API): Multi-phase research with stateful conversations and auto-generated infographics
  6. AI Consultant Agent: Market analysis and strategy recommendations with live web research
  7. AI System Architect Agent: Architecture reviews using DeepSeek R1 reasoning plus Claude
  8. AI Financial Coach Agent: Personalized budget, debt, and savings analysis
  9. AI Movie Production Agent: Script drafts and casting ideas from a one-line movie concept
  10. AI Investment Agent: Stock comparison reports built on Yahoo Finance data
  11. Earnings Call Analyst Agent: Turns YouTube earnings calls into a playback-synced analyst workspace
  12. AI Health & Fitness Agent: Tailored diet and workout plans from your goals
  13. AI Product Launch Intelligence Agent: Go-to-market intelligence on competitor launches
  14. AI Fraud Investigation Agent: Cross-references public records to flag facilities that don't add up
  15. AI Journalist Agent: Researches, writes, and edits articles on any topic
  16. AI Mental Wellbeing Agent: A coordinated agent team for mental health support plans
  17. AI Meeting Agent: Context, industry insights, and strategy briefs before you walk in
  18. AI Self-Evolving Agent: Agents that rewrite their own workflows with EvoAgentX
  19. AI Sales Intelligence Agent Team: Generates competitive sales battle cards in real time
  20. AI Social Media News and Podcast Agent: Curates your trusted sources into briefs and generated podcasts
  21. Openwork - Open Browser Automation Agent (separate repo): Open-source agent that operates a real browser
  22. Trust-Gated Multi-Agent Research Team: Every agent verified, every action in a hash-chained audit trail

Always-on Agents (2)

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

Multi-agent Teams (14)

  1. AI Competitor Intelligence Agent Team: Structured competitor teardowns built from their own websites
  2. AI Finance Agent Team: A financial analyst team in 20 lines of Python
  3. AI Game Design Agent Team: Full game concepts from a swarm of design specialists
  4. AG2 Adaptive Research Team: Agent teamwork with routing and fallback, built on AG2
  5. AI Legal Agent Team (Cloud & Local): Research, contract analysis, and strategy from a full legal bench
  6. AI Recruitment Agent Team: Resume screening to interview scheduling, end to end
  7. AI Real Estate Agent Team: Property search, market analysis, and recommendations
  8. AI Services Agency (CrewAI): A digital agency that scopes and plans your software project
  9. AI Teaching Agent Team: A faculty of agents that builds your complete learning path
  10. Multimodal Coding Agent Team: Snap a photo of a coding problem, get a sandboxed solution
  11. Multimodal Design Agent Team: Design critiques from a Gemini-powered expert panel
  12. Multimodal UI/UX Feedback Agent Team: Landing page feedback plus an auto-generated improved version
  13. AI Travel Planner Agent Team: A complete trip itinerary, crafted by a team
  14. LLM Panel Agent Team: Three vendors review the same diff blind, then argue it out anonymously

Voice AI Agents (5)

  1. AI Audio Tour Agent: Self-guided audio tours from your location, interests, and pace
  2. Customer Support Voice Agent: Voice answers grounded in your own docs
  3. Insurance Claim Live Agent Team: Voice claim intake on Gemini 3.8 Live that writes a field notebook, looks at damage through the webcam, and sketches the incident
  4. Voice RAG Agent (OpenAI SDK): Ask your PDFs questions, hear the answers
  5. OpenSource Voice Dictation Agent (Wispr Flow clone) (separate repo): Open-source dictation that types where you talk

Generative UI and Agentic Frontends (7)

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

Autonomous Game-Playing Agents (3)

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

MCP AI Agents (6)

  1. Browser MCP Agent: Drive a real browser with natural language over MCP
  2. GitHub MCP Agent: Explore and analyze any repo in plain English
  3. Notion MCP Agent: Talk to your Notion pages from the terminal
  4. AI Travel Planner MCP Agent: Itineraries built on live Airbnb and Google Maps data
  5. Multi-MCP Agent Router: Specialist agents, each wired to its own MCP server
  6. OpenAI Remote MCP Tool Bridge: Connect OpenAI function calling directly to a remote MCP server

RAG (Retrieval Augmented Generation) (21)

  1. Agentic RAG with Embedding Gemma: Fully local agentic RAG with EmbeddingGemma and Llama 3.2
  2. Agentic RAG with Reasoning: Watch the agent's step-by-step reasoning as it retrieves
  3. AI Blog Search (RAG): Agentic search over blog content, built on LangGraph
  4. Autonomous RAG: GPT-4o answers from your PDFs, falls back to web search
  5. Contextual AI RAG Agent: Managed RAG: datastore to grounded chat in minutes
  6. Corrective RAG (CRAG): Retrieval that grades itself and retries before answering
  7. Typed Agentic RAG with Pydantic AI: Validated answers with exact citations, or a refusal when evidence is weak
  8. Deepseek Local RAG Agent: Local DeepSeek reasoning over your own documents
  9. Gemini Agentic RAG: Query rewriting and web fallback with Gemini Flash Thinking
  10. Hybrid Search RAG (Cloud): Keyword plus vector search feeding Claude
  11. Llama 3.1 Local RAG: Chat with any webpage, fully offline
  12. Local Hybrid Search RAG: Hybrid search with everything running on your machine
  13. Multimodal Agentic RAG: Text, PDFs, images, audio, and video, answered with citations
  14. Local RAG Agent: Llama 3.2 and Qdrant, no API keys required
  15. RAG-as-a-Service: A production RAG service in under 50 lines
  16. RAG Agent with Cohere: Command R7B retrieval with web-search fallback
  17. Basic RAG Chain: The minimal retrieval pipeline, applied to pharma research
  18. RAG with Database Routing: Routes each question to the right database automatically
  19. Vision RAG: Ask questions about images and PDF pages with Embed-4
  20. RAG Failure Diagnostics Clinic: Find out why your RAG pipeline is wrong, systematically
  21. Knowledge Graph RAG with Citations: Multi-hop answers with verifiable source attribution

AI Browser Tools (2)

  1. Needle - A New Way to Find: Search webpages by meaning and highlight the strongest source sentence, using a Chrome extension powered by TypeSafe Jev
  2. Ripple - Change One Thing, Find What Else Needs to Change: Find related inconsistencies and suggested fixes as you edit a Google Doc, using TypeSafe Jev and Gemini

LLM Apps with Memory (6)

  1. AI ArXiv Agent with Memory: Paper search that remembers your research interests
  2. AI Travel Agent with Memory: A travel assistant that remembers your preferences
  3. Llama3 Stateful Chat: Session-persistent chat with Llama 3
  4. LLM App with Personalized Memory: A chatbot that keeps context across conversations
  5. Local ChatGPT Clone with Memory: Fully local, with a personal memory per user
  6. Multi-LLM Application with Shared Memory: Different models, one shared conversation memory

Chat with X (6)

  1. Chat with GitHub (GPT & Llama3): Any repo, answered in 30 lines of RAG
  2. Chat with Gmail: Ask your inbox questions
  3. Chat with PDF (GPT & Llama3): The classic, in 30 lines of Python
  4. Chat with Research Papers (ArXiv) (GPT & Llama3): Explore arXiv conversationally with GPT-4o
  5. Chat with Substack: Chat with any newsletter's archive
  6. Chat with YouTube Videos: Ask videos questions via their transcripts

LLM Optimization Tools (2)

  1. Toonify Token Optimization: Reduce LLM API costs by 30-60% using TOON format
  2. Headroom Context Optimization: Reduce LLM API costs by 50-90%

LLM Fine-tuning (2)

  1. Gemma 3 Fine-tuning: 4-bit LoRA with Unsloth, small and readable
  2. Llama 3.2 Fine-tuning: Fine-tune in 30 lines, free on Colab

AI Agent Framework Crash Courses (2)

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

Part 2: ai-engineering-hub (88 projects)

Beginner: OCR & Vision (4)

  1. LaTeX OCR with Llama: Convert LaTeX equation images to code using Llama 3.2 vision
  2. Llama OCR: 100% local OCR app with Llama 3.2 and Streamlit
  3. Gemma-3 OCR: Local OCR with structured text extraction using Gemma-3
  4. Qwen 2.5 OCR: Text extraction using Qwen 2.5 VL model

Beginner: Chat Interfaces & UI (7)

  1. Local ChatGPT with DeepSeek: Mini-ChatGPT with DeepSeek-R1 and Chainlit
  2. Local ChatGPT with Llama: ChatGPT clone using Llama 3.2 vision
  3. Local ChatGPT with Gemma 3: Local chat interface with Gemma 3
  4. DeepSeek Thinking UI: ChatGPT with visible reasoning using DeepSeek-R1
  5. Qwen3 Thinking UI: Thinking UI with Qwen3:4B and Streamlit
  6. GPT-OSS Thinking UI: GPT-OSS with reasoning visualization
  7. Streaming AI Chatbot: Real-time AI streaming with Motia framework

Beginner: Basic RAG (6)

  1. Simple RAG Workflow: Basic RAG with LlamaIndex and Ollama
  2. Document Chat RAG: Chat with documents using Llama 3.3
  3. Fastest RAG Stack: Fast RAG with SambaNova, LlamaIndex, and Qdrant
  4. GitHub RAG: Chat with GitHub repos locally
  5. ModernBERT RAG: RAG with ModernBert embeddings
  6. Llama 4 RAG: RAG powered by Meta's Llama 4

Beginner: Multimodal & Media (2)

  1. Image Generation with Janus-Pro: Local image generation with DeepSeek Janus-pro 7B
  2. Video RAG with Gemini: Chat with videos using Gemini AI

Beginner: Other Tools (3)

  1. Website to API with FireCrawl: Convert websites to APIs
  2. AI News Generator: News generation with CrewAI and Cohere
  3. Siamese Network: Digit similarity detection on MNIST

Intermediate: AI Agents & Workflows (13)

  1. YouTube Trend Analysis: Analyze YouTube trends with CrewAI and BrightData
  2. AutoGen Stock Analyst: Advanced analyst with Microsoft AutoGen
  3. Agentic RAG: RAG with document search and web fallback
  4. Agentic RAG with DeepSeek: Enterprise agentic RAG with GroundX
  5. Book Writer Flow: Automated book writing with CrewAI
  6. Content Planner Flow: Content workflow with CrewAI Flow
  7. Brand Monitoring: Automated brand monitoring system
  8. Hotel Booking Crew: Multi-agent hotel booking with DeepSeek-R1
  9. Deploy Agentic RAG: Private Agentic RAG API with LitServe
  10. Zep Memory Assistant: AI Agent with human-like memory
  11. Agent with MCP Memory: Agents with Graphiti memory and Opik
  12. ACP Code: Agent Communication Protocol demo
  13. Motia Content Creation: Social media automation workflow

Intermediate: Voice & Audio (5)

  1. Real-time Voice Bot: Conversational travel guide with AssemblyAI
  2. RAG Voice Agent: Real-time RAG Voice Agent with Cartesia
  3. Chat with Audios: RAG over audio files
  4. Audio Analysis Toolkit: Audio analysis with AssemblyAI
  5. Multilingual Meeting Notes: Auto meeting notes with language detection

Intermediate: Advanced RAG (5)

  1. RAG with Dockling: RAG over Excel with IBM's Docling
  2. Trustworthy RAG: RAG over complex docs with TLM
  3. Fastest RAG with Milvus and Groq: Sub-15ms retrieval latency
  4. Chat with Code: Chat with code using Qwen3-Coder
  5. RAG SQL Router: Agent with RAG and SQL routing

Intermediate: Multimodal (3)

  1. DeepSeek Multimodal RAG: MultiModal RAG with DeepSeek-Janus-Pro
  2. ColiVara Website RAG: MultiModal RAG for websites
  3. Multimodal RAG with AssemblyAI: Audio + vector database + CrewAI

Intermediate: MCP (Model Context Protocol) (10)

  1. Cursor Linkup MCP: Custom MCP with deep web search
  2. EyeLevel MCP RAG: MCP for RAG over complex docs
  3. LlamaIndex MCP: Local MCP client with LlamaIndex
  4. MCP Agentic RAG: MCP-powered Agentic RAG for Cursor
  5. MCP Agentic RAG Firecrawl: Agentic RAG with Firecrawl
  6. MCP Video RAG: Video RAG using Ragie via MCP
  7. MCP Voice Agent: Voice agent with Firecrawl and Supabase
  8. SDV MCP: Synthetic Data Vault orchestration
  9. KitOps MCP: ML model management with KitOps
  10. Stagehand × MCP-Use: Web automation with Stagehand MCP

Intermediate: Model Comparison & Evaluation (8)

  1. Evaluation and Observability: E2E RAG evaluation with CometML Opik
  2. Llama 4 vs DeepSeek-R1: Compare models using RAG
  3. Qwen3 vs DeepSeek-R1: Model comparison with Opik
  4. O3 vs Claude Code: Compare Claude 3.7 and o3
  5. Sonnet4 vs O4: Code generation comparison
  6. Sonnet4 vs Qwen3-Coder: Coder model comparison
  7. Code Model Comparison: Frontier model code comparison
  8. GPT-OSS vs Qwen3: Reasoning capabilities comparison

Advanced: Fine-tuning & Model Development (2)

  1. DeepSeek Fine-tuning: Fine-tune DeepSeek with Unsloth and Ollama
  2. Build Reasoning Model: Build DeepSeek-R1-like reasoning models

Advanced: Advanced Agent Systems (10)

  1. Documentation Writer Flow: Agentic documentation workflow
  2. Multi-Agent Deep Researcher: MCP-powered deep researcher
  3. Multiplatform Deep Researcher: Multi-platform research with BrightData
  4. Web Browsing Agent: Browser automation with CrewAI and Stagehand
  5. Paralegal Agent Crew: Intelligent paralegal with RAG
  6. FireCrawl Agent: Corrective RAG with web search fallback
  7. Context Engineering Workflow: Research assistant with TensorLake and Zep
  8. Parlant Conversational Agent: Compliance-driven conversational agent
  9. Stock Portfolio Analysis Agent: Portfolio analysis with React frontend
  10. Guidelines vs Traditional Prompt: Structured guidelines comparison

Advanced: Advanced MCP & Infrastructure (5)

  1. MindsDB MCP: Unified MCP for all data sources
  2. Financial Analyst DeepSeek: MCP financial analysis workflow
  3. Graphiti MCP: Persistent memory with Zep's Graphiti
  4. Pixeltable MCP: Unified multimodal data orchestration
  5. Ultimate AI Assistant: Multi-MCP server interface

Advanced: Production Systems (2)

  1. GroundX Document Pipeline: World-class document processing
  2. NotebookLM Clone: Full NotebookLM with RAG, citations, and podcasts

Advanced: Advanced Agent Systems (2)

  1. Build a Claude Code Harness with CrewAI: Build your own Claude Code style coding harness on top of CrewAI
  2. Open Agent Builder (with Composio): Drag-and-drop workflow builder for AI agent pipelines, with Composio tools and MCP support

Advanced: Fine-tuning & Model Development (1)

  1. Train YOLO26 Object Detection: Train a YOLO26 object detection model on your own custom dataset

How I'd use this

A note on the count: a couple of projects share names across the two repos (there are two different "AI Deep Research Agent" builds and two "AI Financial Coach Agent" builds). Two entries in the ai-engineering-hub README pointed to folders that no longer exist, so I swapped in two real projects from the same repo that aren't in its README yet.

Want the learning path to go with the projects? Read AI Engineering from Scratch: 523 free lessons, then 25 projects to build to get hired in 2026.

Follow @avi_vashishta29 for one practical AI dev resource a day.