--- title: Best Llama posts of 2025 | daily.dev description: The most upvoted Llama posts of 2025, curated by the daily.dev community. canonical: https://daily.dev/tags/llama/best-of/2025 twitter:card: summary_large_image twitter:site: @dailydotdev og:url: https://daily.dev/tags/llama/best-of/2025 og:type: website og:site_name: daily.dev og:title: Best Llama posts of 2025 | daily.dev og:description: The most upvoted Llama posts of 2025, curated by the daily.dev community. og:image: https://media.daily.dev/image/upload/s--VAY5ToZt--/f_auto/v1724209435/public/daily.dev%20-%20open%20graph --- # Best of Llama — 2025 1. 1 [](https://daily.dev/posts/building-a-100-local-mcp-client-xhl5tvrju "Building a 100% local MCP Client") Article Daily Dose of Data Science | Avi Chawla | Substack · 1y Building a 100% local MCP Client Learn how to build a completely local Model Context Protocol (MCP) client using tools like LlamaIndex, Ollama, and LightningAI. The tutorial provides a comprehensive walkthrough to create an MCP client capable of communicating with external tools and data sources through a structured protocol. It demonstrates setting up an SQLite server and building an AI agent using Deepseek-R1 as the local LLM, providing users with context-aware responses based on their queries. 133 1 2. 2 [](https://daily.dev/posts/mcp-integration-with-4-popular-agentic-frameworks-gojamcx1c "MCP Integration with 4 Popular Agentic Frameworks") Article Daily Dose of Data Science | Avi Chawla | Substack · 1y MCP Integration with 4 Popular Agentic Frameworks Part 8 of an MCP crash course demonstrates how to integrate Model Context Protocol with four popular agentic frameworks: LangGraph, CrewAI, LlamaIndex, and PydanticAI. The tutorial provides step-by-step practical walkthroughs for connecting MCP to each framework, along with detailed implementations. This builds on previous parts covering MCP fundamentals, custom client development, tools/resources/prompts, sampling integration, and security considerations including testing and sandboxing. 67 3. 3 [](https://daily.dev/posts/make-rag-systems-32x-memory-efficient--qxzqnyhia "Make RAG systems 32x Memory Efficient!") Article Daily Dose of Data Science | Avi Chawla | Substack · 1y Make RAG systems 32x Memory Efficient! Binary quantization can make RAG systems 32x more memory efficient by converting float32 embeddings to binary vectors. The technique involves ingesting documents, generating binary embeddings, storing them in a vector database like Milvus, and using Hamming distance for retrieval. A complete implementation demonstrates querying 36M+ vectors in under 30ms using LlamaIndex, Milvus, and Groq for inference, with deployment via Beam Cloud. 54 1 4. 4 [](https://daily.dev/posts/run-deepseek-r1-dynamic-1-58-bit-0kkr1wyzi "Run DeepSeek-R1 Dynamic 1.58-bit") Article Hacker News · 2y Run DeepSeek-R1 Dynamic 1.58-bit The post explains how to install and run the DeepSeek-R1 model, highlighting the importance of adding BOS and EOS tokens in interactions. It provides detailed setup instructions using commands like \`apt-get update\` for dependencies, downloading the model via \`huggingface\_hub\`, and outlines how to configure GPU offloading based on available memory. Additionally, there's guidance on quantizing the model's K cache to 4bit and running the model using those configurations. 47 3 5. 5 [](https://daily.dev/posts/building-ai-agents-that-actually-automate-knowledge-work---jerry-liu-llamaindex-fqosh52nk "Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex") Video AI Engineer · 1y Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex Jerry Liu from LlamaIndex presents a framework for building AI agents that automate knowledge work over unstructured documents. He distinguishes between assistive agents (chat interfaces that help humans get information) and automation agents (background processes that handle routine tasks). The approach requires a comprehensive document toolbox with parsing capabilities for complex PDFs, Excel sheets, and other formats, plus appropriate agent architectures ranging from constrained to unconstrained workflows. Real-world applications include financial due diligence, enterprise search, and technical data sheet processing, with LlamaIndex providing cloud services for document parsing that outperform existing benchmarks. 37 6. 6 [](https://daily.dev/posts/why-meta-stole-millions-of-books-to-train-ai-w6pivzcxp "Why Meta stole millions of books to train AI") Video Hiten Shah · 1y Why Meta stole millions of books to train AI Meta downloaded 82 terabytes of pirated books from shadow libraries like LibGen to train their Llama AI model, despite legal concerns from engineers. After publishers refused licensing deals deemed too expensive and slow, Meta chose piracy over falling behind competitors like OpenAI and Google. The pirated data improved Llama's performance by 5%, leading to 800 more correct answers. Meta covered their tracks by masking IP addresses and removing copyright tags, while relying on a fair use legal defense strategy shared across the AI industry when facing inevitable lawsuits from authors and publishers. 36 16 7. 7 [](https://daily.dev/posts/corrective-rag-agentic-workflow-od2ssqhpw "Corrective RAG Agentic Workflow") Article Daily Dose of Data Science | Avi Chawla | Substack · 1y Corrective RAG Agentic Workflow Corrective RAG (CRAG) enhances traditional RAG systems by adding a self-assessment step that evaluates retrieved document relevance before generating responses. The workflow searches documents, uses an LLM to assess context relevance, retains only relevant information, performs web search when needed, and aggregates context for final response generation. The implementation uses a tech stack including Firecrawl for web search, Milvus for vector storage, Beam for deployment, and LlamaIndex workflows for orchestration, with observability through CometML's Opik. 26 [See all Llama archives](/tags/llama/best-of) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@graph":[{"@type":"CollectionPage","@id":"https://daily.dev/tags/llama/best-of/2025#page","url":"https://daily.dev/tags/llama/best-of/2025","name":"Best Llama Posts of 2025","description":"The most upvoted Llama posts of 2025, curated by the daily.dev community.","isPartOf":{"@type":"WebSite","url":"https://daily.dev"}},{"@type":"ItemList","@id":"https://daily.dev/tags/llama/best-of/2025#items","numberOfItems":7,"itemListElement":[{"@type":"ListItem","position":1,"url":"https://daily.dev/posts/building-a-100-local-mcp-client-xhl5tvrju","name":"Building a 100% local MCP Client"},{"@type":"ListItem","position":2,"url":"https://daily.dev/posts/mcp-integration-with-4-popular-agentic-frameworks-gojamcx1c","name":"MCP Integration with 4 Popular Agentic Frameworks"},{"@type":"ListItem","position":3,"url":"https://daily.dev/posts/make-rag-systems-32x-memory-efficient--qxzqnyhia","name":"Make RAG systems 32x Memory Efficient!"},{"@type":"ListItem","position":4,"url":"https://daily.dev/posts/run-deepseek-r1-dynamic-1-58-bit-0kkr1wyzi","name":"Run DeepSeek-R1 Dynamic 1.58-bit"},{"@type":"ListItem","position":5,"url":"https://daily.dev/posts/building-ai-agents-that-actually-automate-knowledge-work---jerry-liu-llamaindex-fqosh52nk","name":"Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex"},{"@type":"ListItem","position":6,"url":"https://daily.dev/posts/why-meta-stole-millions-of-books-to-train-ai-w6pivzcxp","name":"Why Meta stole millions of books to train AI"},{"@type":"ListItem","position":7,"url":"https://daily.dev/posts/corrective-rag-agentic-workflow-od2ssqhpw","name":"Corrective RAG Agentic Workflow"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tags","item":"https://daily.dev/tags"},{"@type":"ListItem","position":3,"name":"Llama","item":"https://daily.dev/tags/llama"},{"@type":"ListItem","position":4,"name":"Best of","item":"https://daily.dev/tags/llama/best-of"},{"@type":"ListItem","position":5,"name":"2025"}]}]} ```