InternLM/MindSearch
🔍 a LLM-based Multi-agent Framework of Web Search Engine similar to Perplexity.ai Pro and SearchGPT
Language: Python
#ai_search_engine #gpt #llm #llms #multi_agent_systems #perplexity_ai #search #searchgpt #transformer #web_search
Stars: 792 Issues: 9 Forks: 60
https://github.com/InternLM/MindSearch

DocumindHQ/documind
Open-source platform for extracting structured data from documents using AI.
Language: TypeScript
#ai #document_extraction #document_processing #llms #open_source #pdf_extractor
Stars: 742 Issues: 2 Forks: 16
https://github.com/DocumindHQ/documind

HKUDS/VideoRAG
"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos"
Language: Python
#large_language_models #llms #long_video_understanding #multi_modal_llms #rag #retrieval_augmented_generation
Stars: 201 Issues: 1 Forks: 14
https://github.com/HKUDS/VideoRAG

seal-rg/recurrent-pretraining
Pretraining code for a large-scale depth-recurrent language model
Language: Python
#llms #pretraining #reasoning #recurrent_depth
Stars: 249 Issues: 2 Forks: 14
https://github.com/seal-rg/recurrent-pretraining

therealoliver/Deepdive-llama3-from-scratch
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
Language: Jupyter Notebook
#attention #attention_mechanism #gpt #inference #kv_cache #language_model #llama #llm_configuration #llms #mask #multi_head_attention #positional_encoding #residuals #rms #rms_norm #rope #rotary_position_encoding #swiglu #tokenizer #transformer
Stars: 388 Issues: 0 Forks: 28
https://github.com/therealoliver/Deepdive-llama3-from-scratch

KalyanKS-NLP/rag-zero-to-hero-guide
Comprehensive guide to learn RAG from basics to advanced.
Language: Jupyter Notebook
#ai_engineer #generative_ai #large_language_models #llm_engineer #llm_rag #llms #retrieval_augmented_generation
Stars: 344 Issues: 0 Forks: 89
https://github.com/KalyanKS-NLP/rag-zero-to-hero-guide

mirth/chonky
Fully neural approach for text chunking
Language: Python
#ai #chunking #llms #ml #rag #semantic_chunking #text_splitter
Stars: 232 Issues: 0 Forks: 6
https://github.com/mirth/chonky

steipete/agent-rules
Rules and Knowledge to work better with agents such as Claude Code or Cursor
Language: Shell
#agent #claudecode #cursor #llms #rules
Stars: 342 Issues: 3 Forks: 13
https://github.com/steipete/agent-rules

NirDiamant/agents-towards-production
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.
Language: Jupyter Notebook
#agent #agent_framework #agents #ai_agents #genai #generative_ai #llm #llms #mlops #multi_agent #production #tool_integration #tutorials
Stars: 1422 Issues: 0 Forks: 141
https://github.com/NirDiamant/agents-towards-production

Varietyz/Disciplined-AI-Software-Development
This methodology provides a structured approach for collaborating with AI systems on software development projects. It addresses common issues like code bloat, architectural drift, and context dilution through systematic constraints and validation checkpoints.
Language: Python
#ai #ai_agents #ai_collaboration #best_practices #collaborate #collaboration #collaborative #context #documentation #dry #educational #kiss #llms #methodology #methodology_development #prompt_engineering #software_architecture #software_development #software_engineering #workflow
Stars: 194 Issues: 1 Forks: 7
https://github.com/Varietyz/Disciplined-AI-Software-Development

jdevalk/specification.website
Website specification — HTML, accessibility, security, SEO, agent-readiness. Platform-agnostic, sourced, MIT.
Language: TypeScript
#accessibility #agent_readiness #astro #cloudflare_pages #llms_txt #mcp #seo #specification #web_security #web_standards #well_known
Stars: 407 Issues: 5 Forks: 28
https://github.com/jdevalk/specification.website