Trending repositories: nlp

10 of 10 repositories

• headroomlabs-ai/headroom

  Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

  AI summary: An open-source platform for conducting and analyzing AI-driven user research interviews.

  65,316productivityPythonApache-2.0agentaianthropicclaude-code

• microsoft/AI-For-Beginners

  12 Weeks, 24 Lessons, AI for All!

  AI summary: A comprehensive, 12-week curriculum for learning Artificial Intelligence from Microsoft.

  63,088learningJupyter NotebookMITaiartificial-intelligencecnncomputer-vision

• rohitg00/ai-engineering-from-scratch

  Learn it. Build it. Ship it for others.

  AI summary: A comprehensive, code-first curriculum to master AI engineering and build production-ready LLM applications.

  46,045learningPythonMITagentsaiai-agentsai-engineering

• google/langextract

  A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

  AI summary: AI-powered tool for extracting structured data from unstructured text using large language models.

  37,990dataPythonApache-2.0geminigemini-aigemini-apigemini-flash

• MoonshotAI/Kimi-K3

  Open Frontier Intelligence

  AI summary: An open-source AI model by Moonshot AI available via Hugging Face.

  8,147ai-mlOtheraichathuggingfacemoonshot-ai

• HenryNdubuaku/maths-cs-ai-compendium

  Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.

  AI summary: A comprehensive compendium covering Mathematics, Computer Science, and Artificial Intelligence concepts.

  7,254learningTypeScriptApache-2.0ai-textbookalgorithmsartificial-intelligencecomputer-science

• marcelroed/gigatoken

  Language model tokenization at GB/s

  AI summary: Gigatoken is a high-performance tokenizer for language models capable of processing text at GB/s.

  3,933ai-mlRustMITllmnlptokenizationtokenizer

• rahulnyk/knowledge_graph

  Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA

  AI summary: A tool to convert unstructured text into knowledge graphs for enhanced QnA and data generation.

  3,627dataJupyter NotebookMITknowledge-graphnlpragdata-extraction

• org2AI/ORG2

  System of record for how agents build software: Built-in rust harness & 20+ CLIs.

  AI summary: Fork of ORG2 focusing on enhanced natural language understanding for organizational agents.

  2,175ai-mlTypeScriptAGPL-3.0ai-coding-assistantcoding-agentsidelocal-first

• stepfun-ai/Step-3.5-Flash

  Fast, Sharp & Reliable Agentic Intelligence

  AI summary: Step-3.5-Flash is a highly optimized, fast inference LLM for real-time applications.

  2,092ai-mlC++Apache-2.0llmfast-inferencelow-latencyreal-time