Lists (6)
Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
A fast and powerful log viewer and processor that converts JSON logs or logfmt logs into a clear human-readable format.
Lightweight coding agent that runs in your terminal
GenAI Agent Framework, the Pydantic way
A very fast and expressive template engine.
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Supercharge Your LLM Application Evaluations 🚀
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website …
Repository for "MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents" (COLM 2024)
A framework for few-shot evaluation of language models.
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
An incremental parsing system for programming tools
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Kimi K2 is the large language model series developed by Moonshot AI team
🦜🔗 LangChain interfaces to Google's suite of AI products (Gemini & Vertex AI)
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
A library for efficient similarity search and clustering of dense vectors.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Python tool for converting files and office documents to Markdown.
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
🚀 The fast, Pythonic way to build MCP servers and clients
GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.