Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
🤗 smolagents: a barebones library for agents that think in code.
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
LLM agents built for control. Designed for real-world use. Deployed in minutes.
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seekin…
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"
AIVA (AI Virtual Assistant) Mock Interviews is an interactive platform that simulates real interview scenarios using AI-generated questions and evaluations, enabling candidates to practice both CV-…
Intelligent web discovery agent with LLM-powered planning, multi-source search, smart deduplication, and GRPO preference dataset collection. Autonomously searches, analyzes, and summarizes web cont…
Process your PDF and then ask what you did not understand about it
Building a semantic search engine for ArXiv research papers recommendation using DistilBERT and Qdrant vector database
This is an application made using NoSQL databases : Neo4j graph databse and Python