Official Repo for Open-Reasoner-Zero

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on…

MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.

A generative world for general-purpose robotics & embodied AI learning.

PDF++: the most Obsidian-native PDF annotation & viewing tool ever. Comes with optional Vim keybindings.

This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

A system for agentic LLM-powered data processing and ETL

Build resilient language agents as graphs.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

LLM-powered RAG Question Answering Slack bot for DataTalksClub Zoomcamps

A fork of sqlite-utils with CLI etc removed

A multi-factor equity risk model for quantitative trading.

Download market data from Yahoo! Finance's API

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

Structured Text Generation

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

✨ AI agents that spark joy

Harness LLMs with Multi-Agent Programming

Using Langroid's Multi-Agent Framework to Build LLM Apps

Interactive environment for evaluating LLM prompts on natural language criteria.

Robotics Gym Environments

AIDE: the Machine Learning CodeGen Agent

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

Entropy Based Sampling and Parallel CoT Decoding