yhshu

OpenDevin

🐚 OpenDevin: Code Less, Make More

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

UFO

A UI-Focused Agent for Windows OS Interaction.

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

langgraph

Build resilient language agents as graphs.

memary

Human Memory for AI Agents.

SoM

Set-of-Mark Prompting for LMMs

raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

HippoRAG

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents.

MiLM-6B

OmniGibson

OmniGibson: a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse engine. Join our Discord for support: https://discord.gg/bccR5vGFEx

zshot

Zero and Few shot named entity & relationships recognition

DAIL-SQL

A efficient and effective few-shot NL2SQL method on GPT-4.

Few-shot-NL2SQL-with-prompting

awesome-large-multimodal-agents

suql

SUQL: Conversational Search over Structured and Unstructured Data with LLMs

scidocs

Dataset accompanying the SPECTER model

multimodalqa

factoid-wiki

Dense X Retrieval: What Retrieval Granularity Should We Use?

multimodal-knowledge-graph

A collection of resources on multimodal knowledge graph, including datasets, papers and contests.

episodic-memory

LLM_Agent_Memory_Survey

musique

Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition, TACL 2022

code-html-to-markdown

A lightweight script for processing HTML page to markdown format with support for code blocks

entailment_bank

MuMuQA

fact-linking

Codebase for "Linking Surface Facts to Large-Scale Knowledge Graphs" (EMNLP 2023)

WebNLG-Text-to-triples

WebNLG+ Challenge 2020: the automatic evaluation script for the text-to-RDF task

OSWorld

OSWorld: A unified, real computer environment for multimodal agents to evaluate open-ended computer tasks involving arbitrary apps and interfaces on Ubuntu, Windows, and macOS