-
Umea University
- Sweden
Stars
An open-source AI agent that brings the power of Gemini directly into your terminal.
A system for agentic LLM-powered data processing and ETL
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Build Real-Time Knowledge Graphs for AI Agents
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
Open-source, self-hosted note-taking tool built for quick capture. Markdown-native, lightweight, and fully yours.
The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data 📊
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
CLI tool to insert spacers when command output stops
💬 Create Dialogs, Visual Novels, RPGs, and manage Characters with Godot to create your Game!
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
DSPy: The framework for programming—not prompting—language models
🪄 Data Formulator is an interactive AI-powered data analysis system makes it easy to connect, explore and visualize data.
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
A socially aware interaction management system that can utilize social context to create scenarios for dialogue and multi-agent systems
Godot Engine – Multi-platform 2D and 3D game engine
A persisting WebSocket client for Django
Turkish Morphological Analyzer with dictionaries for stems and suffixes + Neural Morphological Disambiguation implemented in DyNet
Lovely console emulator package for Windows
Code to sample all sensors on Samsung Galaxy Gear S, S2 and S3.
Quickly and accurately render even the largest data.
Modified version of the JWNL (http://sourceforge.net/projects/jwordnet/)
Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)