semio

chatgpt-on-wechat

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT4.0/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

upscayl

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

llamafile

Distribute and run LLMs with a single file.

marker

Convert PDF to markdown quickly with high accuracy

pyxel

A retro game engine for Python

pip-tools

A set of tools to keep your pinned Python dependencies fresh.

gpt-computer-assistant

Intelligence development framework in python for your product like Apple Intelligence

heynote

A dedicated scratchpad for developers

llm

Access large language models from the command-line

grobid

A machine learning software for extracting information from scholarly documents

dataherald

Interact with your SQL database, Natural Language to SQL using LLMs

GhostText

👻 Use your text editor to write in your browser. Everything you type in the editor will be instantly updated in the browser (and vice versa).

camelot

A Python library to extract tabular data from PDFs

DecryptPrompt

总结Prompt&LLM论文，开源数据&模型，AIGC应用

autorandr

Auto-detect the connected display hardware and load the appropriate X11 setup using xrandr

lem

Common Lisp editor/IDE with high expansibility

NsCDE

Modern and functional CDE desktop based on FVWM

logica

Logica is a logic programming language that compiles to SQL. It runs on DuckDB, Google BigQuery, PostgreSQL and SQLite.

arquero

Query processing and transformation of array-backed data tables.

arxiv-style

A Latex style and template for paper preprints (based on NIPS style)

jd

JSON diff and patch

cs6120

advanced compilers

Paper-Piano

Piano like no other, Piano on Paper

MonoSketch

An ASCII graph drawing app

large-qa-datasets

A collection of large question answering datasets

preprint-template.tex

A template for two-column scientific preprints

TAT-QA

TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.

segment-anything-comic

The repository provides code for training the SegmentAnything Model (SAM) for predicting frame polygons in comic books

purescript-d3-tagless-II

Tagless final style interpreter / wrapper for D3 in PureScript, latest of many re-writes

ET_Bembo