General Introduction agents.json is an open source specification developed by the Wildcard AI team, based on the OpenAPI standard, designed to allow intelligences to communicate efficiently with APIs through natural language. It defines the interaction contract between intelligences and APIs through structured JSON files, optimized for endpoint discovery and parameter...
General Introduction Foudinge Scrub is an open source web tool hosted on GitHub and created by developer Théophile Cantelobre. It is designed to help users clean and edit knowledge graph entities extracted from complex textual data, and is especially targeted at the restaurant review site LeFooding.com from ...
Enable Builder Smart Programming Mode, unlimited use of DeepSeek-R1 and DeepSeek-V3, smoother experience than the overseas version. Just enter the Chinese commands, even a novice programmer can write his own apps with zero threshold.
General Introduction PhotoDoodle is an open source image editing tool developed by ShowLab, focusing on artistic editing of photos through artificial intelligence technology. Users can add cartoon style, 3D effect, halo, wings and other decorative elements to real photos by just typing simple text prompts,...
Comprehensive Introduction DiffRhythm is an open source project developed by ASLP-lab (Audio, Speech and Language Processing Group, Northwestern Polytechnical University), focusing on end-to-end music creation through artificial intelligence technology. It is based on the Latent Diffusion model (Latent Diffusion) and is capable of generating in just 10 seconds a...
General Introduction Awesome AI Agents is a GitHub open source project maintained by the e2b-dev team focused on collecting and organizing resources related to autonomous AI intelligences. The project brings together over 150 AI agents and development frameworks, ranging from coding assistants to data processing agents...
General Introduction Anon-Kode is an open source AI code assistant for terminal-based operations, launched on GitHub by developer Daniel Nakov. Designed for programmers, it helps users quickly fix code, run tests, and interpret complex functions by integrating language models that support OpenAI-style APIs...
General Introduction ReSearch is an open-source research tool developed by the Agent-RL team to improve the search and inference capabilities of Large Language Models (LLMs) through Reinforcement Learning (RL). The project is inspired by Deepseek-R1-Zero and OpenAI's Deep ...
General Introduction AI Writing Assistant is an open source AI writing assistant based on Next.js, hosted on GitHub, designed to help writers, content creators, and copywriting professionals improve the efficiency and quality of their writing through artificial intelligence technology. The tool allows users to style editors with detailed groups of prompts...
Comprehensive Introduction PrimisAI Nexus is a lightweight open-source Python framework hosted on GitHub and developed by the PrimisAI team, aiming to help users build and manage scalable AI multi-intelligence systems for automating complex tasks through Large Language Modeling (LLM). It uses a modularized design through...
Comprehensive Introduction Probly is a spreadsheet tool developed by the PragmaticMachineLearning team and open-sourced on GitHub that combines the functionality of traditional spreadsheets with powerful AI data analysis capabilities. It not only supports users to manage data like using Excel, but also through the built-in...
General Introduction CogView4 is an open source text-to-graph model developed by the KEG Lab (THUDM) at Tsinghua University, focusing on converting text descriptions into high-quality images. It supports bilingual cue input, and is especially good at understanding Chinese cues and generating images with Chinese characters, which is very suitable for advertising design,...
General Introduction MTranServer is an open source server project focused on offline translation, hosted on GitHub and created by developer xxnuo. Its biggest highlight is the ultra-low resource requirements, requiring only a CPU and 1GB of RAM to run without GPU support, it can achieve an average of 50ms of a single please...
General Introduction code2prompt is an open source command line tool, created and hosted on GitHub by developer Mufeed VH, designed to help users quickly convert entire code bases into prompts (prompts) suitable for the Large Language Model (LLM). It does this by traversing code directories, generating source code tree structures...
General Introduction hugo-translator is an automated translation tool designed for Hugo's static site builder, hosted on GitHub and created by developer Rico00121. The tool is designed to help Hugo users quickly translate their blog content into multiple languages, utilizing Google Translate...
Comprehensive Introduction FireRedASR is a speech recognition model developed and open-sourced by the Little Red Book FireRed team, focusing on providing high-precision, multi-language-supported automatic speech recognition (ASR) solutions. The project is hosted on GitHub for developers and researchers, provides industrial-grade design, and supports Mandarin, Chinese...
General Introduction DeepRant is an open source translation tool for gamers, designed to solve the problem of language barriers in international servers. It realizes instant translation of in-game text through shortcut keys, supports multiple languages to translate each other, and allows players to quickly understand and reply to chat messages without exiting the game. The ...
General Introduction Shandu is an open source artificial intelligence-based research system hosted on GitHub and created by developer jolovicdev. It utilizes LangChain and LangGraph technologies and is designed to provide users with automated, comprehensive and efficient research capabilities on topics. Unlike traditional single search worker...
Comprehensive Introduction MTEB (Massive Text Embedding Benchmark) is an open source project developed by the embeddings-benchmark team and hosted on GitHub, aiming to provide comprehensive performance evaluation for text embedding models. It covers 8 major task types, including classification, clustering, retrieval...
General Introduction Wan2.1 is a suite of video generation tools developed by the Wan-Video team and open-sourced on GitHub, focusing on pushing the boundaries of video creation through artificial intelligence technologies. It is based on an advanced diffusion converter architecture and integrates a unique time-varying self-encoder (Wan-VAE) that supports...