Tools for OpenDataArena: Fair, Open, and Transparent Arena for Data

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。 AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测。支持 Docker 一键部署，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。⭐

[ICLR 2025 Oral] Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Web-Bench is a benchmark designed to evaluate the performance of LLMs in actual Web development.

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

SWE-bench: Can Language Models Resolve Real-world Github Issues?

A benchmark for LLMs on complicated tasks in the terminal

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

Kimi CLI is your next CLI agent.

Create and modify Word documents with Python

🔧 Electron based open source toolbox, free integration of rich plug-ins. 基于 electron 的开源工具箱，自由集成丰富插件。

Your API ⇒ Paid MCP. Instantly.

vsag is a vector indexing library used for similarity search.

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Background Music, a macOS audio utility: automatically pause your music, set individual apps' volumes and record system audio.

Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.

Integrate the DeepSeek API into popular softwares

💫 Toolkit to help you get started with Spec-Driven Development

Multilingual Document Layout Parsing in a Single Vision-Language Model

IndexTTS Voice Cloning: Supports two-person dialogue

Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.

Open-Source Frontier Voice AI

A cross-platform bilibili toolbox. 跨平台哔哩哔哩工具箱，支持下载视频、番剧等等各类资源

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

Official implementation of AnimateDiff.