The Best Agent Harness. Meet Sisyphus: The Batteries-Included Agent that codes like you.

Professional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).专业的 Antigravity 账号管理与切换工具。为 Antigravity 提供一键无缝账号切…

NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation

开源SSL证书管理工具；全自动证书申请、更新、续期；通配符证书，泛域名证书申请；证书自动化部署到阿里云、腾讯云、主机、群晖、宝塔；https证书，pfx证书，der证书，TLS证书，nginx证书自动续签自动部署

ProxyLLM是一款本地 Electron 应用，通过捕获浏览器会话把多种 LLM网站的能力统一为 OpenAI 兼容 API, 一键应用到Claude Code (ProxyLLM is a local Electron application that captures browser sessions to unify the capabilities of multiple LLM…

Official Implementation of "MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation"

一个现代化的 Claude Code & Codex API 代理服务，提供智能负载均衡、用户管理和使用统计功能。

Bash-based Git worktree manager with editor and AI tool integration. Automates per-branch worktree creation, configuration copying, dependency installation, and workspace setup for efficient parall…

Spec-driven development (SDD) for AI coding assistants.

[DAI 2025] Beyond GPT-5: Making LLMs Cheaper and Better via Performance–Efficiency Optimized Routing

CCR 的非官方镜像

Two always-on AI peers co-drive your repository as equals. They plan, build, critique, and converge through evidence — not just talk. You stay in control via an interactive TUI or your team chat: T…

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

Gorgeous Claude Code Extend for VS Code.

Simulates Gemini CLI, Antigravity, Qwen Code, and Kiro client requests, compatible with the OpenAI API. It supports thousands of Gemini model requests per day and offers free use of the built-in Cl…

一个将ACE(Augment Context Engine) 做成MCP的项目

Presentation Slides for Developers

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution

Native Multimodal Models are World Learners

A Data Streaming Library for Efficient Neural Network Training

Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Tunnel, Mixed, HTTP)

基于 FastAPI 重构的 Grok2API，适配最新的Web调用格式，支持流式对话、图像生成、图像编辑、联网搜索、视频生成、深度思考，支持号池并发调用和自动负载均衡。

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

🚀 阿里通义千问2.5大模型逆向API【特长：六边形战士】，支持高速流式输出、无水印AI绘图、长文档解读、图像解析、联网检索、多轮对话，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

PDF2zh for Zotero | Zotero PDF中文翻译插件

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

[NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think