DeepSeek Harness: Everything is a Plugin.

🔥 Seata is an easy-to-use, high-performance, open source distributed transaction solution.

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

The fastest and simplest library for SQLite3 in Node.js.

A vector search SQLite extension that runs anywhere!

Headless CLI client for stateful Agent Client Protocol (ACP) sessions

Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

An incremental parsing system for programming tools

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

OpenClaw 中文文档站 | AI 智能体框架 源码剖析 安装教程 | WhatsApp Telegram Discord 飞书 多通道机器人

The agent that grows with you

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

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

from vibe coding to agentic engineering - practice makes claude perfect

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

🌈 React for interactive command-line apps

TypeScript-first schema validation with static type inference

A meticulous HTTP client for the JVM, Android, and GraalVM.

Upserts, Deletes And Incremental Processing on Big Data.

Distributed high performance task scheduling framework

Enterprise job scheduling middleware with distributed computing ability.

Code for Quartz Scheduler

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Train your Agent model via our easy and efficient framework

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…

Evaluation and Tracking for LLM Experiments and AI Agents